AI Cookbooks Overview
EvalsAPI_Audio_Inputs.ipynb from openai-cookbook
Summary: This cookbook demonstrates the use of OpenAI’s Evals framework for evaluating audio-based tasks, allowing for grading of model-generated audio responses against reference answers. It highlights the ability to work directly with audio inputs, enhancing workflows in scenarios like customer support.
| Tags: Evals API, audio evaluation, model grading, big_bench_audio, OpenAI | Task Categories: evaluation,multimodal |
Last modified: 2025-09-02
voice_translation_into_different_languages_using_GPT-4o.ipynb from openai-cookbook
Summary: This cookbook provides a guide for translating and dubbing audio content from English to Hindi using OpenAI’s GPT-4o audio modality API. It simplifies the process by allowing direct audio input and output, eliminating the need for intermediate text processing.
| Tags: audio-translation, dubbing, GPT-4o, multimodal, API-integration, evaluation | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
steering_tts.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use OpenAI’s audio chat completions to generate dynamic text-to-speech (TTS) audio with specific instructions for tone, accent, and speed. It showcases the flexibility of the API in creating context-appropriate audio outputs for various applications, including educational settings.
| Tags: text-to-speech, audio generation, dynamic audio, OpenAI, educational applications, multimodal, API | Task Categories: multimodal |
Last modified: 2025-08-31
Getting_started_with_Zilliz_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a guide for generating embeddings of book descriptions using OpenAI and utilizing those embeddings within Zilliz to find relevant books. It includes setup instructions, code for embedding, and querying the database for book recommendations.
| Tags: embeddings, Zilliz, OpenAI, book search, data processing, vector databases, HuggingFace | Task Categories: rag |
Last modified: 2025-08-31
Filtered_search_with_Zilliz_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to generate embeddings for movie descriptions using OpenAI and utilize those embeddings within Zilliz to perform filtered searches for relevant movies. It provides a practical example of integrating various libraries to manage and query a dataset effectively.
| Tags: embeddings, Zilliz, OpenAI, movie-search, HuggingFace | Task Categories: rag |
Last modified: 2025-08-31
question-answering-with-weaviate-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to setting up a Weaviate instance integrated with OpenAI for question answering using vectorized data. It covers the installation of necessary libraries, schema configuration, data importation, and querying capabilities.
| Tags: Weaviate, OpenAI, question-answering, vector-database, data-import, schema-configuration | Task Categories: rag |
Last modified: 2025-08-31
hybrid-search-with-weaviate-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to setting up and using Weaviate with OpenAI for hybrid search capabilities. It covers the installation of necessary libraries, configuration of data schemas, and the process of importing and querying data using vector embeddings.
| Tags: Weaviate, OpenAI, hybrid search, vector databases, data import, schema configuration | Task Categories: rag |
Last modified: 2025-08-31
getting-started-with-weaviate-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to setting up and using Weaviate with the OpenAI module for vectorized search on unvectorized data. It covers the installation of necessary libraries, schema configuration, data import, and querying processes.
| Tags: Weaviate, OpenAI, vector search, data import, schema configuration, semantic search, embeddings | Task Categories: rag |
Last modified: 2025-08-31
generative-search-with-weaviate-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides practical examples of using Weaviate with the Generative OpenAI module for performing generative search on data stored in Weaviate. It guides users through the setup and execution of queries leveraging OpenAI’s capabilities.
| Tags: weaviate, openai, generative-search, api-integration, data-query | Task Categories: rag,summarization |
Last modified: 2025-08-31
Using_Weaviate_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to using Weaviate for embedding search, demonstrating how to download, embed, index, and search data using vector databases. It serves as a practical resource for implementing embeddings in secure and scalable environments for various applications such as chatbots and topic modeling.
| Tags: Weaviate, embeddings, vector database, semantic search, OpenAI | Task Categories: rag,other |
Last modified: 2025-08-31
Using_Typesense_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to using Typesense for embedding search, demonstrating how to download, embed, index, and query data using a vector database. It is aimed at users looking to implement secure and scalable solutions for searching embeddings in production environments.
| Tags: Typesense, embeddings, vector database, semantic search, OpenAI, data indexing, production use cases | Task Categories: rag,other |
Last modified: 2025-08-31
QA_with_Langchain_Tair_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to implementing a Question Answering system using Langchain, Tair, and OpenAI embeddings. It covers the end-to-end process of calculating embeddings, storing them in a knowledge base, and querying for answers using a language model.
| Tags: question-answering, langchain, tair, openai, embeddings, vector-database | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_Tair_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide on using Tair as a vector database for storing and querying OpenAI embeddings. It covers the entire process from embedding generation to nearest neighbor search using Tair’s capabilities.
| Tags: Tair, OpenAI, vector-database, embeddings, nearest-neighbor-search, data-storage, cloud-database | Task Categories: rag |
Last modified: 2025-08-31
redisqna.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to integrate Redis with OpenAI’s API to create a high-speed context memory for chat applications. It provides examples of how to set up the environment, create embeddings, and perform queries using Redis.
| Tags: redis, openai, context-memory, embeddings, chatbot, vector-database, python | Task Categories: rag |
Last modified: 2025-08-31
redisjson.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use Redis with OpenAI to store and manage text vectors in JSON format, enabling efficient retrieval and processing of embeddings. It provides practical examples of creating text embeddings and integrating them with Redis functionalities.
| Tags: redis, openai, json, vector-databases, embeddings, data-storage, python | Task Categories: other |
Last modified: 2025-08-31
redis-hybrid-query-examples.ipynb from openai-cookbook
Summary: This cookbook provides a guide on using Redis as a vector database in conjunction with OpenAI embeddings to perform hybrid queries that combine vector similarity and traditional search capabilities. It demonstrates how to set up the environment, index data, and execute queries effectively.
| Tags: Redis, OpenAI, vector-database, hybrid-queries, data-indexing, search-optimization | Task Categories: other |
Last modified: 2025-08-31
getting-started-with-redis-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on using Redis as a vector database in conjunction with OpenAI embeddings. It covers the setup, indexing, and querying of vector data using the RediSearch module in Redis.
| Tags: Redis, OpenAI, vector-database, RediSearch, embedding, data-indexing, search | Task Categories: rag |
Last modified: 2025-08-31
Using_Redis_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on using Redis as a vector database for embedding search, enabling users to efficiently store and query embeddings derived from unstructured data. It covers setup, data loading, indexing, and searching processes, making it suitable for production use cases such as chatbots and topic modeling.
| Tags: vector-database, embeddings, Redis, search, OpenAI | Task Categories: rag,other |
Last modified: 2025-08-31
Using_Qdrant_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on using Qdrant for embedding search, detailing the process of downloading data, embedding it, and indexing it in a vector database for efficient searching. It is designed for users looking to implement embeddings in secure and scalable environments for various applications such as chatbots and topic modeling.
| Tags: Qdrant, embeddings, vector database, semantic search, OpenAI | Task Categories: rag,other |
Last modified: 2025-08-31
QA_with_Langchain_Qdrant_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to implement a Question Answering system using Langchain, Qdrant, and OpenAI embeddings. It guides users through the process of calculating embeddings, storing them in a vector database, and querying them to retrieve answers from a knowledge base.
| Tags: question-answering, langchain, qdrant, openai, embeddings, vector-database, api-integration | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_Qdrant_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide on using Qdrant as a vector database for managing OpenAI embeddings. It covers the process of storing embeddings, querying them, and performing nearest neighbor searches.
| Tags: Qdrant, OpenAI, vector-database, embeddings, nearest-neighbor-search, data-management | Task Categories: rag |
Last modified: 2025-08-31
Using_vision_modality_for_RAG_with_Pinecone.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to implementing Retrieval-Augmented Generation (RAG) systems that effectively handle documents with complex visual elements, utilizing the vision modality for enhanced information extraction and interpretation.
| Tags: rag, data-extraction, image-processing, semantic-search, Pinecone, GPT-4o, document-analysis | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Using_Pinecone_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to using Pinecone for embedding search, demonstrating how to download data, embed it, and index it for efficient searching. It is designed for users looking to implement vector databases for various AI applications such as chatbots and topic modeling.
| Tags: Pinecone, embeddings, vector database, semantic search, OpenAI, data indexing, AI applications | Task Categories: rag,other |
Last modified: 2025-08-31
Semantic_Search.ipynb from openai-cookbook
Summary: This cookbook provides a guide on how to use the OpenAI Embedding API to generate language embeddings and index them in the Pinecone vector database for efficient semantic search. It covers the entire workflow from embedding text data to querying for semantically similar documents.
| Tags: semantic-search, NLP, vector-database, OpenAI, Pinecone, embeddings, question-answering | Task Categories: rag |
Last modified: 2025-08-31
Gen_QA.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to enhance the capabilities of GPT-3 by integrating it with Pinecone for retrieval-augmented generation (RAG). It provides practical examples of querying relevant contexts to improve the accuracy of generated answers.
| Tags: rag, openai, pinecone, question-answering, embedding | Task Categories: rag |
Last modified: 2025-08-31
GPT4_Retrieval_Augmentation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize retrieval-augmented generation (RAG) with GPT-4 and Pinecone to enhance responses based on relevant context from external data sources. It provides a step-by-step guide for loading documents, creating embeddings, and querying the model effectively.
| Tags: rag, Pinecone, GPT-4, langchain, embedding, document-retrieval, AI-cookbook | Task Categories: rag |
Last modified: 2025-08-31
neon-postgres-vector-search-pgvector.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to using Neon Serverless Postgres as a vector database for storing and querying OpenAI embeddings. It covers the installation of necessary libraries, database setup, and executing vector similarity searches using embeddings generated by the OpenAI API.
| Tags: vector-database, OpenAI, Neon, embeddings, Postgres, similarity-search, pgvector | Task Categories: rag |
Last modified: 2025-08-31
Using_MyScale_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on how to use MyScale for embedding search, including downloading data, embedding it, and indexing it in a vector database. It aims to help users implement secure and scalable solutions for various AI use cases such as chatbots and topic modeling.
| Tags: vector-database, embeddings, MyScale, OpenAI, semantic-search, data-indexing, AI-use-cases | Task Categories: rag,other |
Last modified: 2025-08-31
Getting_started_with_MyScale_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on utilizing MyScale as a vector database for managing OpenAI embeddings, enabling efficient storage and retrieval of vectorized data. It includes steps for setting up the environment, creating a database, and querying for similar content based on user input.
| Tags: vector-database, OpenAI, MyScale, embedding, nearest-neighbor-search, data-storage, SQL | Task Categories: rag |
Last modified: 2025-08-31
semantic_search_using_mongodb_atlas_vector_search.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a semantic search application using OpenAI’s embedding capabilities and MongoDB Atlas vector search. It provides a step-by-step guide for setting up the environment, generating embeddings for movie plots, and querying the database for relevant results.
| Tags: semantic search, OpenAI, MongoDB Atlas, vector search, embeddings, database integration, Python | Task Categories: other |
Last modified: 2025-08-31
Getting_started_with_Milvus_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to generate embeddings for book descriptions using OpenAI and utilize those embeddings within the Milvus vector database to find relevant books. It provides a step-by-step guide on setting up the environment, embedding data, and querying the database for results.
| Tags: OpenAI, Milvus, embeddings, vector-database, book-search, datasets, python | Task Categories: rag |
Last modified: 2025-08-31
Filtered_search_with_Milvus_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to generate embeddings for movie descriptions using OpenAI’s API and utilize those embeddings within the Milvus vector database for filtered search functionality. It provides a practical example of integrating AI with a database to enhance search capabilities based on metadata and content similarity.
| Tags: embeddings, Milvus, OpenAI, movie search, vector databases, metadata filtering | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_kusto_and_openai_embeddings.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide on utilizing Azure Data Explorer (Kusto) as a vector database for managing OpenAI embeddings. It demonstrates how to download, process, and query embedded data using Python and relevant libraries.
| Tags: Kusto, OpenAI, embeddings, vector database, data processing, Python, Azure | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_Hologres_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide on using Hologres as a vector database for storing and querying OpenAI embeddings. It covers the entire process from setting up the environment to performing nearest neighbor searches using embeddings.
| Tags: Hologres, OpenAI, vector-database, embeddings, nearest-neighbor-search, data-warehousing, PostgreSQL | Task Categories: rag |
Last modified: 2025-08-31
elasticsearch-semantic-search.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to index a Wikipedia vector dataset into Elasticsearch and perform semantic search using OpenAI’s embeddings. It provides a practical guide for integrating Elasticsearch with OpenAI’s API for enhanced search capabilities.
| Tags: semantic search, Elasticsearch, OpenAI, data indexing, vector databases, API integration, question answering | Task Categories: rag |
Last modified: 2025-08-31
elasticsearch-retrieval-augmented-generation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to index a Wikipedia vector dataset into Elasticsearch and perform semantic search using OpenAI’s embeddings. It further integrates the search results with OpenAI’s Chat Completions for retrieval augmented generation (RAG).
| Tags: rag, elasticsearch, openai, semantic search, data indexing, vector databases | Task Categories: rag |
Last modified: 2025-08-31
deeplake_langchain_qa.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a question answering system using LangChain, Deep Lake as a vector store, and OpenAI embeddings. It guides users through loading a dataset, initializing a vector store, adding text, and running queries.
| Tags: question-answering, langchain, deeplake, openai, vector-store, embeddings, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
hyde-with-chroma-and-openai.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building a robust question-answering system using OpenAI’s API and Chroma for embedding storage and retrieval. It demonstrates how to assess scientific claims based on evidence and improve the accuracy of responses through contextual querying.
| Tags: question-answering, embeddings, OpenAI, Chroma, data-retrieval, scientific-claims, evaluation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
Using_Chroma_for_embeddings_search.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to using Chroma for embedding search, allowing users to download, embed, index, and search data using vector databases. It is designed for those looking to implement embeddings in a secure and scalable environment for various applications such as chatbots and topic modeling.
| Tags: embeddings, vector-database, Chroma, OpenAI, semantic-search, data-indexing, machine-learning | Task Categories: rag |
Last modified: 2025-08-31
Philosophical_Quotes_cassIO.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a philosophy quote finder and generator using OpenAI’s vector embeddings and Apache Cassandra/Astra DB for data persistence. It covers the process of indexing quotes, searching for similar quotes, and generating new quotes based on user input.
| Tags: vector search, quote generation, OpenAI, Cassandra, data persistence, embedding | Task Categories: rag,other |
Last modified: 2025-08-31
Philosophical_Quotes_CQL.ipynb from openai-cookbook
Summary: This cookbook provides a guide to building a philosophy quote finder and generator using OpenAI’s vector embeddings and Apache Cassandra or DataStax Astra DB for data persistence. It demonstrates how to evaluate, store, and search for quotes using vector similarity search techniques.
| Tags: vector search, Cassandra, OpenAI, quote generation, data persistence, embedding | Task Categories: rag,other |
Last modified: 2025-08-31
Philosophical_Quotes_AstraPy.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a philosophy quote finder and generator using OpenAI’s vector embeddings and Astra DB for data persistence. It guides users through the process of indexing quotes, performing vector similarity searches, and generating new quotes based on existing ones.
| Tags: vector embeddings, quote generation, Astra DB, OpenAI, semantic search, philosophy | Task Categories: rag,other |
Last modified: 2025-08-31
Getting_started_with_azure_ai_search_and_openai.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on using Azure AI Search as a vector database for OpenAI embeddings, enabling developers to build rich search experiences over diverse content. It includes step-by-step instructions for setting up the environment, configuring the search service, and performing vector and hybrid searches.
| Tags: Azure AI Search, OpenAI, vector database, search integration, embeddings, cloud services | Task Categories: rag |
Last modified: 2025-08-31
QA_with_Langchain_AnalyticDB_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a Question Answering system using Langchain, AnalyticDB, and OpenAI embeddings. It covers the end-to-end process of embedding calculations, storage, and querying to retrieve answers from a knowledge base.
| Tags: question-answering, langchain, OpenAI, AnalyticDB, embeddings, vector-database, rag | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_AnalyticDB_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for using AnalyticDB as a vector database to store and query OpenAI embeddings. It covers the entire process from setting up the database to executing queries for nearest neighbor searches.
| Tags: OpenAI, AnalyticDB, vector-database, embeddings, data-retrieval, PostgreSQL, nearest-neighbor-search | Task Categories: rag |
Last modified: 2025-08-31
OpenAI_wikipedia_semantic_search.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build an interactive Q&A application using SingleStoreDB for vector storage and OpenAI’s ChatGPT for generating responses. It provides a step-by-step guide to querying data and integrating embeddings for enhanced search capabilities.
| Tags: Q&A, semantic-search, vector-database, OpenAI, SingleStoreDB, embeddings, data-querying | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_PolarDB_and_OpenAI.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide for using PolarDB-PG as a vector database to store and query OpenAI embeddings. It covers the entire process from setting up the database to executing queries using embedded vectors.
| Tags: OpenAI, PolarDB, vector-database, embeddings, PostgreSQL, data-storage, nearest-neighbor-search | Task Categories: rag |
Last modified: 2025-08-31
financial_document_analysis_with_llamaindex.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to perform financial analysis on 10-K documents using the LlamaIndex framework, enabling users to extract and query financial data efficiently. It includes examples of loading documents, creating query engines, and performing comparisons between different companies’ financials.
| Tags: financial analysis, 10-K, data extraction, query engine, LlamaIndex, Python, langchain | Task Categories: rag,other |
Last modified: 2025-08-31
Web_search_with_google_api_bring_your_own_browser_tool.ipynb from openai-cookbook
Summary: This cookbook provides a guide to building a Bring Your Own Browser (BYOB) tool that integrates web search capabilities with a large language model to generate up-to-date responses. It demonstrates how to use Google’s Custom Search API to retrieve current information and summarize it using an LLM.
| Tags: rag, web-scraping, API-integration, summarization, OpenAI, Python | Task Categories: rag,summarization,agents |
Last modified: 2025-08-31
Visualizing_embeddings_with_Atlas.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to visualize food review embeddings using the Atlas tool by uploading and mapping embeddings in a web browser. It provides a step-by-step guide to loading data, processing embeddings, and interacting with the visualized data.
| Tags: embeddings, visualization, Atlas, food reviews, data analysis, Python, nomic | Task Categories: other |
Last modified: 2025-08-31
Visualizing_embeddings_in_wandb.ipynb from openai-cookbook
Summary: This cookbook provides a guide for visualizing embeddings using Weights & Biases (W&B) by logging data and utilizing dimension reduction techniques. It demonstrates how to prepare and upload embedding data for visualization in a user-friendly manner.
| Tags: embeddings, visualization, weights-and-biases, data-logging, dimension-reduction | Task Categories: other |
Last modified: 2025-08-31
Visualizing_embeddings_in_Kangas.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to visualize embeddings using the Kangas library in a Jupyter Notebook. It provides a step-by-step guide to setting up the environment, loading data, and creating a DataGrid for interactive exploration of embeddings.
| Tags: embeddings, data-visualization, kangas, jupyter-notebook, data-science, open-source | Task Categories: multimodal |
Last modified: 2025-08-31
Openai_monitoring_with_wandb_weave.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to monitor OpenAI API calls using Weights & Biases (W&B) Weave, allowing users to track usage metrics and visualize data. It provides a step-by-step guide for setting up the integration and generating insights from API interactions.
| Tags: OpenAI, W&B, monitoring, API, data-visualization, machine-learning | Task Categories: other |
Last modified: 2025-08-31
How_to_automate_S3_storage_with_functions.ipynb from openai-cookbook
Summary: This cookbook provides a guide on automating tasks related to Amazon S3 storage using OpenAI’s ChatGPT functions. It demonstrates how to perform key operations such as listing buckets, uploading and downloading files, and searching for specific files within S3 buckets.
| Tags: S3, automation, OpenAI, functions, cloud-storage, boto3 | Task Categories: agents |
Last modified: 2025-08-31
GPT_finetuning_with_wandb.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning OpenAI’s ChatGPT-3.5 and GPT-4 models using Weights & Biases for experiment tracking and dataset management. It includes code examples for preparing datasets, validating data formats, and logging training artifacts.
| Tags: fine-tuning, OpenAI, Weights & Biases, legal dataset, experiment tracking | Task Categories: fine-tuning |
Last modified: 2025-08-31
selecting_a_model_based_on_stripe_conversion.ipynb from openai-cookbook
Summary: This cookbook provides a practical evaluation approach for startups to select AI models based on their impact on payment conversion rates, specifically using Stripe as a payment processor. It emphasizes the importance of real-world A/B testing over traditional benchmarks for model selection.
| Tags: A/B testing, model evaluation, conversion rates, startups, Stripe, AI models | Task Categories: evaluation |
Last modified: 2025-08-31
responses_example.ipynb from openai-cookbook
Summary: This AI cookbook provides practical examples and guidance on using the Responses API to build advanced AI applications that can handle multi-turn conversations and integrate various tools. It emphasizes the API’s stateful nature and its ability to work with different data types, including text and images.
| Tags: Responses API, multi-turn interactions, web search, image processing, AI applications | Task Categories: multimodal,agents |
Last modified: 2025-08-31
responses_api_tool_orchestration.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building dynamic workflows using OpenAI’s Responses API, focusing on a Retrieval-Augmented Generation (RAG) approach. It demonstrates how to effectively route user queries to various tools, including external vector databases, to generate accurate and context-aware responses.
| Tags: rag, openai, responses-api, document-retrieval, medical-dataset, tool-orchestration, embedding | Task Categories: rag,other |
Last modified: 2025-08-31
reasoning_items.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to effectively utilize OpenAI’s Responses API with the latest reasoning models to enhance application performance and efficiency. It provides practical examples of function calling and reasoning integration.
| Tags: responses-api, reasoning, function-calling, openai, api-integration, weather-forecasting | Task Categories: agents,other |
Last modified: 2025-08-31
reasoning_function_calls.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize OpenAI’s reasoning models for managing function calls and complex reasoning tasks through the Responses API. It provides practical examples of invoking functions and handling multi-step reasoning in AI applications.
| Tags: function-calling, reasoning, API, OpenAI, multi-step tasks, coding | Task Categories: agents,rag |
Last modified: 2025-08-31
temporal_agents_with_knowledge_graphs.ipynb from openai-cookbook
Summary: This AI cookbook provides a framework for processing and analyzing earnings call transcripts using semantic chunking and embeddings. It facilitates the extraction of structured information from unstructured text data, enabling better insights into company performance.
| Tags: earnings-call, semantic-chunking, data-extraction, openai, pydantic, text-analysis | Task Categories: agents,other |
Last modified: 2025-08-31
Appendix.ipynb from openai-cookbook
Summary: This appendix provides an in-depth exploration of implementing temporal agents using knowledge graphs, focusing on transitioning from prototype to production. It serves as a resource for developers looking to enhance their understanding of temporal agents within the context of knowledge graphs.
| Tags: temporal agents, knowledge graphs, prototype to production, AI cookbook, development | Task Categories: agents,other |
Last modified: 2025-08-31
model_selection_guide.ipynb from openai-cookbook
Summary: This cookbook serves as a practical guide for selecting, prompting, and deploying the right OpenAI model for specific workloads, focusing on real-world applications and providing actionable decision frameworks.
| Tags: model-selection, deployment, real-world-use-cases, openai, guidance | Task Categories: rag,agents,other |
Last modified: 2025-08-31
mcp_powered_agents_cookbook.ipynb from openai-cookbook
Summary: This cookbook provides a modular approach to building voice-enabled agents using the Model Context Protocol (MCP) and the OpenAI Agents SDK, specifically tailored for the insurance industry. It demonstrates how to create a voice assistant that can interact with users and provide information about insurance plans.
| Tags: voice-assistant, MCP, insurance, agent-workflows, openai-agents, audio-processing | Task Categories: agents,rag |
Last modified: 2025-08-31
receipt_inspection.ipynb from openai-cookbook
Summary: This cookbook provides a practical guide for building an eval-driven system to automate receipt analysis, focusing on extracting structured data from images of receipts and evaluating the need for audits based on defined criteria.
| Tags: receipt-parsing, data-extraction, audit-evaluation, eval-driven, machine-learning | Task Categories: evaluation,multimodal |
Last modified: 2025-08-31
Secure_code_interpreter_tool_for_LLM_agents.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building a custom code interpreter tool for LLM agents, focusing on dynamic tool generation and execution using the o3-mini model. It emphasizes the flexibility and adaptability of LLMs in data analysis and code execution tasks.
| Tags: dynamic-tool-generation, data-analysis, python-execution, docker, llm-agents, o3-mini, code-interpreter | Task Categories: agents,rag |
Last modified: 2025-08-31
Using_reasoning_for_routine_generation.ipynb from openai-cookbook
Summary: This cookbook provides a method for transforming customer service knowledge base articles into structured routines that can be executed by a language model, enhancing automated customer support capabilities.
| Tags: routine-generation, customer-service, LLM, automation, knowledge-base, OpenAI | Task Categories: agents,rag |
Last modified: 2025-08-31
Using_reasoning_for_data_validation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use the o1 model for data validation in synthetic medical datasets, focusing on identifying inconsistencies and assessing data quality through reasoning.
| Tags: data-validation, synthetic-data, medical-datasets, AI-assistant, o1-model, data-quality, reasoning | Task Categories: evaluation |
Last modified: 2025-08-31
Using_chained_calls_for_o1_structured_outputs.ipynb from openai-cookbook
Summary: This cookbook provides guidance on using the OpenAI API to fetch data from external sources and analyze it for business insights, specifically focusing on how AI can benefit large corporations. It demonstrates how to structure prompts to elicit JSON responses from the o1 model.
| Tags: AI, business-analysis, data-fetching, JSON, structured-outputs, openai | Task Categories: rag,other |
Last modified: 2025-08-31
o3o4-mini_prompting_guide.ipynb from openai-cookbook
Summary: This cookbook provides guidance on utilizing the o3/o4-mini models for effective function calling and reasoning in AI applications, particularly for tasks like weather retrieval.
| Tags: function-calling, AI, weather-api, prompt-engineering, openai, o3, o4 | Task Categories: agents,other |
Last modified: 2025-08-31
image_understanding_with_rag.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using OpenAI’s Vision and Responses APIs, focusing on analyzing customer experiences through multimodal data.
| Tags: rag, image-understanding, customer-feedback, synthetic-data, openai | Task Categories: rag,multimodal,evaluation |
Last modified: 2025-08-31
Vision_Fine_tuning_on_GPT4o_for_Visual_Question_Answering.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning the GPT-4o model for visual question answering using multimodal inputs, specifically focusing on images of books. It outlines the steps for preparing datasets, training the model, and generating accurate answers based on visual content.
| Tags: fine-tuning, visual-question-answering, multimodal, image-processing, GPT-4o, dataset-preparation, AI-cookbook | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
Using_GPT4_Vision_With_Function_Calling.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize GPT-4o’s vision capabilities with function calling to create a customer service assistant that analyzes package images and processes delivery exceptions accordingly.
| Tags: function-calling, image-analysis, customer-service, refund-processing, replacement-orders, multimodal | Task Categories: agents,multimodal |
Last modified: 2025-08-31
mcp_tool_guide.ipynb from openai-cookbook
Summary: This cookbook provides guidance on using the Model Context Protocol (MCP) tool to streamline interactions with external services, particularly in commerce and data analysis applications.
| Tags: MCP, API integration, data analysis, e-commerce, automation, tool orchestration | Task Categories: agents,rag,other |
Last modified: 2025-08-31
databricks_mcp_cookbook.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building a supply-chain copilot using the OpenAI Agent SDK and Databricks Managed MCP, enabling real-time querying of enterprise data for improved decision-making in supply-chain operations.
| Tags: supply-chain, databricks, openai, agent-sdk, real-time-querying, data-analytics, mcp | Task Categories: agents |
Last modified: 2025-08-31
introduction_to_gpt4o.ipynb from openai-cookbook
Summary: This cookbook provides examples of using the GPT-4o and GPT-4o mini models for various tasks, including math assistance, video processing, and audio transcription. It demonstrates how to handle multimodal inputs and outputs effectively.
| Tags: multimodal, video-processing, audio-transcription, GPT-4o, OpenAI, image-display | Task Categories: multimodal,summarization,evaluation |
Last modified: 2025-08-31
gpt4-1_prompting_guide.ipynb from openai-cookbook
Summary: The AI cookbook provides a comprehensive guide for utilizing the GPT-4.1 model in coding tasks, emphasizing a structured approach to problem-solving and debugging. It includes detailed workflows and strategies for effectively leveraging the model’s capabilities in an agentic context.
| Tags: gpt-4.1, problem-solving, debugging, agentic workflows, coding, AI engineering | Task Categories: agents |
Last modified: 2025-08-31
prompt-optimization-cookbook.ipynb from openai-cookbook
Summary: This cookbook provides guidance on optimizing prompts for the GPT-5 model, focusing on enhancing performance in coding and agentic tasks. It includes practical examples and best practices for prompt crafting and migration.
| Tags: prompt-optimization, GPT-5, coding, agentic-tasks, best-practices, migration | Task Categories: agents,evaluation |
Last modified: 2025-08-31
gpt-5_prompting_guide.ipynb from openai-cookbook
Summary: The GPT-5 prompting guide provides best practices and strategies for effectively utilizing the GPT-5 model in various applications, particularly focusing on agentic task performance and coding. It emphasizes the importance of tailored prompting techniques to enhance model outputs and efficiency.
| Tags: GPT-5, prompting, agentic tasks, coding, model optimization, best practices | Task Categories: agents |
Last modified: 2025-08-31
gpt-5_new_params_and_tools.ipynb from openai-cookbook
Summary: This AI cookbook provides examples and guidelines for utilizing the new features and parameters introduced in the GPT-5 series, including verbosity control and freeform function calling. It demonstrates how to interact with the OpenAI API to generate responses and execute code in various programming languages.
| Tags: GPT-5, OpenAI, code execution, verbosity, function calling, API integration, programming | Task Categories: other |
Last modified: 2025-08-31
gpt-5_frontend.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to leverage GPT-5 for frontend development, showcasing examples of generating websites and interactive applications using AI. It includes practical functions for creating and saving HTML content based on user prompts.
| Tags: frontend-development, GPT-5, HTML, web-design, AI-cookbook, interactive-examples, web-development | Task Categories: multimodal |
Last modified: 2025-08-31
reinforcement_finetuning_healthbench.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use OpenAI’s reinforcement fine-tuning to enhance conversational reasoning capabilities in AI models, particularly for healthcare-related question answering. It focuses on evaluating and improving model performance using specific rubrics from the HealthBench benchmark.
| Tags: reinforcement-learning, fine-tuning, healthcare, evaluation, OpenAI, conversational-AI | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
olympics-3-train-qa.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for training fine-tuned models specialized in question answering using context, question, and answer pairs. It includes methods for creating adversarial examples and applying fine-tuned models to assess and answer questions based on provided contexts.
| Tags: fine-tuning, question-answering, adversarial-examples, openai, data-preparation | Task Categories: fine-tuning,rag |
Last modified: 2025-08-31
olympics-2-create-qa.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to create a synthetic question-and-answer dataset using the OpenAI API, specifically leveraging the davinci-instruct-beta-v3 model for generating questions and answers based on provided text contexts. It also includes methods for evaluating the performance of a search model in retrieving relevant contexts for given questions.
| Tags: Q&A generation, data processing, openai, pandas, text analysis, search evaluation | Task Categories: rag,fine-tuning,other |
Last modified: 2025-08-31
olympics-1-collect-data.ipynb from openai-cookbook
Summary: This cookbook focuses on collecting and processing Wikipedia data related to the Olympic Games 2020 to create a question-answering model. It includes methods for filtering relevant titles, extracting sections, and preparing data for training a model that answers questions based on provided context.
| Tags: data-extraction, question-answering, wikipedia-api, fine-tuning, transformers | Task Categories: rag,fine-tuning |
Last modified: 2025-08-31
ft_retrieval_augmented_generation_qdrant.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on fine-tuning OpenAI models for Retrieval Augmented Generation (RAG) using the SQuAD dataset and integrating Qdrant to enhance model performance. It covers data preparation, model training, and evaluation techniques to improve the accuracy of generated answers.
| Tags: fine-tuning, RAG, OpenAI, Qdrant, SQuAD, evaluation, machine learning | Task Categories: rag,fine-tuning,evaluation |
Last modified: 2025-08-31
web-search-evaluation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to evaluate a model’s ability to retrieve correct answers from the web using the OpenAI Evals framework with a custom dataset. It provides a structured approach to assessing web search quality through a series of defined queries and expected answers.
| Tags: evaluation, web-search, openai, dataset, quality-assessment, llm | Task Categories: evaluation |
Last modified: 2025-08-31
tools-evaluation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to measure and enhance a model’s capability to extract structured information, specifically symbols from Python code, using tool evaluation with OpenAI’s Evals. It provides a setup guide, dataset creation, and grading rubric for evaluating the extraction quality.
| Tags: evaluation, data-extraction, openai, python, symbols, tool-evaluation | Task Categories: evaluation |
Last modified: 2025-08-31
structured-outputs-evaluation.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to using the OpenAI Evals framework for testing and grading tasks that require large language models to produce structured outputs, such as code symbol extraction.
| Tags: evaluation, structured-outputs, code-extraction, automated-testing, openai | Task Categories: evaluation |
Last modified: 2025-08-31
responses-evaluation.ipynb from openai-cookbook
Summary: This cookbook provides a framework for evaluating AI models by comparing their performance in explaining code files. It utilizes the OpenAI SDK to generate responses and assess their quality based on specific scoring dimensions.
| Tags: evaluation, code-explanation, AI-model-comparison, OpenAI-SDK, response-evaluation | Task Categories: evaluation |
Last modified: 2025-08-31
regression.ipynb from openai-cookbook
Summary: This cookbook provides a framework for evaluating the performance of a push notification summarization model using OpenAI’s API. It includes examples of how to set up evaluations and run tests to detect regressions in model performance.
| Tags: push notifications, summarization, evaluation, openai, model testing, regression | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
mcp_eval_notebook.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to evaluate the performance of different AI models using a custom dataset focused on the tiktoken GitHub repository. It utilizes the OpenAI Evals framework to compare the capabilities of models like gpt-4.1 and o4-mini in providing accurate answers.
| Tags: evaluation, MCP, OpenAI, tiktoken, Q&A, model-comparison, custom-dataset | Task Categories: evaluation |
Last modified: 2025-08-31
completion-monitoring.ipynb from openai-cookbook
Summary: This cookbook provides a framework for evaluating the performance of push notification summarization using different prompt versions. It demonstrates how to monitor and grade the effectiveness of AI-generated summaries in a production environment.
| Tags: push notifications, summarization, evaluation, AI monitoring, chat completions | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
bulk-experimentation.ipynb from openai-cookbook
Summary: This cookbook provides a framework for evaluating the performance of push notification summarization models using various prompts and models. It focuses on testing and improving the summarization capabilities of AI models through structured evaluations.
| Tags: push notifications, summarization, evaluation, openai, pydantic, model testing, API integration | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
EvalsAPI_Image_Inputs.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize OpenAI’s Evals framework to evaluate model-generated responses to image prompts by grading their alignment with reference answers. It focuses on generating appropriate responses and assessing their quality against provided criteria.
| Tags: image-evaluation, model-grading, openai, evals-api, multimodal, data-science | Task Categories: evaluation,multimodal |
Last modified: 2025-08-31
How_to_evaluate_LLMs_for_SQL_generation.ipynb from openai-cookbook
Summary: This cookbook provides a framework for evaluating large language models (LLMs) specifically for SQL generation from natural language queries, focusing on unit testing and evaluation metrics to ensure consistency and correctness.
| Tags: SQL generation, evaluation, unit testing, LLMs, data validation, code execution | Task Categories: evaluation |
Last modified: 2025-08-31
How_to_eval_abstractive_summarization.ipynb from openai-cookbook
Summary: This cookbook provides techniques for evaluating the quality of abstractive summarization using traditional metrics like ROUGE and BERTScore, as well as novel approaches leveraging large language models. It includes practical examples and code implementations for scoring summaries against reference texts.
| Tags: evaluation, summarization, ROUGE, BERTScore, gpt-4, text-analysis | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
Getting_Started_with_OpenAI_Evals.ipynb from openai-cookbook
Summary: This cookbook provides guidance on evaluating large language models (LLMs) using the OpenAI Evals framework, focusing on creating and running evaluations to assess model performance.
| Tags: evaluation, LLM, OpenAI, SQL, data-generation, model-grading | Task Categories: evaluation |
Last modified: 2025-08-31
Evaluate_RAG_with_LlamaIndex.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building and evaluating a Retrieval-Augmented Generation (RAG) pipeline using LlamaIndex, focusing on integrating specific data into language model responses.
| Tags: rag, llama-index, evaluation, openai, data-integration, asynchronous | Task Categories: rag,evaluation |
Last modified: 2025-08-31
introduction_to_deep_research_api_agents.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building agentic research workflows using the OpenAI Deep Research API and Agents SDK, focusing on orchestrating multi-agent pipelines and enhancing user query outputs. It emphasizes the importance of structured research applications and offers practical examples for implementation.
| Tags: deep research, agents, workflow orchestration, web search, MCP integration, API usage | Task Categories: agents,rag |
Last modified: 2025-08-31
introduction_to_deep_research_api.ipynb from openai-cookbook
Summary: The AI cookbook provides a comprehensive guide to using the Deep Research API for automating complex research workflows, enabling users to generate structured, citation-rich reports from high-level queries. It emphasizes the importance of data-driven insights and the use of reliable sources for healthcare analysis.
| Tags: deep research, API, health economics, data analysis, automation | Task Categories: rag,agents |
Last modified: 2025-08-31
Image_generations_edits_and_variations_with_DALL-E.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on how to use OpenAI’s DALL·E API for generating, editing, and creating variations of images based on text prompts. It includes code examples and explanations for setting up the environment and making API calls.
| Tags: image-generation, DALL-E, API, image-editing, variations, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
How_to_create_dynamic_masks_with_DALL-E_and_Segment_Anything.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use the Segment Anything model in conjunction with DALL·E to create dynamic masks for image editing. It guides users through the process of generating images, creating masks, and inpainting specified areas with new content.
| Tags: image-generation, mask-creation, DALL-E, Segment Anything, fashion-design, AI-tools | Task Categories: multimodal |
Last modified: 2025-08-31
custom_image_embedding_search.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to integrate CLIP embeddings with GPT-4 Vision for enhanced multimodal retrieval-augmented generation (RAG) tasks. It showcases the process of embedding images for similarity search to improve the accuracy of information retrieval based on user queries.
| Tags: rag, multimodal, image-retrieval, CLIP, GPT-4, similarity-search | Task Categories: rag,multimodal |
Last modified: 2025-08-31
completions_usage_api.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to retrieving and visualizing usage data from the OpenAI Completions Usage API. It demonstrates how to parse JSON responses into a pandas DataFrame and visualize token usage over time using matplotlib, with options for grouping by model and project.
| Tags: API, data-visualization, pandas, matplotlib, OpenAI, usage-analysis | Task Categories: other |
Last modified: 2025-08-31
jira-github.ipynb from openai-cookbook
Summary: This cookbook provides a practical guide to automating workflows between Jira and GitHub using the codex-cli agent within GitHub Actions. It outlines the steps to set up automation that triggers pull requests and updates Jira issues with minimal manual intervention.
| Tags: automation, Jira, GitHub, codex-cli, workflow | Task Categories: agents |
Last modified: 2025-08-31
gpt-action-pinecone-retool-rag.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide for integrating Pinecone as a vector database with OpenAI embeddings, enabling efficient querying and interaction with ChatGPT. It demonstrates how to set up a REST endpoint using Retool for seamless AI-powered applications.
| Tags: Pinecone, OpenAI, ChatGPT, vector-database, REST API, low-code, embedding | Task Categories: rag |
Last modified: 2025-08-31
Getting_started_with_bigquery_vector_search_and_openai.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for integrating Google Cloud BigQuery with OpenAI embeddings to create a retrieval-augmented generation (RAG) infrastructure. It outlines the steps to set up the environment, prepare data, and create a Google Cloud Function for use with ChatGPT.
| Tags: gcp, bigquery, openai, embeddings, cloud-functions, rag, data-integration | Task Categories: rag |
Last modified: 2025-08-31
Azure_AI_Search_with_Azure_Functions_and_GPT_Actions_in_ChatGPT.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide on using Azure AI Search as a vector database integrated with OpenAI embeddings, along with creating an Azure Function to connect with ChatGPT. It is designed for users looking to set up a Retrieval-Augmented Generation (RAG) infrastructure within Azure.
| Tags: azure, openai, search, functions, rag, integration | Task Categories: rag |
Last modified: 2025-08-31
gpt_middleware_azure_function.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create middleware that connects GPT Actions to specific applications using Azure Functions. It includes instructions and examples to facilitate the integration process.
| Tags: GPT Actions, Azure Functions, middleware, integration, developers, API | Task Categories: agents |
Last modified: 2025-08-31
gpt_middleware_aws_function.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on building an AWS Lambda function that connects to a GPT Action, focusing on OAuth protection and integration with a sample application. It utilizes AWS SAM to set up the serverless architecture necessary for deployment.
| Tags: AWS Lambda, GPT Actions, OAuth, serverless, AWS SAM, middleware | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_zapier.ipynb from openai-cookbook
Summary: The ‘gpt_action_zapier.ipynb’ cookbook provides a guide for developers to create GPT Actions specifically for integration with the Zapier platform. It includes foundational information and links to resources for building these actions effectively.
| Tags: GPT Actions, Zapier, integration, developers, automation | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_sql_database.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to enable ChatGPT to query a PostgreSQL database through a middleware application, facilitating data analysis and retrieval without requiring users to write SQL queries themselves.
| Tags: SQL, PostgreSQL, middleware, data-analysis, API | Task Categories: rag,agents |
Last modified: 2025-08-31
gpt_action_snowflake_middleware.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create a middleware function that connects ChatGPT with a Snowflake Data Warehouse, allowing SQL queries to be executed and results returned as CSV files. It outlines the necessary Azure Functions setup and integration steps for effective data analysis.
| Tags: Snowflake, Azure Functions, SQL execution, CSV generation, middleware | Task Categories: agents,other |
Last modified: 2025-08-31
gpt_action_snowflake_direct.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for developers to create a GPT Action that connects to a Snowflake Data Warehouse, allowing users to execute SQL queries based on their questions. It outlines the steps for querying data schema and constructing SQL statements to retrieve relevant information.
| Tags: snowflake, sql-queries, data-extraction, gpt-actions, api-integration, data-warehouse | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_sharepoint_text.ipynb from openai-cookbook
Summary: This cookbook provides guidance for developers on creating a Q&A helper that interacts with SharePoint documents through an API. It outlines scenarios for handling search results and user interactions effectively.
| Tags: Q&A, SharePoint, API, document search, user interaction, search term | Task Categories: agents,rag |
Last modified: 2025-08-31
gpt_action_sharepoint_doc.ipynb from openai-cookbook
Summary: This AI cookbook provides a guide for developers to build a Q&A helper that interacts with a SharePoint document repository using an API. It outlines scenarios for handling search results and offers instructions for implementing a search functionality.
| Tags: Q&A, SharePoint, API, document-search, user-assistance, search-optimization | Task Categories: agents,rag |
Last modified: 2025-08-31
gpt_action_salesforce.ipynb from openai-cookbook
Summary: This AI cookbook provides a detailed guide for developers on how to create a GPT Action that interacts with Salesforce Service Cloud to retrieve and update case information. It includes API specifications and example interactions to facilitate integration with ChatGPT.
| Tags: Salesforce, API, case management, GPT Actions, Service Cloud, data retrieval, update cases | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_redshift.ipynb from openai-cookbook
Summary: This cookbook provides a middleware solution for executing SQL statements against AWS Redshift and returning the results as CSV files through an API. It includes setup instructions for AWS resources and example code for handling SQL execution and response formatting.
| Tags: AWS, Redshift, SQL, API, middleware, data-extraction, csv | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_outlook.ipynb from openai-cookbook
Summary: This AI cookbook provides a comprehensive guide for integrating GPT with Microsoft Outlook through the Microsoft Graph API, enabling users to manage emails and calendar events efficiently. It includes instructions for performing various tasks such as sending emails, scheduling meetings, and retrieving user information.
| Tags: Microsoft Graph API, email management, calendar events, GPT integration, automation, productivity | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_notion.ipynb from openai-cookbook
Summary: This AI cookbook provides a guide for developers on how to build a GPT Action specifically for interacting with Notion’s pages and databases. It includes instructions on searching for relevant information, retrieving page contents, and summarizing findings for user queries.
| Tags: notion, gpt-actions, api-integration, information-retrieval, developers-guide, chatbot | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_jira.ipynb from openai-cookbook
Summary: This AI cookbook provides a comprehensive guide for developers to create and manage Jira issues using a specialized GPT model through API interactions. It includes instructions for creating, reading, and updating issues and subtasks in Jira Cloud.
| Tags: Jira, API, issue-management, GPT, automation, software-development | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_googleads_adzviser.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for Google Ads specialists to audit account health, retrieve real-time reporting data, and optimize performance using structured workflows and Python code snippets.
| Tags: Google Ads, audit, reporting, optimization, Python, real-time data, account health | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_google_drive.ipynb from openai-cookbook
Summary: This AI cookbook provides instructions for developers to create a GPT Action that interacts with Google Drive, enabling file listing and content querying. It emphasizes the integration of ChatGPT with Google Drive for efficient document management and information retrieval.
| Tags: Google Drive, GPT Action, file management, natural language processing, document retrieval, API integration | Task Categories: agents,rag |
Last modified: 2025-08-31
gpt_action_gmail.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for developers to create a GPT-based email assistant that interacts with Gmail, enhancing productivity through email management features such as summarization, drafting, and sending emails.
| Tags: email-assistant, Gmail, productivity, API-integration, automation, email-management | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_confluence.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create a GPT Action that interacts with Atlassian’s Confluence API, enabling users to retrieve product-related information efficiently.
| Tags: confluence, API, gpt-actions, data-retrieval, product-information, search | Task Categories: agents |
Last modified: 2025-08-31
gpt_action_box.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create a GPT Action that interacts with Box.com, enabling users to search and retrieve files efficiently while ensuring data security and clarity in responses.
| Tags: Box.com, GPT Action, file retrieval, data security, API integration, search functionality, user support | Task Categories: agents,rag |
Last modified: 2025-08-31
gpt_action_bigquery.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create a GPT Action that interacts with Google BigQuery, enabling users to run SQL queries and retrieve data from specified datasets.
| Tags: BigQuery, SQL, GPT Action, data-querying, cloud-computing, API | Task Categories: agents |
Last modified: 2025-08-31
.gpt_action_getting_started.ipynb from openai-cookbook
Summary: This cookbook provides a guide for developers to create a GPT Action that retrieves weather forecasts based on user-provided locations. It outlines the necessary API interactions and user instructions for effective implementation.
| Tags: weather-forecast, API-integration, user-interaction, gpt-action, NWS | Task Categories: agents |
Last modified: 2025-08-31
translate_latex_book.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to translate a LaTeX book from Slovenian to English while preserving the LaTeX formatting. It involves splitting the text into manageable chunks, translating each chunk, and then recombining them into a single document.
| Tags: translation, LaTeX, OpenAI, text-processing, chunking | Task Categories: other |
Last modified: 2025-08-31
batch_processing.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize the Batch API for processing tasks such as categorizing movies and generating captions for images. It provides practical examples and code snippets to facilitate batch processing with OpenAI’s models.
| Tags: batch-processing, movie-categorization, image-captioning, gpt-4o, json-mode, data-extraction | Task Categories: classification,multimodal |
Last modified: 2025-08-31
whisper.ipynb from openai-cookbook
Summary: This cookbook provides an example of using the Azure OpenAI Whisper model to transcribe audio files. It includes setup instructions, authentication methods, and a sample implementation for audio transcription.
| Tags: Azure, Whisper, audio-transcription, OpenAI, cognitive-services, API | Task Categories: multimodal |
Last modified: 2025-08-31
functions.ipynb from openai-cookbook
Summary: This AI cookbook demonstrates how to utilize function calling capabilities with the Azure OpenAI service, allowing for enhanced interactions with external tools and data sources. It provides a practical example of setting up and using Azure OpenAI for weather information retrieval.
| Tags: Azure OpenAI, function calling, weather API, authentication, chat completions, Python | Task Categories: agents |
Last modified: 2025-08-31
embeddings.ipynb from openai-cookbook
Summary: This cookbook provides examples of how to use the Azure OpenAI service for generating embeddings. It includes setup instructions, authentication methods, and code snippets for implementation.
| Tags: Azure, embeddings, OpenAI, authentication, API | Task Categories: other |
Last modified: 2025-08-31
chat_with_your_own_data.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize Azure OpenAI service models with custom data, enabling users to enhance conversational AI applications by integrating specific data sources. It provides a practical guide for setting up and using Azure AI Search alongside OpenAI models for improved data retrieval and contextual responses.
| Tags: azure, openai, data-integration, chatbot, cognitive-search, rag, ai-services | Task Categories: rag |
Last modified: 2025-08-31
chat.ipynb from openai-cookbook
Summary: This cookbook provides examples of using the Azure OpenAI service for chat completions, including setup, authentication, and content filtering mechanisms.
| Tags: Azure, OpenAI, chat-completions, content-filtering, API, authentication, Python | Task Categories: other |
Last modified: 2025-08-31
whisper.ipynb from openai-cookbook
Summary: This cookbook provides an example of using the Azure OpenAI Whisper model to transcribe audio files. It includes setup instructions, code for authentication, and a sample audio transcription process.
| Tags: Azure, Whisper, audio-transcription, OpenAI, Python, cognitive-services | Task Categories: multimodal |
Last modified: 2025-08-31
functions.ipynb from openai-cookbook
Summary: This AI cookbook provides an example of how to use function calling capabilities with the Azure OpenAI service, allowing users to extend the model’s functionality to interact with external tools and data sources. It includes setup instructions and a sample implementation for retrieving weather information.
| Tags: Azure, OpenAI, function-calling, weather, API | Task Categories: other |
Last modified: 2025-08-31
embeddings.ipynb from openai-cookbook
Summary: This cookbook provides an example of how to use the Azure OpenAI service to create embeddings. It includes code for setting up the environment, authenticating, and retrieving embeddings from a specified deployment.
| Tags: Azure, embeddings, OpenAI, API, Python, requests, authentication | Task Categories: other |
Last modified: 2025-08-31
completions.ipynb from openai-cookbook
Summary: This cookbook provides examples and code snippets for using the Azure OpenAI service to generate text completions. It demonstrates how to set up the environment, authenticate, and make requests to the OpenAI API using Azure.
| Tags: Azure, OpenAI, text-completion, API, authentication, Python, requests | Task Categories: other |
Last modified: 2025-08-31
chat_with_your_own_data.ipynb from openai-cookbook
Summary: This cookbook provides guidance on using Azure OpenAI service models with your own data, enabling enhanced conversational AI capabilities. It demonstrates how to set up the OpenAI Python SDK to interact with Azure Cognitive Search for knowledge retrieval and contextual responses.
| Tags: Azure OpenAI, chat-completion, knowledge-retrieval, Cognitive Search, data-integration, API | Task Categories: rag |
Last modified: 2025-08-31
chat.ipynb from openai-cookbook
Summary: This AI cookbook provides an example of using the Azure OpenAI service for chat completions, demonstrating how to set up and make requests to the API. It includes code snippets for authentication and handling responses from the service.
| Tags: Azure, OpenAI, chat-completions, API, authentication, Python, requests | Task Categories: agents |
Last modified: 2025-08-31
DALL-E.ipynb from openai-cookbook
Summary: This cookbook provides a guide for generating images using the Azure OpenAI service with DALL·E. It includes setup instructions, code examples, and details on how to retrieve and display generated images.
| Tags: image-generation, Azure, DALL-E, OpenAI, Python, API | Task Categories: multimodal |
Last modified: 2025-08-31
parallel_agents.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to run multiple specialized agents in parallel using the OpenAI Agents SDK to analyze product reviews. It showcases the efficiency of concurrent execution and the integration of their outputs into a final summary.
| Tags: parallelization, agents, product-review-analysis, asyncio, OpenAI | Task Categories: agents,summarization |
Last modified: 2025-08-31
multi_agent_portfolio_collaboration.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to orchestrate a multi-agent collaboration system for financial portfolio analysis using the OpenAI Agents SDK. It provides a structured approach to building workflows where specialized agents work together to solve complex investment research problems.
| Tags: multi-agent collaboration, financial analysis, investment research, OpenAI Agents SDK, workflow orchestration, modularity, parallel execution | Task Categories: agents |
Last modified: 2025-08-31
evaluate_agents.ipynb from openai-cookbook
Summary: This cookbook provides guidance on monitoring and evaluating the performance of OpenAI agents using Langfuse, covering both online and offline evaluation metrics. It includes practical examples and code snippets to help users implement effective evaluation strategies for AI agents.
| Tags: AI agents, evaluation, monitoring, Langfuse, OpenAI SDK, performance metrics | Task Categories: agents,evaluation |
Last modified: 2025-08-31
dispute_agent.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize the Agents SDK in conjunction with Stripe’s API to automate dispute management workflows, addressing common operational challenges faced by businesses.
| Tags: dispute-management, agents-sdk, stripe-api, automation, workflow | Task Categories: agents |
Last modified: 2025-08-31
app_assistant_voice_agents.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a voice assistant for a consumer application using OpenAI’s Agents SDK, enabling users to interact with specialized agents for account information, product knowledge, and real-time web searches. It showcases the orchestration of multiple agents to provide a seamless user experience.
| Tags: voice-assistant, agents-sdk, web-search, file-search, account-management, real-time-assistance | Task Categories: agents,rag |
Last modified: 2025-08-31
Zero-shot_classification_with_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to perform zero-shot classification of sentiment in reviews using embeddings without any labeled data. It utilizes cosine similarity to compare review embeddings with predefined class embeddings for positive and negative sentiments.
| Tags: zero-shot classification, sentiment analysis, embeddings, cosine similarity, machine learning, pandas, sklearn | Task Categories: classification |
Last modified: 2025-08-31
Whisper_prompting_guide.ipynb from openai-cookbook
Summary: This cookbook provides techniques for using OpenAI’s Whisper audio transcription API, focusing on how to effectively utilize prompts to improve transcription accuracy. It includes examples of how to create fictitious prompts to guide the model’s output.
| Tags: audio-transcription, OpenAI, Whisper, prompting, fictitious-prompts, NLP, machine-learning | Task Categories: multimodal,other |
Last modified: 2025-08-31
Whisper_processing_guide.ipynb from openai-cookbook
Summary: This cookbook provides techniques for enhancing audio transcriptions using Whisper by implementing pre-processing and post-processing methods. It includes steps for trimming silence, segmenting audio, and refining transcriptions with punctuation and product terminology adjustments.
| Tags: audio-processing, transcription, Whisper, Pydub, text-cleaning, punctuation | Task Categories: multimodal,other |
Last modified: 2025-08-31
Whisper_correct_misspelling.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to enhance transcription accuracy using OpenAI’s Whisper model and GPT-4 for post-processing corrections. It focuses on correcting misspellings of company names and product references in audio transcriptions.
| Tags: transcription, OpenAI, Whisper, GPT-4, spellcheck, audio processing, AI cookbook | Task Categories: evaluation,other |
Last modified: 2025-08-31
Visualizing_embeddings_in_3D.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to visualize text embeddings in 3D using PCA for dimensionality reduction. It provides a practical example of loading a dataset, querying embeddings, and plotting the results in a 3D space.
| Tags: PCA, data visualization, embeddings, 3D plotting, text analysis, DBpedia | Task Categories: other |
Last modified: 2025-08-31
Visualizing_embeddings_in_2D.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to visualize high-dimensional embeddings using t-SNE, a technique for dimensionality reduction. It provides a step-by-step guide to transforming embeddings into a 2D scatter plot, colored by review ratings.
| Tags: t-SNE, dimensionality reduction, data visualization, embeddings, Python, machine learning | Task Categories: other |
Last modified: 2025-08-31
Using_tool_required_for_customer_service.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to implement a customer service assistant using OpenAI’s GPT model, focusing on tool integration for handling user queries effectively.
| Tags: customer-service, LLM, tool-integration, OpenAI, chatbot, support | Task Categories: agents,evaluation |
Last modified: 2025-08-31
Using_logprobs.ipynb from openai-cookbook
Summary: This cookbook demonstrates the use of the logprobs parameter in the Chat Completions API for classification tasks and Q&A evaluation. It provides insights into how log probabilities can be utilized to assess model confidence and improve output accuracy.
| Tags: logprobs, classification, Q&A evaluation, model confidence, AI applications | Task Categories: classification,evaluation |
Last modified: 2025-08-31
Using_embeddings.ipynb from openai-cookbook
Summary: This cookbook provides practical code snippets for embedding text using the OpenAI API’s ‘text-embedding-3-small’ model. It emphasizes best practices for managing API rate limits through exponential backoff techniques.
| Tags: embeddings, OpenAI API, exponential backoff, rate limiting, text processing | Task Categories: other |
Last modified: 2025-08-31
User_and_product_embeddings.ipynb from openai-cookbook
Summary: This cookbook provides a method for calculating user and product embeddings from fine food reviews and evaluates their effectiveness in predicting review scores using cosine similarity. It includes code for data processing, embedding generation, and visualization of results.
| Tags: embeddings, cosine-similarity, recommendation-systems, data-analysis, user-product-interaction | Task Categories: evaluation |
Last modified: 2025-08-31
Unit_test_writing_using_a_multi-step_prompt_with_older_completions_API.ipynb from openai-cookbook
Summary: This cookbook provides a structured approach to writing unit tests for Python functions using a multi-step prompting technique with GPT-3. It emphasizes generating explanations, planning tests, and writing the actual test code in a systematic manner.
| Tags: unit testing, Python, GPT-3, AI-assisted coding, software testing, automation | Task Categories: other |
Last modified: 2025-08-31
Unit_test_writing_using_a_multi-step_prompt.ipynb from openai-cookbook
Summary: This cookbook provides a structured approach to writing unit tests for Python functions using a multi-step prompting technique with GPT. It emphasizes the importance of explanation, planning, and execution in generating effective unit tests.
| Tags: unit testing, Python, GPT, multi-step prompts, AI-assisted coding, software testing | Task Categories: other |
Last modified: 2025-08-31
Tag_caption_images_with_GPT4V.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use GPT-4o models to tag and caption images of furniture items, leveraging their multimodal capabilities for enhanced search functionality.
| Tags: image-tagging, caption-generation, furniture-dataset, multimodal-models, keyword-extraction | Task Categories: multimodal,other |
Last modified: 2025-08-31
Summarizing_long_documents.ipynb from openai-cookbook
Summary: This cookbook provides methods for summarizing long documents using OpenAI’s GPT models, allowing users to control the level of detail in the summaries. It includes functions for chunking text, generating summaries, and handling token limits effectively.
| Tags: summarization, text-chunking, openai-api, gpt-4, document-summarization, token-management | Task Categories: summarization |
Last modified: 2025-08-31
Structured_outputs_multi_agent.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build a multi-agent system using structured outputs to enhance data analysis tasks. It outlines the roles of various agents responsible for triaging, data processing, analysis, and visualization, leveraging strict schemas for improved performance.
| Tags: multi-agent system, data analysis, structured outputs, data processing, visualization | Task Categories: agents |
Last modified: 2025-08-31
Structured_Outputs_Intro.ipynb from openai-cookbook
Summary: This cookbook demonstrates the use of Structured Outputs in the Chat Completions API, showcasing how to generate responses that adhere to a specified JSON schema. It includes examples of building a math tutoring tool, summarizing articles, and recommending products based on user input.
| Tags: structured-outputs, math-tutoring, article-summarization, product-recommendation, json-schema | Task Categories: agents,summarization,other |
Last modified: 2025-08-31
Speech_transcription_methods.ipynb from openai-cookbook
Summary: This cookbook provides a hands-on guide for implementing Speech-to-Text (STT) methods using the OpenAI API, focusing on various practical approaches and their applications. It covers both file-based and real-time audio transcription techniques, enabling users to select the most suitable method for their needs.
| Tags: speech-to-text, OpenAI API, audio transcription, real-time processing, Python | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Semantic_text_search_using_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to perform semantic text search using embeddings to find similar reviews from a dataset efficiently. It utilizes cosine similarity to compare the embeddings of search queries with those of the reviews.
| Tags: semantic search, embeddings, cosine similarity, data analysis, reviews, pandas, numpy | Task Categories: rag |
Last modified: 2025-08-31
Search_reranking_with_cross-encoders.ipynb from openai-cookbook
Summary: This cookbook provides a practical guide for implementing search reranking using cross-encoders, particularly in the context of semantic search with embeddings. It demonstrates how to leverage OpenAI’s models to improve the relevance of search results by reordering them based on domain-specific criteria.
| Tags: search, reranking, cross-encoder, semantic search, OpenAI, embeddings | Task Categories: rag,evaluation |
Last modified: 2025-08-31
SDG1.ipynb from openai-cookbook
Summary: This cookbook provides guidance on generating synthetic data using large language models, focusing on structured prompts and Python programming to create diverse datasets for various applications.
| Tags: synthetic data, data generation, fine-tuning, Python, machine learning, data augmentation, LLMs | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
Reproducible_outputs_with_the_seed_parameter.ipynb from openai-cookbook
Summary: This cookbook provides guidance on generating reproducible outputs using the OpenAI API by implementing a seed parameter and monitoring system fingerprints. It demonstrates how to achieve consistent results in AI-generated text outputs.
| Tags: reproducibility, OpenAI, API, seed parameter, system fingerprint, text generation, asyncio | Task Categories: other |
Last modified: 2025-08-31
Reinforcement_Fine_Tuning.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for developers and ML practitioners on how to apply reinforcement fine-tuning (RFT) to improve the reasoning performance of OpenAI’s models, specifically in the context of medical data analysis. It includes steps for dataset preparation, model benchmarking, and the creation of effective grading systems for model training.
| Tags: reinforcement-fine-tuning, medical-data, model-evaluation, OpenAI, data-preparation, grading-systems | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
Regression_using_embeddings.ipynb from openai-cookbook
Summary: Classification failed.
| Tags: | Task Categories: other |
Last modified: 2025-08-31
Recommendation_using_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use embeddings to find similar articles using nearest neighbor search techniques. It utilizes the AG news dataset to recommend articles based on their descriptions.
| Tags: recommendation, embeddings, nearest neighbors, data analysis, machine learning | Task Categories: rag |
Last modified: 2025-08-31
Realtime_prompting_guide.ipynb from openai-cookbook
Summary: This cookbook provides guidelines and tools for implementing a speech-to-speech AI model, focusing on real-time interaction and conversation management.
| Tags: speech-to-speech, real-time, conversation flow, AI agents, prompting techniques | Task Categories: agents,multimodal |
Last modified: 2025-08-31
RAG_with_graph_db.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to integrate large language models with a graph database to perform Retrieval Augmented Generation, enabling efficient and contextually relevant responses based on product data.
| Tags: rag, graph-database, recommendation-system, langchain, openai, data-integration, chatbot | Task Categories: rag,agents |
Last modified: 2025-08-31
Question_answering_using_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates a method for enabling GPT to answer questions about unfamiliar topics by utilizing a two-step Search-Ask approach with embeddings-based search. It provides examples of querying recent events and integrating reference text to enhance the model’s responses.
| Tags: question-answering, embeddings, search, GPT, OpenAI, data-retrieval, API | Task Categories: rag |
Last modified: 2025-08-31
Question_answering_using_a_search_API.ipynb from openai-cookbook
Summary: This cookbook provides a method for augmenting search systems using AI techniques, specifically focusing on generating queries and re-ranking search results based on semantic similarity. It demonstrates how to utilize the News API alongside OpenAI’s models to answer user questions effectively.
| Tags: search, query-generation, re-ranking, news-api, openai | Task Categories: rag |
Last modified: 2025-08-31
Prompt_migration_guide.ipynb from openai-cookbook
Summary: This AI cookbook provides a structured approach to refining prompts for GPT-4.1, focusing on clarity and effectiveness in instruction following.
| Tags: prompt-engineering, instruction-extraction, critique, AI-cookbook, GPT-4.1, best-practices | Task Categories: evaluation,other |
Last modified: 2025-08-31
Prompt_Caching101.ipynb from openai-cookbook
Summary: This AI cookbook provides guidance on implementing customer support functionalities using OpenAI’s API, focusing on tools for order management and user interaction.
| Tags: customer support, order management, API integration, function definitions, prompt caching, OpenAI | Task Categories: agents |
Last modified: 2025-08-31
Parse_PDF_docs_for_RAG.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to convert PDF documents into usable content for retrieval-augmented generation (RAG) applications using GPT-4o. It covers techniques for extracting text and analyzing images from PDFs to enhance knowledge retrieval systems.
| Tags: rag, data-extraction, image-analysis, pdf-processing, openai | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Orchestrating_agents.ipynb from openai-cookbook
Summary: This cookbook provides guidance on orchestrating multiple AI agents using routines and handoffs to improve performance in complex workflows. It includes practical implementations and examples to facilitate the integration of various tools and agents.
| Tags: orchestration, AI agents, routines, handoffs, customer service, tool integration | Task Categories: agents |
Last modified: 2025-08-31
Optimize_Prompts.ipynb from openai-cookbook
Summary: This cookbook demonstrates best practices for using a multi-agent system to optimize AI prompts by identifying and resolving common issues such as contradictions and format inconsistencies. It provides a structured approach to enhance the effectiveness of prompts for AI models.
| Tags: prompt-optimization, AI-agents, evaluation, Pydantic, OpenAI | Task Categories: agents,evaluation |
Last modified: 2025-08-31
Named_Entity_Recognition_to_enrich_text.ipynb from openai-cookbook
Summary: This AI cookbook demonstrates how to perform Named Entity Recognition (NER) using OpenAI’s API to enrich text with links to a knowledge base like Wikipedia. It provides a practical implementation for extracting and linking named entities in text, enhancing data usability.
| Tags: NER, OpenAI, text-enrichment, Wikipedia, data-extraction, natural-language-processing | Task Categories: rag,other |
Last modified: 2025-08-31
Multiclass_classification_for_transactions.ipynb from openai-cookbook
Summary: This cookbook provides methods for classifying transaction data into predefined categories using various approaches, including zero-shot classification, embeddings, and fine-tuning a model. It aims to demonstrate replicable techniques for multiclass classification tasks with both labeled and unlabeled datasets.
| Tags: multiclass classification, zero-shot classification, fine-tuning, embeddings, transaction analysis, data science | Task Categories: classification,fine-tuning |
Last modified: 2025-08-31
Leveraging_model_distillation_to_fine-tune_a_model.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to leverage model distillation to fine-tune a smaller model using outputs from a larger model, specifically focusing on classifying grape varieties from wine reviews. It highlights the performance improvements achieved through structured outputs and the distillation process.
| Tags: fine-tuning, classification, model distillation, structured outputs, wine reviews, OpenAI | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
How_to_use_moderation.ipynb from openai-cookbook
Summary: This cookbook provides detailed guidance on implementing moderation techniques for content safety, focusing on input and output moderation, as well as custom moderation tailored to specific application needs.
| Tags: moderation, content safety, input moderation, output moderation, custom moderation, AI ethics | Task Categories: other |
Last modified: 2025-08-31
How_to_use_guardrails.ipynb from openai-cookbook
Summary: This cookbook provides examples and guidelines for implementing guardrails in LLM applications to enhance steerability and prevent inappropriate content. It covers both input and output guardrails, emphasizing the importance of moderation and topical relevance.
| Tags: guardrails, LLM, moderation, asynchronous, input validation, output validation | Task Categories: other |
Last modified: 2025-08-31
How_to_stream_completions.ipynb from openai-cookbook
Summary: This cookbook provides examples and guidance on how to use the OpenAI ChatCompletion API, particularly focusing on streaming responses for improved efficiency. It demonstrates how to implement various API calls and handle responses effectively.
| Tags: streaming, API, OpenAI, ChatCompletion, Python, code examples, efficiency | Task Categories: other |
Last modified: 2025-08-31
How_to_handle_rate_limits.ipynb from openai-cookbook
Summary: This cookbook provides practical examples and strategies for handling rate limits when using the OpenAI API, including retry mechanisms and exponential backoff techniques. It aims to help developers manage API requests efficiently to avoid errors and ensure smooth operation.
| Tags: rate-limits, API, exponential-backoff, retry, openai | Task Categories: other |
Last modified: 2025-08-31
How_to_format_inputs_to_ChatGPT_models.ipynb from openai-cookbook
Summary: This cookbook provides examples and guidelines for using the OpenAI API with chat models like gpt-3.5-turbo and gpt-4. It includes code snippets for making API calls, formatting inputs, and handling responses effectively.
| Tags: OpenAI, API, chat models, gpt-3.5, gpt-4, Python, programming | Task Categories: other |
Last modified: 2025-08-31
How_to_finetune_chat_models.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide for fine-tuning the GPT-4o mini model using the RecipesNLG dataset to improve entity extraction of generic ingredients from recipes. It covers setup, data preparation, fine-tuning, and inference processes.
| Tags: fine-tuning, recipe-extraction, NER, GPT-4o, data-preparation, inference | Task Categories: fine-tuning |
Last modified: 2025-08-31
How_to_count_tokens_with_tiktoken.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on how to count tokens using the tiktoken library, which is essential for understanding the tokenization process in OpenAI’s models. It includes code examples and explanations for different encoding types and their usage in various models.
| Tags: tokenization, tiktoken, gpt-4o, OpenAI, encoding, API usage, text processing | Task Categories: other |
Last modified: 2025-08-31
How_to_combine_GPT4o_with_RAG_Outfit_Assistant.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize the GPT-4o mini model in conjunction with Retrieval-Augmented Generation (RAG) to create a clothing matchmaker application that analyzes clothing images and provides recommendations based on style and compatibility.
| Tags: rag, image-analysis, clothing-recommendation, gpt-4o, data-embedding, cosine-similarity | Task Categories: rag,multimodal |
Last modified: 2025-08-31
How_to_call_functions_with_chat_models.ipynb from openai-cookbook
Summary: This cookbook provides guidance on how to use the Chat Completions API in conjunction with external functions to enhance the capabilities of GPT models. It includes examples of generating function arguments and executing functions based on model outputs.
| Tags: chat-completions, function-calls, API-integration, weather-forecasting, python | Task Categories: agents |
Last modified: 2025-08-31
How_to_call_functions_for_knowledge_retrieval.ipynb from openai-cookbook
Summary: This cookbook provides a framework for creating an AI agent that utilizes arXiv articles to answer academic queries through a multi-function workflow. It includes functions for retrieving articles, summarizing their content, and managing embeddings for efficient retrieval.
| Tags: arxiv, summarization, knowledge-retrieval, agents, text-processing, embedding | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
How_to_build_a_tool-using_agent_with_Langchain.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on building tool-using agents with LangChain, enabling LLMs to access external tools for enhanced query responses. It covers setup, agent creation, and integration with a Pinecone vector database.
| Tags: langchain, agents, tool-integration, openai, pinecone, llm, query-response | Task Categories: agents |
Last modified: 2025-08-31
Get_embeddings_from_dataset.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to extract embeddings from a dataset of food reviews using a specified embedding model. It provides a step-by-step guide on loading the dataset, processing the reviews, and saving the resulting embeddings for future use.
| Tags: embeddings, data-processing, text-analysis, pandas, openai | Task Categories: other |
Last modified: 2025-08-31
Generate_Images_With_High_Input_Fidelity.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use the OpenAI Image API to perform high-fidelity edits on images, allowing for precise modifications such as changing colors, removing elements, and adding new objects. It provides practical examples and code snippets for various image editing tasks.
| Tags: image-generation, OpenAI, image-editing, high-fidelity, API | Task Categories: multimodal |
Last modified: 2025-08-31
Generate_Images_With_GPT_Image.ipynb from openai-cookbook
Summary: This cookbook provides instructions on how to generate and edit images using the GPT Image model, showcasing its capabilities in creating photorealistic images based on textual prompts. It includes practical examples and code snippets for users to follow along.
| Tags: image-generation, GPT Image, photorealistic, image-editing, OpenAI | Task Categories: multimodal |
Last modified: 2025-08-31
GPT_with_vision_for_video_understanding.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize GPT’s visual capabilities to process video frames and generate descriptive text and audio narration. It showcases the integration of OpenCV for video processing and OpenAI’s APIs for generating text and audio outputs.
| Tags: video-processing, narration, OpenCV, GPT-4, multimodal, AI-cookbook, text-to-speech | Task Categories: multimodal |
Last modified: 2025-08-31
Function_calling_with_an_OpenAPI_spec.ipynb from openai-cookbook
Summary: This AI cookbook demonstrates how to leverage OpenAPI specifications to enable GPT models to intelligently call RESTful APIs through function definitions. It provides a structured approach to converting API specifications into callable functions and processing user instructions with chained function calls.
| Tags: OpenAPI, function-calling, API integration, GPT, automation, chained calls | Task Categories: agents |
Last modified: 2025-08-31
Function_calling_finding_nearby_places.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to integrate the Google Places API with user profiles to provide personalized location-based recommendations. It focuses on leveraging user preferences to enhance the relevance of search results for nearby places.
| Tags: Google Places API, user profiles, location-based recommendations, function calling, personalization | Task Categories: agents,rag |
Last modified: 2025-08-31
Fine_tuning_for_function_calling.ipynb from openai-cookbook
Summary: This AI cookbook provides guidance on fine-tuning models to enhance their function-calling accuracy and reliability, specifically for chat models. It includes practical examples and code implementations for evaluating model performance in selecting appropriate functions based on user prompts.
| Tags: fine-tuning, function-calling, evaluation, AI models, OpenAI | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
Fine_tuning_direct_preference_optimization_guide.ipynb from openai-cookbook
Summary: This AI cookbook provides a comprehensive guide on fine-tuning techniques, specifically focusing on Direct Preference Optimization (DPO) and its applications in enhancing model performance for customer support tasks.
| Tags: fine-tuning, DPO, customer support, OpenAI, model optimization, evaluation | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
Fine-tuned_classification.ipynb from openai-cookbook
Summary: This cookbook provides a step-by-step guide to fine-tuning a language model to classify text data into categories, specifically distinguishing between baseball and hockey. It utilizes the sklearn library to fetch and preprocess the dataset, and OpenAI’s API for model training and evaluation.
| Tags: fine-tuning, classification, OpenAI, sklearn, text-data, machine-learning | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
File_Search_Responses.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide on how to upload PDF files to a vector store using the OpenAI API and perform retrieval-augmented generation (RAG) to answer questions based on the content of those PDFs. It includes code examples for creating a vector store, uploading files, and querying the store for relevant information.
| Tags: rag, pdf-upload, vector-store, file-search, openai-api, data-retrieval | Task Categories: rag,evaluation |
Last modified: 2025-08-31
Entity_extraction_for_long_documents.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to extract key information from long documents using chunking and AI models. It provides a structured approach to processing PDF documents for entity extraction and combines results for comprehensive insights.
| Tags: entity-extraction, document-processing, pdf, chunking, openai | Task Categories: rag,other |
Last modified: 2025-08-31
Enhance_your_prompts_with_meta_prompting.ipynb from openai-cookbook
Summary: This cookbook focuses on enhancing the quality of outputs from language models through meta prompting techniques, specifically in the context of summarizing news articles. It demonstrates how to refine prompts using a more advanced model to achieve better results in summarization tasks.
| Tags: meta-prompting, summarization, prompt-engineering, evaluation, openai | Task Categories: summarization,evaluation |
Last modified: 2025-08-31
Embedding_long_inputs.ipynb from openai-cookbook
Summary: This cookbook provides methods for embedding long texts using OpenAI’s embedding models, specifically addressing the limitations of maximum context length. It demonstrates techniques for truncating and chunking text to generate embeddings without exceeding model constraints.
| Tags: embedding, text-processing, OpenAI, tokenization, long-text | Task Categories: other |
Last modified: 2025-08-31
Embedding_Wikipedia_articles_for_search.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to prepare and embed Wikipedia articles for search using OpenAI’s API. It includes steps for collecting, chunking, embedding, and storing the data efficiently.
| Tags: embedding, Wikipedia, search, OpenAI, data-preparation, text-processing | Task Categories: rag,other |
Last modified: 2025-08-31
Developing_hallucination_guardrails.ipynb from openai-cookbook
Summary: This cookbook provides a structured approach to developing guardrails for AI models, focusing on ensuring accurate and appropriate outputs in customer support scenarios. It includes methods for generating policies and evaluating model interactions to prevent hallucinations.
| Tags: guardrails, customer-support, policy-generation, evaluation, AI-safety, hallucination-prevention | Task Categories: agents,evaluation |
Last modified: 2025-08-31
Data_extraction_transformation.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to utilize GPT-4o for extracting and transforming data from unstructured formats like PDFs, enabling better analysis and product development. It highlights the model’s capabilities in handling complex layouts and multilingual documents.
| Tags: data-extraction, OCR, GPT-4o, PDF, multimodal, invoice-processing, json-output | Task Categories: multimodal,other |
Last modified: 2025-08-31
Data-intensive-Realtime-apps.ipynb from openai-cookbook
Summary: This cookbook provides practical strategies for AI Engineers to optimize the use of OpenAI’s Realtime API in data-intensive applications, particularly in speech-to-speech scenarios. It focuses on enhancing performance and reliability when handling large volumes of data in real-time interactions.
| Tags: Realtime API, data-intensive, speech-to-speech, conversational agents, performance optimization | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Customizing_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to customize OpenAI embeddings for a specific task by processing training data and generating custom embeddings to improve classification accuracy. It includes methods for generating synthetic negative examples and optimizing embedding matrices.
| Tags: embeddings, text-similarity, classification, fine-tuning, data-processing | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
Custom-LLM-as-a-Judge.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to build an LLM-as-a-judge evaluation system to assess the accuracy of AI-generated responses and detect hallucinations using the Braintrust platform and OpenAI’s models.
| Tags: LLM-as-a-judge, evaluation, hallucination-detection, Braintrust, OpenAI, CoQA, asyncio | Task Categories: evaluation |
Last modified: 2025-08-31
Creating_slides_with_Assistants_API_and_DALL-E3.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to use the Assistants API and DALL·E-3 to automate the creation of informative slides from data insights without manual intervention in presentation software. It provides a step-by-step guide for generating visual content and summarizing key insights effectively.
| Tags: AI, slide-creation, data-visualization, DALL-E, presentation, automation | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Context_summarization_with_realtime_api.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to building a voice bot that captures audio from a microphone, processes it in real-time, and summarizes conversations to maintain context. It leverages OpenAI’s Realtime API for voice interactions and includes mechanisms for managing conversation state and token utilization.
| Tags: voice bot, real-time processing, OpenAI API, conversation summarization, audio streaming, asyncio | Task Categories: summarization,multimodal |
Last modified: 2025-08-31
Code_search_using_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to implement semantic code search using embeddings from the OpenAI Python repository. It includes functions for parsing Python files, extracting function definitions, and performing similarity searches on code snippets.
| Tags: code search, embeddings, function extraction, semantic search, openai-python | Task Categories: rag,other |
Last modified: 2025-08-31
Clustering_for_transaction_classification.ipynb from openai-cookbook
Summary: This cookbook provides a method for clustering unlabelled transaction data using K-Means and generating meaningful descriptions for each cluster using OpenAI’s GPT-3.5 model. It aims to help users identify spending patterns and categorize transactions effectively.
| Tags: clustering, transaction classification, K-Means, GPT-3, data analysis, embeddings, machine learning | Task Categories: classification |
Last modified: 2025-08-31
Clustering.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to perform K-means clustering on a dataset of fine food reviews, utilizing OpenAI’s API for thematic analysis of customer reviews. It includes data loading, clustering, visualization, and interpretation of results.
| Tags: K-means, clustering, customer reviews, data analysis, OpenAI, Python, visualization | Task Categories: classification,other |
Last modified: 2025-08-31
Classification_using_embeddings.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to classify food reviews using embeddings and a Random Forest classifier. It provides a practical example of text classification, evaluating model performance on unseen data.
| Tags: text classification, embeddings, Random Forest, machine learning, data evaluation, food reviews | Task Categories: classification |
Last modified: 2025-08-31
Chat_finetuning_data_prep.ipynb from openai-cookbook
Summary: This AI cookbook provides a comprehensive guide for preprocessing and analyzing chat datasets intended for fine-tuning chat models. It includes format validation, error checking, and token count estimation for training costs.
| Tags: fine-tuning, data-validation, token-counting, chat-models, error-checking | Task Categories: fine-tuning |
Last modified: 2025-08-31
Assistants_API_overview_python.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to utilizing the OpenAI Assistants API for creating interactive assistant experiences, including features like code interpretation and file search. It demonstrates how to set up assistants, manage threads, and handle user interactions effectively.
| Tags: assistants, API, interactive, code-interpreter, file-search, OpenAI, Python | Task Categories: agents,other |
Last modified: 2025-08-31
run-nvidia.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide for optimizing OpenAI’s GPT-OSS models using NVIDIA’s TensorRT-LLM for efficient inference on NVIDIA GPUs. It includes practical examples and setup instructions to facilitate high-performance deployment.
| Tags: NVIDIA, TensorRT, GPT-OSS, model optimization, high-performance inference, Python API, deployment guide | Task Categories: other |
Last modified: 2025-08-31
run-colab.ipynb from openai-cookbook
Summary: This cookbook provides a guide to running the OpenAI gpt-oss 20B model in a Google Colab environment, focusing on low-latency applications and ease of use in resource-constrained settings. It includes code snippets for model setup and interaction, demonstrating how to generate responses based on user prompts.
| Tags: gpt-oss, Google Colab, transformers, model deployment, AI cookbook, text generation | Task Categories: other |
Last modified: 2025-08-31
fine-tune-transfomers.ipynb from openai-cookbook
Summary: This cookbook demonstrates how to fine-tune the OpenAI gpt-oss-20b model for multilingual reasoning using Hugging Face’s libraries. It guides users through the setup, dataset preparation, model configuration, training, and inference processes to enable reasoning in multiple languages.
| Tags: fine-tuning, multilingual, transformers, Hugging Face, AI reasoning, supervised learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine-tune-korean.ipynb from openai-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning OpenAI’s gpt-oss model specifically for Korean news style and modern chat tone, utilizing both Korean and English languages. It includes detailed steps for environment setup, data preparation, model training, and evaluation.
| Tags: fine-tuning, gpt-oss, Korean, chat, news, transformers, LoRA | Task Categories: fine-tuning |
Last modified: 2025-08-31
vision_with_tools.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to analyze an image of a nutrition label and extract structured nutrition information using a custom tool integrated with the Anthropic API. It combines vision capabilities with tool usage to facilitate data extraction from images.
| Tags: nutrition-extraction, image-analysis, tool-integration, anthropic, multimodal | Task Categories: multimodal,other |
Last modified: 2025-08-31
tool_use_with_pydantic.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to create a note-saving tool using Pydantic for data validation and the Anthropic API for interaction. It includes the definition of models, processing tool calls, and generating responses based on user input.
| Tags: note-saving, pydantic, anthropic, API, data-validation, tool-integration | Task Categories: agents |
Last modified: 2025-08-31
tool_choice.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the Anthropic Claude model for various tasks, including web searching, sentiment analysis, and customer interaction via SMS. It showcases the use of tool choices to enhance the model’s capabilities in responding to user queries.
| Tags: tool-use, web-search, sentiment-analysis, sms-chatbot, agent-design, dynamic-tool-selection | Task Categories: agents,rag |
Last modified: 2025-08-31
parallel_tools_claude_3_7_sonnet.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to implement parallel tool calls using the Claude 3.7 Sonnet model, specifically focusing on weather and time retrieval tools. It introduces a ‘batch tool’ to facilitate simultaneous tool invocations, enhancing the model’s efficiency in handling multiple requests.
| Tags: parallel tool calls, Claude 3.7, API integration, weather retrieval, time retrieval, batch processing, tool invocation | Task Categories: agents,other |
Last modified: 2025-08-31
memory_cookbook.ipynb from anthropic-cookbook
Summary: This cookbook provides strategies for managing memory in LLM-based agents, focusing on self-managed memory implementations. It includes examples of memory tools and discusses the importance of efficient memory management for long-horizon tasks.
| Tags: memory management, LLM, agents, self-managed memory, tool implementation, anthropic | Task Categories: agents,other |
Last modified: 2025-08-31
extracting_structured_json.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize Claude’s tool use feature for extracting structured JSON data from various inputs, including article summarization, entity extraction, and sentiment analysis. It provides practical examples and code snippets for implementing these tasks.
| Tags: json-extraction, sentiment-analysis, entity-extraction, article-summarization, api-integration | Task Categories: summarization,classification,other |
Last modified: 2025-08-31
customer_service_agent.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to create a customer service chatbot using the Claude 3 model and client-side tools for retrieving customer information, order details, and processing order cancellations.
| Tags: customer-service, chatbot, tool-integration, anthropic, order-management, data-retrieval | Task Categories: agents |
Last modified: 2025-08-31
calculator_tool.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to integrate a simple calculator tool with the Claude AI model, allowing it to perform arithmetic operations based on user input. It provides a step-by-step guide on setting up the environment, defining the tool, and processing user queries.
| Tags: calculator, AI integration, arithmetic operations, Anthropic, tool usage | Task Categories: agents,other |
Last modified: 2025-08-31
using_llm_api.ipynb from anthropic-cookbook
Summary: This cookbook provides a guide on integrating the Wolfram Alpha LLM API with Claude, enabling it to send queries and receive computed responses for user questions. It includes setup instructions and code examples for effective implementation.
| Tags: Wolfram Alpha, API integration, Claude, LLM, query processing, Python | Task Categories: agents,other |
Last modified: 2025-08-31
wikipedia-search-cookbook.ipynb from anthropic-cookbook
Summary: This cookbook provides a framework for creating a virtual research assistant that can search Wikipedia to answer user queries by utilizing a search tool and iterative prompting. It outlines the process of integrating a search tool with Claude to enhance its ability to provide accurate and up-to-date information.
| Tags: rag, wikipedia-search, tool-use, virtual-assistant, information-retrieval | Task Categories: rag,agents |
Last modified: 2025-08-31
rag_using_pinecone.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to implement retrieval-augmented generation (RAG) by connecting Claude with a Pinecone vector database to enhance responses using embedded data. It covers embedding datasets, uploading to Pinecone, retrieving information, and generating answers using Claude.
| Tags: rag, Pinecone, Claude, embedding, data-retrieval, Voyage AI, API integration | Task Categories: rag |
Last modified: 2025-08-31
claude_3_rag_agent.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) agent using Claude 3, Voyage AI for embeddings, and Pinecone for knowledge retrieval. It provides step-by-step instructions for setting up the environment, embedding documents, and querying the knowledge base.
| Tags: rag, agents, knowledge-retrieval, embeddings, langchain, Pinecone, AI | Task Categories: rag,agents |
Last modified: 2025-08-31
rag_using_mongodb.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide to building a Retrieval-Augmented Generation (RAG) system using Claude 3 and MongoDB, focusing on data ingestion, vector search, and response generation based on tech news articles. It includes step-by-step instructions for setting up the environment, handling data, and integrating various APIs for enhanced functionality.
| Tags: rag, mongodb, data-ingestion, vector-search, anthropic, voyageai, tech-analysis | Task Categories: rag |
Last modified: 2025-08-31
SubQuestion_Query_Engine.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide on using the SubQuestionQueryEngine to handle complex queries across multiple documents, specifically focusing on financial data from Lyft and Uber. It includes installation instructions, API setup, and practical examples of querying and displaying results.
| Tags: rag, query-engine, financial-analysis, data-extraction, llama-index, sub-queries, API-integration | Task Categories: rag,agents |
Last modified: 2025-08-31
Router_Query_Engine.ipynb from anthropic-cookbook
Summary: This cookbook provides a practical guide for using the Router Query Engine in conjunction with LlamaIndex to handle user queries effectively. It demonstrates how to set up various query engines for summarization and context retrieval from documents.
| Tags: llama-index, query-engine, summarization, text-retrieval, anthropic | Task Categories: rag,summarization |
Last modified: 2025-08-31
ReAct_Agent.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates the creation of a ReAct Agent using various tools for performing calculations and querying financial data from documents. It provides practical examples of integrating LLMs with data retrieval capabilities.
| Tags: rag, agents, data-extraction, financial-analysis, llama-index, python | Task Categories: rag,agents |
Last modified: 2025-08-31
Multi_Modal.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the Anthropic MultiModal LLM for image understanding and reasoning, integrating various libraries for image processing and data extraction. It provides practical examples of loading images, generating descriptions, and extracting structured data from images using a defined Pydantic schema.
| Tags: multi-modal, image-processing, data-extraction, llama-index, pydantic, API-integration | Task Categories: multimodal,other |
Last modified: 2025-08-31
Multi_Document_Agents.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using multiple document agents with the LlamaIndex framework. It provides a practical guide for integrating various AI models to retrieve and summarize information from a set of documents.
| Tags: rag, document-agents, information-retrieval, summarization, llama-index, anthropic | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
Basic_RAG_With_LlamaIndex.ipynb from anthropic-cookbook
Summary: This cookbook provides a step-by-step guide to building a basic Retrieval-Augmented Generation (RAG) pipeline using LlamaIndex. It covers the setup of language models, data handling, and querying mechanisms.
| Tags: rag, llama-index, data-loading, query-engine, embedding-model | Task Categories: rag |
Last modified: 2025-08-31
prerecorded_audio.ipynb from anthropic-cookbook
Summary: This cookbook provides a step-by-step guide to transcribing audio files using the Deepgram API and generating interview questions with the Anthropic API. It allows users to manipulate audio URLs and customize the transcription process.
| Tags: audio-transcription, interview-questions, Deepgram, Anthropic, API-integration, Python | Task Categories: rag,other |
Last modified: 2025-08-31
guide.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide to building a Text to SQL system using the Claude model, enabling users to convert natural language queries into SQL statements. It covers setup, effective prompting techniques, and methods for handling complex database interactions.
| Tags: text-to-sql, natural-language-processing, sqlite, database-querying, AI-assistant, prompt-engineering | Task Categories: rag,other |
Last modified: 2025-08-31
guide.ipynb from anthropic-cookbook
Summary: This AI cookbook provides a comprehensive guide on leveraging Claude for summarizing legal documents, focusing on techniques for effective summarization, evaluation methods, and iterative improvement strategies. It includes practical code examples for extracting text from PDFs and generating summaries using an API client.
| Tags: summarization, legal-documents, text-extraction, API-integration, evaluation-methods, iterative-improvement | Task Categories: summarization |
Last modified: 2025-08-31
guide.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide on building and optimizing a Retrieval Augmented Generation (RAG) system using Anthropic documentation as a knowledge base. It includes setup instructions, evaluation techniques, and advanced methods for improving retrieval performance.
| Tags: rag, evaluation, anthropic, data-retrieval, embedding | Task Categories: rag,evaluation |
Last modified: 2025-08-31
guide.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide to enhancing Retrieval Augmented Generation (RAG) systems using Contextual Embeddings, aimed at improving the accuracy of document retrieval from internal knowledge bases. It includes practical implementations, performance evaluations, and techniques for optimizing retrieval systems.
| Tags: rag, contextual-embeddings, document-retrieval, performance-evaluation, code-generation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
guide.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide on leveraging large language models for classifying customer support tickets in the insurance industry. It includes steps for data preparation, prompt engineering, and evaluation of classification performance using various methods.
| Tags: classification, customer support, insurance, data preparation, prompt engineering, evaluation | Task Categories: classification,evaluation |
Last modified: 2025-08-31
orchestrator_workers.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates a flexible orchestrator-worker workflow for breaking down complex tasks and processing them in parallel using language models. It allows for dynamic task generation based on input, making it suitable for varied applications such as marketing content creation.
| Tags: orchestrator, task-decomposition, parallel-processing, AI-workflow, content-generation | Task Categories: agents |
Last modified: 2025-08-31
evaluator_optimizer.ipynb from anthropic-cookbook
Summary: This cookbook provides a structured approach to generating and evaluating code solutions using an iterative feedback loop with language models. It emphasizes the importance of clear evaluation criteria and the potential for improvement through feedback.
| Tags: iterative refinement, code evaluation, feedback loop, LLM, stack implementation | Task Categories: agents,evaluation |
Last modified: 2025-08-31
basic_workflows.ipynb from anthropic-cookbook
Summary: This AI cookbook provides practical implementations of multi-LLM workflows, including prompt-chaining, parallelization, and routing for various tasks such as data extraction and customer support ticket handling.
| Tags: prompt-chaining, parallelization, routing, data-extraction, customer-support | Task Categories: agents |
Last modified: 2025-08-31
usage_cost_api.ipynb from anthropic-cookbook
Summary: This cookbook provides a practical guide for programmatically accessing and analyzing usage and cost data from the Anthropic Admin API. It includes methods for tracking token consumption, monitoring costs, and generating reports for financial analysis.
| Tags: API, usage tracking, cost analysis, financial reporting, data analysis, token consumption | Task Categories: other |
Last modified: 2025-08-31
using_sub_agents.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to analyze Apple’s 2023 financial earnings reports using Claude 3 Haiku sub-agent models to extract relevant information from PDFs and generate accompanying visualizations with matplotlib.
| Tags: rag, data-extraction, image-generation, financial-analysis, python | Task Categories: rag,agents,multimodal |
Last modified: 2025-08-31
reading_charts_graphs_powerpoints.ipynb from anthropic-cookbook
Summary: This cookbook provides guidance on using the Anthropic Claude model to process and analyze PDF documents, particularly focusing on charts, graphs, and slide decks. It includes code examples for encoding documents and querying the model for insights.
| Tags: pdf-processing, data-extraction, multimodal-analysis, charts, graphs, AI-cookbook | Task Categories: multimodal,rag |
Last modified: 2025-08-31
how_to_transcribe_text.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to use Claude 3 for transcribing text from images, leveraging its advanced reasoning capabilities to extract structured information from unstructured data. It provides practical examples of transcribing both typed and handwritten text.
| Tags: transcription, image-processing, OCR, AI, Claude 3, data-extraction, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
getting_started_with_vision.ipynb from anthropic-cookbook
Summary: This cookbook provides guidance on how to utilize the Claude 3 model for processing images alongside text inputs. It demonstrates how to pass images through URLs and base64 encoding to generate responses based on visual content.
| Tags: image-processing, API, Claude-3, multimodal, base64, image-description, sonnet-generation | Task Categories: multimodal |
Last modified: 2025-08-31
best_practices_for_vision.ipynb from anthropic-cookbook
Summary: This cookbook provides best practices for utilizing vision capabilities with the Claude model, focusing on effective prompt engineering techniques to enhance image analysis tasks.
| Tags: image-analysis, prompt-engineering, multimodal, AI-cookbook, best-practices, Claude | Task Categories: multimodal |
Last modified: 2025-08-31
using_citations.ipynb from anthropic-cookbook
Summary: This cookbook provides examples and guidance on using the Anthropic API for document citation and customer support applications. It demonstrates how to integrate help center articles and PDF documents into a chatbot interface for effective user assistance.
| Tags: citations, customer-support, API-integration, document-processing, help-center | Task Categories: rag,multimodal |
Last modified: 2025-08-31
speculative_prompt_caching.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates the concept of Speculative Prompt Caching, which aims to reduce time-to-first-token (TTFT) by warming up the cache while users are still formulating their queries. It provides practical examples of implementing this caching strategy using the AsyncAnthropic client.
| Tags: caching, asyncio, database, performance, AI | Task Categories: other |
Last modified: 2025-08-31
sampling_past_max_tokens.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the Claude model to generate longer responses by leveraging previous messages, effectively bypassing token limits.
| Tags: Claude, token limit, response generation, AI storytelling, Python | Task Categories: other |
Last modified: 2025-08-31
read_web_pages_with_haiku.ipynb from anthropic-cookbook
Summary: This cookbook provides a step-by-step guide on how to fetch web page content and generate concise summaries using the Anthropic Claude API. It includes installation instructions and code snippets for implementation.
| Tags: web-scraping, API, summarization, Anthropic, Python, requests, cookbook | Task Categories: summarization |
Last modified: 2025-08-31
prompt_caching.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates the use of prompt caching with the Anthropic API to enhance the efficiency of AI interactions, particularly in multi-turn conversations. It provides practical examples of fetching text content and utilizing cached prompts to improve response times and reduce costs.
| Tags: prompt-caching, AI-conversation, text-processing, API-integration, performance-optimization | Task Categories: rag,summarization |
Last modified: 2025-08-31
pdf_upload_summarization.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the Anthropic API to upload and summarize PDF documents using the Claude model. It provides examples of how to encode PDF files and generate responses in various formats, such as summaries and creative outputs.
| Tags: pdf-upload, summarization, anthropic, multimodal, api-integration, creative-writing | Task Categories: summarization,multimodal |
Last modified: 2025-08-31
metaprompt.ipynb from anthropic-cookbook
Summary: This cookbook provides a framework for creating prompts for an AI assistant, focusing on guiding the assistant through various tasks with clear instructions and examples. It emphasizes the importance of structured interactions and the extraction of relevant information from provided documents.
| Tags: prompt-engineering, AI-assistant, task-instruction, FAQ, dialogue-management, text-analysis | Task Categories: agents,rag |
Last modified: 2025-08-31
mc_qa.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize Claude’s long-context question-answering capabilities on government documents by preprocessing data and generating multiple-choice questions. It also evaluates the model’s performance based on the context provided.
| Tags: long-context, question-answering, data-preprocessing, government-documents, evaluation | Task Categories: evaluation,rag |
Last modified: 2025-08-31
illustrated_responses.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to create an AI assistant using Claude that can generate images based on user prompts by integrating with the Stable Diffusion API. It provides guidance on crafting effective prompts for image generation.
| Tags: image-generation, AI-assistant, prompt-engineering, Stable-Diffusion, multimodal | Task Categories: multimodal,agents |
Last modified: 2025-08-31
how_to_make_sql_queries.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to use the Claude AI model to generate SQL queries from natural language questions by setting up a test database and providing the schema to the model. It showcases the integration of AI with database management to facilitate data retrieval through natural language processing.
| Tags: SQL, natural-language-processing, database, AI-integration, data-retrieval, anthropic | Task Categories: rag |
Last modified: 2025-08-31
how_to_enable_json_mode.ipynb from anthropic-cookbook
Summary: This cookbook provides guidance on how to interact with the Claude AI model to generate structured JSON outputs based on user prompts. It includes examples of extracting and formatting JSON data effectively.
| Tags: json, data-extraction, anthropic, AI-cookbook, Claude | Task Categories: other |
Last modified: 2025-08-31
generate_test_cases.ipynb from anthropic-cookbook
Summary: This cookbook provides a framework for generating synthetic test data for prompt templates using the Anthropic API, enabling effective evaluation and improvement of AI models like Claude.
| Tags: synthetic data, prompt evaluation, test cases, AI models, Anthropic API, data generation | Task Categories: evaluation,other |
Last modified: 2025-08-31
building_moderation_filter.ipynb from anthropic-cookbook
Summary: This cookbook provides a guide on how to use the Claude model for building a content moderation filter that classifies user-generated text based on defined guidelines. It includes examples and code snippets for implementation.
| Tags: content moderation, AI, text classification, user-generated content, guidelines | Task Categories: classification |
Last modified: 2025-08-31
building_evals.ipynb from anthropic-cookbook
Summary: This cookbook provides guidelines and examples for building evaluations to assess the performance of AI models, particularly focusing on the Claude model. It emphasizes the importance of structured evals, grading methods, and continuous improvement in model accuracy.
| Tags: evaluation, grading, AI models, Claude, performance assessment, prompt engineering | Task Categories: evaluation |
Last modified: 2025-08-31
batch_processing.ipynb from anthropic-cookbook
Summary: This cookbook provides a comprehensive guide on how to utilize the Message Batches API for efficient batch processing of message requests, enabling cost-effective handling of large volumes of data.
| Tags: batch processing, API, cost-effective, multimodal, message requests, monitoring, results retrieval | Task Categories: multimodal,other |
Last modified: 2025-08-31
finetuning_on_bedrock.ipynb from anthropic-cookbook
Summary: This cookbook provides a step-by-step guide for fine-tuning the Claude 3 Haiku model using Amazon Bedrock, including dataset preparation and model customization. It emphasizes the use of JSONL formatted datasets for training and demonstrates how to upload data to S3 and invoke the model.
| Tags: fine-tuning, Claude 3, Amazon Bedrock, S3, JSONL, AI Cookbook, boto3 | Task Categories: fine-tuning |
Last modified: 2025-08-31
extended_thinking_with_tool_use.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the extended thinking feature of the Claude model while integrating tool use, allowing for transparent step-by-step reasoning before arriving at final answers.
| Tags: extended thinking, tool integration, AI agents, weather API, mock data, Claude model, interactive examples | Task Categories: agents,other |
Last modified: 2025-08-31
extended_thinking.ipynb from anthropic-cookbook
Summary: This cookbook demonstrates how to utilize the extended thinking feature of Claude 3.7 Sonnet for enhanced reasoning capabilities in complex tasks, providing transparency into its thought process before delivering final answers.
| Tags: extended thinking, reasoning, API usage, token management, puzzle solving | Task Categories: other |
Last modified: 2025-08-31
LiveAPI_streaming_in_colab.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for implementing a multimodal live API using websockets in Google Colab, enabling real-time audio processing and interaction. It includes code snippets for setting up audio streams and handling asynchronous communication between Python and JavaScript.
| Tags: websockets, audio-processing, real-time, Colab, multimodal, asyncio | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_LyriaRealTime_websockets.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for generating music in real-time using the Lyria model and websockets. It demonstrates how to set up an audio generation loop that interacts with a generative AI service to create music based on user-defined prompts and configurations.
| Tags: music-generation, websockets, AI, real-time, audio | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_LiveAPI_tools.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini 2.0 multimodal live API with websockets, enabling users to interact with various tools and generate content in real-time. It includes examples of sending prompts and handling responses across different modalities, including text and audio.
| Tags: websockets, multimodal, real-time, API, audio, text, Google | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Get_started_LiveAPI.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Live API with WebSockets to interact with the Gemini model, enabling real-time audio generation based on user input. It demonstrates how to set up a WebSocket connection, send messages, and receive audio responses.
| Tags: websockets, audio-generation, real-time, API, Gemini, interactive | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Video_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini API to upload and process video files through RESTful calls. It includes detailed steps for managing video metadata, uploading files, and generating content based on the uploaded videos.
| Tags: video-upload, API, Gemini, REST, multimodal, content-generation | Task Categories: multimodal |
Last modified: 2025-08-31
System_instructions_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quick start guide for using the Gemini API to implement system instructions through example code snippets. It demonstrates how to utilize curl commands to interact with the API in Google Colab or other environments.
| Tags: Gemini API, system instructions, curl, Google Colab, API integration, quickstart | Task Categories: other |
Last modified: 2025-08-31
Streaming_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to generate content through RESTful streaming. It includes code snippets and instructions for setting up the environment and making API calls.
| Tags: API, streaming, content-generation, Google, quickstart | Task Categories: other |
Last modified: 2025-08-31
Search_Grounding.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide on using the Gemini API for search grounding, enabling users to generate content based on search queries. It includes code snippets for authentication and making API calls to retrieve and display information.
| Tags: gemini, API, search-grounding, content-generation, Google Colab | Task Categories: rag,agents |
Last modified: 2025-08-31
Safety_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to implement safety features in generative language models. It includes code snippets for making API calls and handling responses related to safety settings and content generation.
| Tags: API, safety, generative models, Google, quickstart, colab | Task Categories: other |
Last modified: 2025-08-31
Prompting_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API with REST, demonstrating how to generate content and interact with the API using curl commands. It includes examples of generating text and processing images, making it suitable for developers looking to integrate AI capabilities into their applications.
| Tags: gemini, API, curl, content-generation, image-processing, quickstart, Google Colab | Task Categories: multimodal,other |
Last modified: 2025-08-31
Models_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide on how to interact with the Gemini API to list available models and retrieve model details using RESTful commands. It is designed for use in Google Colab or terminal environments with proper API key configuration.
| Tags: Gemini API, REST, Google Colab, model listing, API key management | Task Categories: other |
Last modified: 2025-08-31
JSON_mode_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to generate JSON outputs based on specified schemas. It includes code examples for running commands in Google Colab or a terminal using curl.
| Tags: API, JSON, Google Colab, curl, quickstart, Gemini | Task Categories: other |
Last modified: 2025-08-31
Imagen_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using Google’s Imagen model to generate images from text prompts via a REST API. It includes code snippets for setting up the environment, making API calls, and processing the generated images.
| Tags: image-generation, API, Google, Imagen, multimodal, text-to-image, Colab | Task Categories: multimodal |
Last modified: 2025-08-31
Function_calling_config_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides guidance on using the Gemini API for function calling configurations, specifically for controlling a lighting system through API calls. It includes examples of how to enable lights, set colors, and manage the lighting system using RESTful interactions.
| Tags: function-calling, API, lighting-control, Gemini, REST | Task Categories: agents |
Last modified: 2025-08-31
Function_calling_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides quick code examples for utilizing the Gemini API to perform function calling via REST. It demonstrates how to interact with the API to retrieve information about movies and theaters based on user queries.
| Tags: API, function-calling, movie-recommendation, Google Colab, curl, theater-finder | Task Categories: agents,rag |
Last modified: 2025-08-31
Embeddings_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to embed text content using RESTful calls. It includes examples of how to make API requests for embedding single and batch text inputs.
| Tags: gemini, embedding, API, REST, quickstart, text-processing | Task Categories: rag |
Last modified: 2025-08-31
Caching_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using context caching with the Gemini API, specifically focusing on the Apollo 11 transcript. It includes examples of how to interact with the API using Python and curl commands to optimize request costs.
| Tags: caching, API, Gemini, transcript, Python, curl, quickstart | Task Categories: rag,summarization |
Last modified: 2025-08-31
Audio_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini API to process audio files through RESTful calls. It includes examples of uploading audio, generating content based on audio input, and managing audio files within the API.
| Tags: audio-processing, gemini-api, rest-api, content-generation, file-management | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
Video_understanding.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for utilizing the Gemini model for video understanding tasks, including generating captions, summarizing content, and transcribing notes from videos. It demonstrates how to upload videos, process them, and extract meaningful information using AI techniques.
| Tags: video-understanding, AI-cookbook, gemini, content-generation, summarization | Task Categories: multimodal,summarization,other |
Last modified: 2025-08-31
Video.ipynb from google-gemini-cookbook
Summary: This cookbook provides insights into utilizing the Gemini API for video understanding capabilities. It serves as a guide for users to explore and implement video processing techniques.
| Tags: video understanding, Gemini API, multimodal, quickstart, notebook | Task Categories: multimodal |
Last modified: 2025-08-31
Template.ipynb from google-gemini-cookbook
Summary: This cookbook provides a template for using the Gemini API with Google Colab, focusing on installation and initial setup for AI model interaction. It includes code snippets for integrating the Gemini model and managing API keys.
| Tags: gemini, google-colab, api-integration, python-sdk, template | Task Categories: other |
Last modified: 2025-08-31
System_instructions.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to use the Gemini API for generating content and interacting with chat models. It includes various system prompts and demonstrates how to generate HTML code based on user descriptions.
| Tags: gemini, content-generation, chatbot, HTML, Python, API | Task Categories: agents,other |
Last modified: 2025-08-31
Streaming.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to generate content through streaming. It includes examples of both synchronous and asynchronous content generation using Python.
| Tags: streaming, content-generation, Python, asynchronous, Google API, quickstart | Task Categories: other |
Last modified: 2025-08-31
Spatial_understanding.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini model to perform 2D spatial understanding tasks, including detecting and labeling objects in images with bounding boxes. It demonstrates how to integrate Google Generative AI capabilities with image processing to enhance visual recognition tasks.
| Tags: bounding-boxes, image-processing, object-detection, generative-ai, spatial-understanding | Task Categories: multimodal |
Last modified: 2025-08-31
Search_Grounding.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini model for generating content and integrating search capabilities to enhance responses. It demonstrates how to utilize both text and audio outputs in interactive applications.
| Tags: gemini, search-grounding, audio-output, interactive-applications, content-generation | Task Categories: rag,agents,multimodal |
Last modified: 2025-08-31
Safety.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API with a focus on safety settings for content generation. It demonstrates how to implement safety measures when generating text responses from the model.
| Tags: safety, content-generation, API, Gemini, quickstart, Google | Task Categories: other |
Last modified: 2025-08-31
Prompting.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples and guidance on using the Gemini API for generating content and interacting with AI models. It includes code snippets for various tasks such as generating text, processing images, and managing chat interactions.
| Tags: gemini, content-generation, image-processing, chatbot, python | Task Categories: multimodal,other |
Last modified: 2025-08-31
PDF_Files.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to convert a PDF file for processing with the Gemini API, allowing for tasks such as summarization and image explanation. It provides step-by-step instructions and code snippets for utilizing the API effectively.
| Tags: gemini, PDF, summarization, image-explanation, API | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
New_in_002.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples and code snippets for using the Gemini generative AI models, focusing on content generation and evaluation techniques. It includes practical implementations for generating diverse outputs and analyzing vocabulary usage.
| Tags: generative AI, content generation, vocabulary analysis, Google Colab, model evaluation, Python | Task Categories: other |
Last modified: 2025-08-31
Models.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini API to list and interact with various AI models. It includes code snippets for installation and model retrieval, making it useful for developers looking to integrate Gemini’s capabilities into their applications.
| Tags: gemini, API, model-listing, google-colab, python | Task Categories: other |
Last modified: 2025-08-31
JSON_mode.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API to generate JSON outputs based on specified schemas. It includes examples of generating cookie recipes using a structured format.
| Tags: Gemini API, JSON generation, cookie recipes, quickstart, Google Colab | Task Categories: other |
Last modified: 2025-08-31
Image_out.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini model for generating images and text in response to user prompts. It demonstrates how to create photorealistic images and engage in interactive chat-based image generation.
| Tags: image-generation, text-generation, google-colab, interactive, AI-cookbook | Task Categories: multimodal |
Last modified: 2025-08-31
Grounding.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to use the Gemini API for generating content and grounding information from various sources. It demonstrates the integration of Google Search and URL context tools to enhance the generated responses.
| Tags: gemini, information-grounding, content-generation, google-search, multimodal | Task Categories: rag,summarization,multimodal |
Last modified: 2025-08-31
Get_started_thinking_REST.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides a series of examples demonstrating how to utilize the Gemini model for various tasks, including text generation and image processing. It showcases the integration of prompts with different configurations and the handling of image data for enhanced interaction.
| Tags: gemini, text-generation, image-processing, API-integration, interactive-prompt | Task Categories: multimodal,other |
Last modified: 2025-08-31
Get_started_thinking.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of using the Gemini model for various tasks, including generating content based on text prompts and images. It demonstrates how to interact with the model in a Google Colab environment, showcasing its capabilities in reasoning and problem-solving.
| Tags: gemini, content-generation, image-analysis, problem-solving, Google Colab | Task Categories: multimodal,other |
Last modified: 2025-08-31
Get_started_imagen_rest.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for using the Gemini API to generate images based on textual prompts. It includes code snippets for making API requests and handling responses, including image processing.
| Tags: image-generation, API, Python, Google Colab, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_imagen.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for generating images using the Gemini API, specifically focusing on the Imagen model. It includes code snippets for setting up the environment, configuring image generation parameters, and displaying the generated images.
| Tags: image-generation, gemini, google-colab, api, multimodal, prompt-engineering | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_Veo_REST.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for generating videos and images using the Veo and Imagen APIs from Google Gemini. It includes code snippets for making API calls, handling responses, and displaying results in a Google Colab environment.
| Tags: video-generation, image-generation, API-integration, Google-Colab, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_Veo.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for generating videos using the Veo model from Google’s Gemini AI. It includes code snippets for setting up the environment, configuring video generation parameters, and displaying the generated videos in a Jupyter notebook environment.
| Tags: video-generation, AI-cookbook, Google-Gemini, Veo, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_TTS.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API for transforming text input into audio outputs, including single and multi-speaker scenarios. It provides examples of controlling the text-to-speech capabilities of the Gemini model, focusing on style, accent, pace, and tone.
| Tags: text-to-speech, audio generation, multispeaker, Gemini API, AI, Google Colab | Task Categories: multimodal,other |
Last modified: 2025-08-31
Get_started_OpenAI_Compatibility.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to interact with the Gemini API using the OpenAI Python library, focusing on multimodal interactions and structured outputs. It includes tasks such as text generation, image processing, and audio transcription.
| Tags: gemini, multimodal, data-extraction, image-processing, audio-transcription, text-generation | Task Categories: multimodal,rag,other |
Last modified: 2025-08-31
Get_started_LyriaRealTime.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for generating music using the Lyria RealTime model from Google. It includes code snippets for setting up the environment, parsing prompts, and generating audio files based on user-defined parameters.
| Tags: music-generation, audio, google-colab, Lyria, real-time, AI | Task Categories: other |
Last modified: 2025-08-31
Get_started_LiveAPI_tools.ipynb from google-gemini-cookbook
Summary: This cookbook provides guidance on using the Gemini 2.5 Multimodal Live API for interactive applications, showcasing how to integrate various tools and manage live sessions. It includes examples of sending prompts and handling responses in both text and audio formats.
| Tags: multimodal, live API, interactive applications, audio processing, tool integration | Task Categories: multimodal,agents |
Last modified: 2025-08-31
Get_started_LiveAPI.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Multimodal Live API, enabling users to interact with the Gemini model for both text and audio responses. It includes code examples for setting up the environment, sending messages, and receiving responses in real-time.
| Tags: multimodal, live API, audio processing, real-time interaction, Google Gemini | Task Categories: multimodal |
Last modified: 2025-08-31
Get_started_LearnLM.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the LearnLM model to create AI tutoring experiences that align with learning science principles. It provides various system instructions for different tutoring scenarios, enabling adaptive and engaging learning interactions.
| Tags: AI tutoring, LearnLM, education, adaptive learning, system instructions, cognitive load, active learning | Task Categories: other |
Last modified: 2025-08-31
Get_started.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide to using the Google Gen AI SDK with Gemini models, covering installation, text and multimodal prompting, and various functionalities like token counting and safety filters.
| Tags: gemini, text-generation, image-generation, function-calling, safety-filters, chatbot | Task Categories: multimodal,agents,other |
Last modified: 2025-08-31
Function_calling_config.ipynb from google-gemini-cookbook
Summary: The cookbook provides a guide for utilizing the Gemini API, specifically focusing on function calling configurations. It serves as a resource for developers looking to implement the latest capabilities of the Gemini framework.
| Tags: Gemini API, function calling, quickstart, configuration, Google | Task Categories: other |
Last modified: 2025-08-31
Function_calling.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini API for function calling with Python, showcasing how to create interactive chatbots that can perform various tasks such as controlling lights, performing calculations, and finding movie showtimes. It demonstrates the integration of function calling capabilities within conversational agents.
| Tags: function-calling, chatbots, API-integration, Python, Gemini | Task Categories: agents,other |
Last modified: 2025-08-31
File_API.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for using the Gemini API’s File API to upload and manage media files for multimodal prompting. It demonstrates how to integrate text, images, and audio in API calls for content generation.
| Tags: gemini, file-api, multimodal, content-generation, media-upload | Task Categories: multimodal |
Last modified: 2025-08-31
Error_handling.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to use the Gemini API for generating content with error handling and retry mechanisms. It demonstrates how to interact with the API to create various text outputs based on user prompts.
| Tags: gemini, content-generation, error-handling, retry-mechanism, api-integration | Task Categories: other |
Last modified: 2025-08-31
Enum.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini API to classify images of musical instruments and generate content based on user-defined schemas, including enums and JSON structures. It demonstrates how to integrate image processing with AI-generated responses.
| Tags: gemini, image-classification, enum, json, api-integration, content-generation | Task Categories: classification,multimodal |
Last modified: 2025-08-31
Embeddings.ipynb from google-gemini-cookbook
Summary: This cookbook provides practical examples for generating and utilizing text embeddings using the Gemini API. It demonstrates how to embed text, calculate similarities, and retrieve relevant passages based on user queries.
| Tags: embeddings, text-retrieval, cosine-similarity, dataframe, google-colab, AI-cookbook | Task Categories: rag,other |
Last modified: 2025-08-31
Counting_Tokens.ipynb from google-gemini-cookbook
Summary: This cookbook provides practical examples for using the Gemini API to count tokens for various types of content, including text, images, and audio. It demonstrates how to interact with the API and manage different data modalities effectively.
| Tags: gemini, token-counting, multimodal, API, content-analysis, Google | Task Categories: multimodal,other |
Last modified: 2025-08-31
Code_Execution.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides a comprehensive guide on using the Gemini API for code execution, allowing users to generate and run Python code based on natural language prompts. It covers various scenarios including file I/O, chat interactions, and multimodal tasks.
| Tags: code execution, Python, Gemini API, data visualization, file I/O, multimodal interactions, AI cookbook | Task Categories: multimodal,agents |
Last modified: 2025-08-31
Caching.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for implementing context caching using the Gemini API, specifically through examples involving the Apollo 11 transcript. It demonstrates how to upload documents, create caches, and interact with the cached content using the Python SDK.
| Tags: caching, gemini-api, python-sdk, transcript-analysis, contextualization | Task Categories: rag,other |
Last modified: 2025-08-31
Batch_mode.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide to using the Gemini API in batch mode for processing large volumes of requests asynchronously, ideal for high-throughput tasks such as dataset pre-processing and content generation.
| Tags: batch-processing, API, content-generation, high-throughput, asynchronous | Task Categories: multimodal,other |
Last modified: 2025-08-31
Authentication_with_OAuth.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for authenticating with the Gemini API using OAuth. It includes code snippets for setting up authentication and accessing generative language models.
| Tags: OAuth, authentication, Google Cloud, generative AI, API integration, quickstart | Task Categories: other |
Last modified: 2025-08-31
Authentication.ipynb from google-gemini-cookbook
Summary: This cookbook provides a quickstart guide for authenticating and using the Gemini API to generate content programmatically. It includes code snippets and instructions for setting up the environment and making API calls.
| Tags: API, authentication, content-generation, python, google | Task Categories: other |
Last modified: 2025-08-31
Audio.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to use the Gemini API to analyze audio files and YouTube videos, generating summaries and transcripts based on the content. It demonstrates the integration of audio processing with AI-generated content analysis.
| Tags: audio-analysis, video-summarization, transcription, AI-integration, Gemini-API | Task Categories: multimodal,summarization,classification |
Last modified: 2025-08-31
Asynchronous_requests.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of how to make asynchronous and parallel requests using the Gemini API’s Python SDK, specifically focusing on image processing and description generation. It demonstrates the use of Python’s asyncio library to handle multiple image requests efficiently.
| Tags: asynchronous, image-description, Gemini API, Python SDK, asyncio, image-processing | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
query-agent-as-a-tool.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Weaviate Query Agent with the Gemini API to interact with a database and retrieve information. It provides step-by-step instructions for setting up the necessary environment and executing queries using natural language.
| Tags: weaviate, gemini, query-agent, database-integration, natural-language-processing | Task Categories: agents |
Last modified: 2025-08-31
personalized_description_with_weaviate_and_gemini_api.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use Weaviate and the Gemini API to create personalized product descriptions by leveraging generative AI capabilities. It includes code examples for setting up collections, inserting data, and querying for product information with image display.
| Tags: personalization, product-descriptions, weaviate, gemini-api, image-display, data-insertion | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Qdrant_similarity_search.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to perform similarity search using the Gemini API and Qdrant, focusing on embedding text and retrieving relevant documents based on queries. It provides practical code examples for extracting content from a webpage, processing it into embeddings, and storing it in a Qdrant collection for efficient searching.
| Tags: similarity-search, embedding, qdrant, gemini-api, data-retrieval, text-processing | Task Categories: rag |
Last modified: 2025-08-31
Movie_Recommendation.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide to building a movie recommendation system using the Gemini API and Qdrant for efficient data retrieval and embedding. It covers data preprocessing, embedding generation, and indexing for effective movie recommendations.
| Tags: movie-recommendation, data-embedding, qdrant, gemini-api, data-preprocessing, recommendation-system | Task Categories: rag,other |
Last modified: 2025-08-31
Zero_shot_prompting.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of zero-shot prompting using the Gemini API, showcasing various tasks such as sorting, sentiment analysis, and error correction in Python code. It serves as a practical guide for developers looking to implement AI functionalities in their applications.
| Tags: zero-shot prompting, AI tasks, sentiment analysis, data extraction, error correction | Task Categories: classification,other |
Last modified: 2025-08-31
Self_ask_prompting.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of self-ask prompting using the Gemini API, demonstrating how to generate content based on user-defined prompts. It includes code snippets for setting up the API and making requests to generate answers to specific questions.
| Tags: self-ask, prompting, gemini, API, content-generation, google-colab | Task Categories: rag,other |
Last modified: 2025-08-31
Role_prompting.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini API for role prompting, showcasing how to generate content based on specific user-defined roles. It includes code snippets for generating text responses in various contexts.
| Tags: role prompting, text generation, AI cookbook, Gemini API, content creation | Task Categories: agents,other |
Last modified: 2025-08-31
Providing_base_cases.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of using the Gemini API to create generative models for specific tasks, such as assisting tourists and recommending books. It demonstrates how to configure the model and generate contextually relevant responses based on user input.
| Tags: generative AI, tourist assistance, book recommendation, API usage, Python | Task Categories: agents,other |
Last modified: 2025-08-31
Few_shot_prompting.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of few-shot prompting using the Gemini API, showcasing how to generate content based on specific prompts. It includes code snippets for sorting and extracting information from text using a pre-trained model.
| Tags: few-shot prompting, content generation, data extraction, google genai, API examples | Task Categories: other |
Last modified: 2025-08-31
Chain_of_thought_prompting.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for generating content through chain of thought prompting. It provides examples of mathematical problem-solving using the API’s capabilities.
| Tags: gemini, API, prompting, content-generation, mathematical-problems | Task Categories: other |
Last modified: 2025-08-31
Basic_Reasoning.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API’s Python SDK for performing reasoning tasks, particularly focusing on mathematical and logical problem-solving through prompting. It provides examples of generating content based on specified problems and instructions.
| Tags: gemini, reasoning, mathematical problems, logical problems, API usage | Task Categories: other |
Last modified: 2025-08-31
Basic_Information_Extraction.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for extracting grocery lists from recipes and organizing them into shopping lists. It provides practical examples of content generation using AI models.
| Tags: grocery-extraction, shopping-list, recipe-processing, AI-cookbook, content-generation | Task Categories: rag,other |
Last modified: 2025-08-31
Basic_Evaluation.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for generating and evaluating student essays. It includes prompts for both generating an essay with common mistakes and grading that essay based on specific criteria.
| Tags: essay-generation, AI-evaluation, text-analysis, Google-GenAI, education, grading | Task Categories: evaluation |
Last modified: 2025-08-31
Basic_Code_Generation.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for basic code generation tasks, specifically focusing on error handling and generating code snippets. It provides practical examples using Python to illustrate the capabilities of the API.
| Tags: code-generation, error-handling, gemini-api, python, AI-cookbook, programming-assistant | Task Categories: other |
Last modified: 2025-08-31
Basic_Classification.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API’s Python SDK for performing classification tasks through prompting. It provides examples of categorizing user comments based on their content.
| Tags: classification, gemini, API, Python SDK, social media moderation, prompting | Task Categories: classification |
Last modified: 2025-08-31
Adding_context_information.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples of using the Gemini API to generate content based on specific prompts, including the integration of context information. It demonstrates how to interact with the API to retrieve structured data related to queries.
| Tags: gemini, API, content-generation, contextual-information, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
MLflow_Observability.ipynb from google-gemini-cookbook
Summary: This cookbook provides guidance on integrating the Gemini API with MLflow for observability and experiment tracking. It includes examples of using Gemini for content generation and multi-turn conversations.
| Tags: gemini, mlflow, observability, content-generation, chatbot | Task Categories: agents |
Last modified: 2025-08-31
Gemini_LlamaIndex_QA_Chroma_WebPageReader.ipynb from google-gemini-cookbook
Summary: This cookbook provides a practical guide for implementing a question-answering system using the Gemini model with LlamaIndex and Chroma. It demonstrates how to extract data from web pages, create embeddings, and query the indexed documents effectively.
| Tags: question-answering, llama-index, chroma, data-extraction, google-genai, embedding, web-scraping | Task Categories: rag,other |
Last modified: 2025-08-31
Gemini_LangChain_Summarization_WebLoad.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API with LangChain to summarize large documents by extracting content from web pages and processing it through a language model. It provides a structured approach to creating a document summarization pipeline using various components of LangChain.
| Tags: summarization, langchain, gemini, web-scraping, document-processing, API-integration | Task Categories: summarization |
Last modified: 2025-08-31
Gemini_LangChain_QA_Pinecone_WebLoad.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to implement a question-answering system using the Gemini model, LangChain, and Pinecone for vector storage. It provides step-by-step instructions for loading documents, creating embeddings, and querying the model for answers based on the context provided.
| Tags: rag, question-answering, langchain, pinecone, gemini | Task Categories: rag,other |
Last modified: 2025-08-31
Gemini_LangChain_QA_Chroma_WebLoad.ipynb from google-gemini-cookbook
Summary: This cookbook provides a guide for implementing a question-answering system using the Gemini model with LangChain and Chroma. It demonstrates how to load web data, process it, and utilize generative AI for answering queries based on the retrieved information.
| Tags: rag, question-answering, langchain, gemini, chroma, data-extraction | Task Categories: rag,other |
Last modified: 2025-08-31
Code_analysis_using_Gemini_LangChain_and_DeepLake.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to perform code analysis using the Gemini API in conjunction with LangChain and DeepLake. It provides examples of how to load, split, and retrieve documents using generative AI models.
| Tags: code-analysis, langchain, gemini, deep-lake, retrieval-augmented-generation, python | Task Categories: rag,other |
Last modified: 2025-08-31
Chat_with_SQL_using_langchain.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Google Gemini API in conjunction with LangChain to interact with SQL databases through natural language queries. It provides a step-by-step guide to setting up a SQL database, generating queries, and retrieving results using AI models.
| Tags: SQL, LangChain, Google Gemini, data-extraction, natural-language-processing, AI agents, database-interaction | Task Categories: rag,agents |
Last modified: 2025-08-31
Text_Summarization.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for text summarization, specifically extracting characters, locations, and plot summaries from generated stories. It provides code examples for generating content and summarizing it using the API.
| Tags: text-summarization, API, story-generation, characters, locations, Google, Gemini | Task Categories: summarization,other |
Last modified: 2025-08-31
Text_Classification.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for text classification, including generating content and extracting relevant topics from the generated text. It provides practical examples and code snippets for users to implement text classification tasks effectively.
| Tags: text-classification, gemini, API, content-generation, topic-extraction | Task Categories: classification |
Last modified: 2025-08-31
Sentiment_Analysis.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for sentiment analysis by generating sentiment scores for various reviews. It provides code examples for integrating the API and processing text data to evaluate sentiment.
| Tags: sentiment-analysis, google-genai, text-processing, api-integration, python | Task Categories: classification |
Last modified: 2025-08-31
Entity_Extraction_JSON.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for entity extraction from text using Python. It provides a structured approach to identify and categorize entities such as persons, companies, and locations.
| Tags: entity-extraction, google-genai, python, json, api | Task Categories: other |
Last modified: 2025-08-31
Getting_started_with_ADK.ipynb from google-gemini-cookbook
Summary: This cookbook provides a demonstration of creating a stateful echo agent using the Google ADK and the Gemini model. It illustrates how to manage workflow states and process user interactions asynchronously.
| Tags: echo agent, workflow management, asynchronous processing, Google ADK, Gemini model, stateful interactions, Python | Task Categories: agents |
Last modified: 2025-08-31
document_search.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Gemini API for document search and retrieval using embeddings. It provides practical examples of embedding content and querying documents to find relevant information.
| Tags: document search, embeddings, generative AI, Google Gemini, retrieval-augmented generation | Task Categories: rag |
Last modified: 2025-08-31
clustering_with_embeddings.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to perform clustering on text data using embeddings generated by the Gemini model. It provides a step-by-step guide on data preprocessing, embedding generation, and visualization of clustering results using t-SNE and KMeans.
| Tags: clustering, embeddings, text-analysis, KMeans, t-SNE, data-preprocessing | Task Categories: classification,other |
Last modified: 2025-08-31
Vectordb_with_chroma.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API for document retrieval and question answering using ChromaDB as a vector database. It provides practical examples of embedding documents and querying them to generate informative responses.
| Tags: document-retrieval, question-answering, embedding, ChromaDB, Gemini API, vector-database, Python | Task Categories: rag |
Last modified: 2025-08-31
anomaly_detection.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide for anomaly detection using embeddings in text data. It demonstrates how to preprocess text, create embeddings, and visualize clusters while identifying outliers using t-SNE.
| Tags: anomaly-detection, embeddings, t-SNE, data-preprocessing, outlier-detection, Google-Gemini, machine-learning | Task Categories: classification,other |
Last modified: 2025-08-31
Working_with_Charts_Graphs_and_Slide_Decks.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini model for extracting and interpreting data from images, particularly charts and graphs, using a combination of text and image inputs. It provides practical examples of generating content based on visual data.
| Tags: gemini, data-extraction, image-analysis, charts, graphs, GCP | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
Voice_memos.ipynb from google-gemini-cookbook
Summary: This cookbook provides a framework for transforming raw thoughts and ideas into polished blog posts using audio inputs and example texts. It leverages generative AI to analyze user preferences and generate engaging content.
| Tags: generative-ai, blog-post-generation, audio-transcription, style-analysis, content-creation | Task Categories: multimodal |
Last modified: 2025-08-31
Virtual_Try_On.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to implement virtual try-on functionality using Gemini 2.5 and Imagen 3, focusing on image editing and segmentation mask generation. It provides a step-by-step guide for users to apply these techniques in a Google Colab environment.
| Tags: virtual try-on, image segmentation, Gemini 2.5, Imagen 3, Google Colab, image editing, multimodal AI | Task Categories: multimodal |
Last modified: 2025-08-31
Upload_files_to_Colab.ipynb from google-gemini-cookbook
Summary: This cookbook provides examples for using Google Colab to upload files and interact with the Gemini model for generating content. It includes practical steps for integrating external data sources into AI workflows.
| Tags: Google Colab, file upload, Gemini model, AI integration, data processing, transcript analysis | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Translate_a_Public_Domain_Book.ipynb from google-gemini-cookbook
Summary: Classification failed.
| Tags: | Task Categories: other |
Last modified: 2025-08-31
Talk_to_documents_with_embeddings.ipynb from google-gemini-cookbook
Summary: This cookbook provides a practical guide for developers to utilize the Gemini API and Google AI Studio for creating generative AI applications. It demonstrates how to embed content and retrieve relevant passages using embeddings for effective document interaction.
| Tags: embeddings, document-retrieval, generative-ai, google-ai, api-integration, data-processing | Task Categories: rag |
Last modified: 2025-08-31
Tag_and_caption_images.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API to tag and caption images of clothing, leveraging vision capabilities and embedding models for enhanced search functionality. It provides practical code examples for generating keywords and captions from images, facilitating natural language queries.
| Tags: image-tagging, caption-generation, embedding-model, clothing-recognition, natural-language-search | Task Categories: multimodal |
Last modified: 2025-08-31
Story_Writing_with_Prompt_Chaining.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize prompt chaining and iterative generation techniques for writing a compelling story using AI. It guides users through the process of breaking down complex writing tasks into manageable steps, allowing for detailed and structured storytelling.
| Tags: story-writing, prompt-chaining, iterative-generation, AI, creative-writing | Task Categories: other |
Last modified: 2025-08-31
Spatial_understanding_3d.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to utilize the Gemini model for 3D spatial understanding and image analysis. It provides code examples for loading images, processing them, and generating content based on the visual data.
| Tags: image-analysis, 3D-spatial-understanding, gemini, python, colab, visualization | Task Categories: multimodal |
Last modified: 2025-08-31
Search_reranking_using_embeddings.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides examples of using the Gemini model for search re-ranking and information extraction from Wikipedia. It demonstrates how to generate relevant search queries and summarize results based on user queries.
| Tags: rag, information-extraction, search-re-ranking, wikipedia-api, gemini | Task Categories: rag,agents |
Last modified: 2025-08-31
Search_grounding_for_research_report.ipynb from google-gemini-cookbook
Summary: This AI cookbook provides a framework for generating company research reports using Google’s Gemini model and Google Search for grounding information. It demonstrates how to set up the model, configure it for specific tasks, and handle the output effectively.
| Tags: company-research, google-search, gemini, report-generation, AI-cookbook, data-extraction | Task Categories: rag,agents |
Last modified: 2025-08-31
Search_Wikipedia_using_ReAct.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the ReAct framework to perform question answering tasks by leveraging Wikipedia as a knowledge source. It provides structured examples of thought, action, and observation steps to guide the model in retrieving and processing information effectively.
| Tags: rag, question-answering, wikipedia, google-generativeai, react | Task Categories: rag,agents |
Last modified: 2025-08-31
Pdf_structured_outputs_on_invoices_and_forms.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for automated extraction of structured data from PDF invoices and forms using Python. It provides a step-by-step guide on setting up the environment, creating a client, and defining data models for extraction.
| Tags: data-extraction, invoice-processing, form-processing, gemini-api, pydantic, python-sdk | Task Categories: rag,other |
Last modified: 2025-08-31
Opossum_search.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to generate a simple web application using the Gemini API, specifically creating a search tool that modifies Google search queries. It provides a practical example of using AI to automate coding tasks.
| Tags: web-app, code-generation, AI-coding, Gemini-API, HTML | Task Categories: other |
Last modified: 2025-08-31
Object_detection.ipynb from google-gemini-cookbook
Summary: This cookbook provides guidance on object detection using the Gemini 1.5 Flash model, highlighting its capabilities and linking to relevant resources. It serves as a reference for users looking to implement spatial understanding in their AI projects.
| Tags: object detection, gemini, spatial understanding, AI Studio, notebook | Task Categories: other |
Last modified: 2025-08-31
Market_a_Jet_Backpack.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API to analyze a product sketch and create a marketing campaign, including generating product descriptions and website copy in JSON format.
| Tags: marketing, product-analysis, json-output, image-analysis, campaign-creation | Task Categories: multimodal,other |
Last modified: 2025-08-31
LiveAPI_plotting_and_mapping.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates the use of the Gemini 2.X API for multimodal interactions, including text and audio processing, and integrates various tools for data visualization and mapping.
| Tags: multimodal, API, data-visualization, audio-processing, Google-Colab | Task Categories: multimodal,agents |
Last modified: 2025-08-31
Guess_the_shape.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API to generate content based on a sequence of images, specifically asking the model to predict the next shape in a series. It provides a practical example of integrating image inputs with AI model prompts.
| Tags: gemini, image-prediction, multimodal, AI-cookbook, shapes, content-generation | Task Categories: multimodal |
Last modified: 2025-08-31
Google_IO2025_Live_Coding.ipynb from google-gemini-cookbook
Summary: This cookbook provides a hands-on guide to exploring the capabilities of the Gemini API, demonstrating how to create generative media, including images and videos, using various models. It allows developers to experiment with different prompts and experience the versatility of the Gemini API in building AI-powered applications.
| Tags: gemini, image-generation, video-generation, multimodal, AI-cookbook, Google-API | Task Categories: multimodal,other |
Last modified: 2025-08-31
Entity_Extraction.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for entity extraction from text, providing examples of extracting street names, forms of transport, phone numbers, and URLs. It includes code snippets for implementation in a Google Colab environment.
| Tags: entity-extraction, google-colab, gemini-api, text-processing, data-extraction, API-integration | Task Categories: other |
Last modified: 2025-08-31
Classify_text_with_embeddings.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide to classifying text using embeddings generated by the Gemini model. It includes steps for data preprocessing, embedding creation, model building, training, and evaluation.
| Tags: text-classification, embeddings, gemini, keras, data-preprocessing, model-training | Task Categories: classification |
Last modified: 2025-08-31
Browser_as_a_tool.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API to connect a browser as a tool for live data retrieval and exploration. It provides examples of requesting live data, returning images from web pages, and connecting to local networks using a browser tool.
| Tags: live data, browser tool, Gemini API, multimodal, data retrieval, web scraping | Task Categories: agents,multimodal |
Last modified: 2025-08-31
Book_illustration.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to illustrate a book using Google’s Imagen and Gemini models, integrating text, image, and audio processing to create a cohesive multimedia experience.
| Tags: image-generation, text-to-image, audiobook, multimodal, Google Gemini, Imagen | Task Categories: multimodal |
Last modified: 2025-08-31
Apollo_11.ipynb from google-gemini-cookbook
Summary: This AI cookbook demonstrates how to use the Google Gemini model to analyze text files and extract specific information, such as lighthearted moments from a transcript. It provides a practical example of integrating generative AI capabilities into a Python environment using Google Colab.
| Tags: google-gemini, text-analysis, generative-ai, colab, data-extraction | Task Categories: rag,summarization |
Last modified: 2025-08-31
Anomaly_detection_with_embeddings.ipynb from google-gemini-cookbook
Summary: This cookbook provides a comprehensive guide on anomaly detection using embeddings from text data. It demonstrates how to preprocess text, create embeddings, and visualize clusters while identifying outliers in the dataset.
| Tags: anomaly-detection, embeddings, text-processing, data-visualization, outlier-detection | Task Categories: classification,other |
Last modified: 2025-08-31
Animated_Story_Video_Generation_gemini.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to generate animated story videos using Google’s Gemini API, integrating text, image, audio, and video processing. It provides a structured approach to creating engaging multimedia content by leveraging generative AI capabilities.
| Tags: animated stories, video generation, image generation, audio synthesis, multimodal AI | Task Categories: multimodal |
Last modified: 2025-08-31
Analyze_a_Video_Summarization.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini API for video summarization by analyzing video content and generating concise summaries. It includes code for uploading a video, processing it, and displaying the results using Python libraries.
| Tags: video-summarization, gemini-api, multimodal, python, colab | Task Categories: summarization,multimodal |
Last modified: 2025-08-31
Analyze_a_Video_Historic_Event_Recognition.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to utilize the Gemini API to analyze videos for historic event recognition, leveraging its multimodal capabilities. It provides a step-by-step guide for uploading a video, processing it, and extracting relevant information about the event depicted.
| Tags: video-analysis, historic-event-recognition, gemini-api, multimodal, google-colab, AI-cookbook | Task Categories: multimodal |
Last modified: 2025-08-31
Analyze_a_Video_Classification.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to use the Gemini model to classify animal species in videos by leveraging its multimodal capabilities. It provides a step-by-step guide to upload a video, process it, and obtain classification results.
| Tags: video-classification, gemini, animal-identification, multimodal, API | Task Categories: classification,multimodal |
Last modified: 2025-08-31
Agents_Function_Calling_Barista_Bot.ipynb from google-gemini-cookbook
Summary: This cookbook demonstrates how to build an interactive café ordering system using the Gemini API’s Python SDK, featuring automatic function calling to manage user orders. It includes functions for adding, removing, and confirming orders, along with a structured prompt for the AI agent to follow.
| Tags: café ordering, AI agents, function calling, Gemini API, Python SDK, interactive systems, Barista bot | Task Categories: agents |
Last modified: 2025-08-31
grammar_dataset_process.ipynb from meta-llama-cookbook
Summary: This cookbook provides a structured approach to preprocess grammar datasets for training AI models, focusing on correcting spacing issues and generating CSV files for input-output pairs. It utilizes the Jfleg dataset and integrates additional datasets for comprehensive training.
| Tags: grammar correction, data preprocessing, dataset integration, csv generation, fine-tuning | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
prompt_guard_tutorial.ipynb from meta-llama-cookbook
Summary: This cookbook provides practical guidance on using the Prompt Guard model for classifying text inputs and evaluating their potential for malicious content. It includes code examples for loading the model, evaluating text, and visualizing results.
| Tags: prompt-guard, text-classification, malicious-content-detection, model-evaluation, transformers | Task Categories: classification,evaluation |
Last modified: 2025-08-31
llama_guard_text_and_vision_inference.ipynb from meta-llama-cookbook
Summary: This cookbook provides inference scripts for utilizing the Llama Guard 3 models, including both text-only and multimodal capabilities, allowing users to generate responses based on text prompts and images. It demonstrates how to load models and run inference using the Hugging Face Transformers library.
| Tags: Llama Guard, multimodal, inference, Hugging Face, transformers, image processing, AI cookbook | Task Categories: multimodal,other |
Last modified: 2025-08-31
llama_guard_finetuning_multiple_violations_with_torchtune.ipynb from meta-llama-cookbook
Summary: This cookbook provides a guide for fine-tuning the Llama Guard model to detect multiple privacy violations in text prompts. It includes code examples for evaluating safety and handling various categories of sensitive information.
| Tags: fine-tuning, privacy-violations, text-analysis, model-evaluation, transformers | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
llama_guard_customization_via_prompting_and_fine_tuning.ipynb from meta-llama-cookbook
Summary: This cookbook provides guidance on customizing the Llama Guard model through prompting and fine-tuning techniques to ensure safe AI interactions. It includes code examples for evaluating safety across various categories and demonstrates how to implement custom safety categories.
| Tags: safety, AI customization, prompt engineering, model evaluation, fine-tuning | Task Categories: evaluation,fine-tuning |
Last modified: 2025-08-31
code_shield_usage_demo.ipynb from meta-llama-cookbook
Summary: This cookbook provides a walkthrough for using CodeShield to scan and evaluate the security of code generated by language models. It includes examples of how to implement security checks on code snippets and handle insecure outputs.
| Tags: code security, AI, CodeShield, Python, code evaluation, hashing, insecure code | Task Categories: evaluation |
Last modified: 2025-08-31
llama-prompt-ops_101.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide for using the llama-prompt-ops library to optimize prompts for AI models. It includes instructions for setting up projects, configuring datasets, and running prompt optimization processes.
| Tags: prompt-optimization, llama, AI, fine-tuning, configuration, dataset | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
llama_inference_api.ipynb from meta-llama-cookbook
Summary: This cookbook provides a guide for using the Llama LLM API to perform inference through a Gradio interface. It demonstrates how to set up the environment, switch between models, and handle user input to generate responses from the Llama API.
| Tags: Llama, API, Gradio, inference, machine-learning, text-generation, interactive | Task Categories: other |
Last modified: 2025-08-31
quickstart_peft_finetuning.ipynb from meta-llama-cookbook
Summary: This cookbook provides a quick start guide for fine-tuning the Meta Llama 3 model using PEFT (Parameter-Efficient Fine-Tuning) techniques on a single GPU. It includes code snippets for setting up the model, training, and generating summaries from dialogues.
| Tags: fine-tuning, PEFT, Llama 3, summarization, transformers, GPU training, dialogue summarization | Task Categories: fine-tuning,summarization |
Last modified: 2025-08-31
build_with_llama_api.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide to utilizing the Llama API for various tasks, including chat completions, image handling, and function calling. It demonstrates how to interact with the Llama models effectively through code examples and practical applications.
| Tags: Llama API, chatbot, image processing, function calling, Python SDK, multimodal interaction, API integration | Task Categories: agents,multimodal,other |
Last modified: 2025-08-31
build_with_llama_4.ipynb from meta-llama-cookbook
Summary: This AI cookbook provides a comprehensive guide for developers to utilize the Llama-4 model for various tasks, including text generation and image processing. It includes code examples and instructions for setting up the model and integrating it into applications.
| Tags: Llama-4, text-generation, image-processing, developer-guide, AI-cookbook, transformers | Task Categories: multimodal,other |
Last modified: 2025-08-31
hello_llama_cloud.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize the Llama 3.1 model in the cloud using Replicate, focusing on Retrieval Augmented Generation (RAG) techniques to enhance the model’s ability to answer questions based on external data sources. It provides practical examples of setting up a conversational AI system that can handle follow-up questions and context retention.
| Tags: rag, langchain, llama-3, conversation, retrieval, api-integration | Task Categories: rag |
Last modified: 2025-08-31
video_summary.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to use LangChain’s YoutubeLoader to retrieve captions from YouTube videos and summarize the content using the Llama 3 model. It showcases methods to handle input size limitations and provides a structured approach to video summarization.
| Tags: youtube-transcript, video-summary, langchain, llama-3, text-summarization | Task Categories: summarization,rag |
Last modified: 2025-08-31
Technical_Blog_Generator.ipynb from meta-llama-cookbook
Summary: This cookbook provides a framework for generating technical blog posts using Retrieval-Augmented Generation (RAG) with Llama and Qdrant. It includes code for querying a knowledge base and generating content based on user-defined topics.
| Tags: technical blogging, rag, llama, qdrant, content generation, API integration | Task Categories: rag |
Last modified: 2025-08-31
walkthrough.ipynb from meta-llama-cookbook
Summary: This AI cookbook provides a comprehensive guide for automating issue triaging on GitHub repositories using the Llama model. It includes setup instructions, data fetching, analysis, and report generation functionalities.
| Tags: github, issue-triaging, llama, data-analysis, report-generation, automation | Task Categories: rag,classification |
Last modified: 2025-08-31
rag_mongodb_llama3_huggingface_open_source.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) pipelines using MongoDB and Hugging Face’s Llama3 model for enhanced question answering capabilities. It covers dataset preparation, database setup, data ingestion, and query processing.
| Tags: rag, mongodb, huggingface, llama3, data-ingestion, vector-search | Task Categories: rag |
Last modified: 2025-08-31
RAG_Chatbot_Example.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide to building a Meta Llama 3 chatbot that utilizes Retrieval Augmented Generation (RAG) to answer questions based on custom data. It includes deployment instructions, chatbot implementation using Gradio, and integration of RAG capabilities.
| Tags: rag, chatbot, llama, gradio, text-generation, nlp | Task Categories: rag |
Last modified: 2025-08-31
quickstart.ipynb from meta-llama-cookbook
Summary: This cookbook provides a quick demo of using Llama 3.3 to generate SQL queries based on user questions about a SQLite database. It demonstrates how to integrate LangChain with the Llama cloud provider to facilitate text-to-SQL conversions.
| Tags: text2sql, Llama, LangChain, SQLite, API integration, database querying | Task Categories: other |
Last modified: 2025-08-31
browser-use-quickstart.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide to building an AI-powered browser agent that can autonomously navigate and interact with websites using Llama 4 Scout and Playwright.
| Tags: AI agent, browser automation, Playwright, Llama 4, multimodal interaction, web scraping | Task Categories: agents,multimodal |
Last modified: 2025-08-31
walkthrough.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide for generating technical blog posts using RAG (Retrieval-Augmented Generation) with Llama and Qdrant. It includes setup instructions, code examples, and best practices for leveraging AI models to create documentation-based content.
| Tags: rag, blog-generation, llama, qdrant, sentence-transformers, api-integration, technical-writing | Task Categories: rag |
Last modified: 2025-08-31
evals_with_synthetic_data.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to generate synthetic data and evaluate the accuracy of generated reports using Llama. It emphasizes the importance of validating AI-generated outputs against ground truth data to minimize hallucinations.
| Tags: synthetic-data, evaluation, report-generation, prompt-engineering, data-validation, llama | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
tool_calling_google_api.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to build a digital assistant using the Llama 3.2 model to schedule meetings by integrating with Google Contacts and Google Calendar APIs through prompt engineering and tool calling.
| Tags: google-api, calendar, contacts, tool-calling, llama, meeting-scheduling, prompt-engineering | Task Categories: agents |
Last modified: 2025-08-31
Functions_Tools_and_Agents_with_LangChain_L1_Function_Calling.ipynb from meta-llama-cookbook
Summary: This cookbook provides a practical guide to implementing function calling and tool usage with the Llama 3 model, showcasing how to interact with APIs and manage responses effectively. It is designed for users looking to enhance their applications with AI capabilities through structured function calls.
| Tags: function-calling, API-integration, Llama-3, LangChain, weather-forecasting, AI-agents, programmatic-execution | Task Categories: agents |
Last modified: 2025-08-31
Building_Agentic_RAG_with_Llamaindex_L1_Router_Engine.ipynb from meta-llama-cookbook
Summary: This cookbook provides a practical guide for building agentic retrieval-augmented generation (RAG) systems using the LlamaIndex framework. It includes code examples for setting up query engines and processing documents to facilitate information retrieval and summarization tasks.
| Tags: rag, llama-index, query-engine, summarization, agents, document-processing | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
AI_Agents_in_LangGraph_L1_Build_an_Agent_from_Scratch.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide to building AI agents using the Llama 3 model and LangGraph framework, focusing on the ReAct (Thought-Action-Observation) paradigm. It includes practical examples and code snippets for implementing various functionalities, such as calculating values and retrieving dog weights.
| Tags: AI agents, Llama 3, LangGraph, ReAct, Python, machine learning, automation | Task Categories: agents |
Last modified: 2025-08-31
AI_Agentic_Design_Patterns_with_AutoGen_L4_Tool_Use_and_Conversational_Chess.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to create conversational agents for playing chess using the Llama 3 model and the AutoGen framework. It includes functions for generating legal moves and executing them in a chess game context, facilitating interaction between two AI players.
| Tags: chess, AI agents, conversational AI, Llama 3, AutoGen, game-playing, tool use | Task Categories: agents |
Last modified: 2025-08-31
Tool_Calling_201.ipynb from meta-llama-cookbook
Summary: This cookbook provides a structured approach to leveraging AI models for research paper analysis, including fetching, processing, and summarizing academic papers from arXiv. It integrates various tools and APIs to streamline the workflow of comparing and extracting insights from research documents.
| Tags: arxiv, summarization, research-analysis, llama, agents, data-extraction | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
Tool_Calling_101.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide on using Llama models for tool calling, demonstrating how to integrate external APIs for enhanced functionality. It covers setup, common pitfalls, and practical examples of invoking tools like brave_search and wolfram_alpha within a conversational AI context.
| Tags: tool-calling, Llama, API-integration, conversational-AI, groq, python | Task Categories: agents,other |
Last modified: 2025-08-31
Step-4-TTS-Workflow.ipynb from meta-llama-cookbook
Summary: This cookbook provides a workflow for generating audio from text using TTS models, specifically focusing on the Parler TTS and Bark models. It guides users through the process of setting up the environment, generating audio segments, and compiling them into a complete podcast.
| Tags: text-to-speech, audio-generation, podcast, transformers, machine-learning | Task Categories: multimodal |
Last modified: 2025-08-31
Step-3-Re-Writer.ipynb from meta-llama-cookbook
Summary: This cookbook provides a guide for rewriting podcast transcripts using the Llama-3.1-8B-Instruct model to enhance their engagement and realism for Text-To-Speech applications. It emphasizes the importance of character-driven dialogue and realistic conversational dynamics.
| Tags: text-generation, podcast, TTS, Llama, AI, transcript-rewriting | Task Categories: other |
Last modified: 2025-08-31
Step-2-Transcript-Writer.ipynb from meta-llama-cookbook
Summary: This cookbook provides a framework for generating engaging podcast transcripts using the Llama-3.1-70B-Instruct model. It emphasizes the creation of realistic dialogues between speakers, incorporating interruptions and anecdotes to enhance listener engagement.
| Tags: podcast, transcript generation, dialogue, AI writing, Llama model, text generation, engagement | Task Categories: other |
Last modified: 2025-08-31
Step-1 PDF-Pre-Processing-Logic.ipynb from meta-llama-cookbook
Summary: This cookbook provides a step-by-step guide to extract text from PDF documents and process it into a format suitable for podcast scripts using the Llama-3.2-1B-Instruct model. It includes code for validating PDFs, extracting text, and cleaning up the content for better usability.
| Tags: pdf-extraction, text-processing, podcast-transcripts, llama, data-cleaning | Task Categories: rag,other |
Last modified: 2025-08-31
Part_3_RAG_Setup_and_Validation.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to set up a Retrieval-Augmented Generation (RAG) pipeline using LanceDB and the Together API for embedding and retrieving clothing item descriptions and images. It includes data cleaning, embedding generation, and retrieval validation steps.
| Tags: rag, data-cleaning, embedding, image-retrieval, lancedb, together-api, multimodal | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Part_2_Cleaning_Data_and_DB.ipynb from meta-llama-cookbook
Summary: This cookbook focuses on cleaning and processing image metadata for a multi-modal retrieval-augmented generation (RAG) pipeline, utilizing various data manipulation techniques and visualizations. It addresses issues such as category hallucination and data imbalance while preparing the dataset for further analysis and model training.
| Tags: data-cleaning, image-processing, metadata, data-visualization, RAG, pandas, machine-learning | Task Categories: rag,multimodal,evaluation |
Last modified: 2025-08-31
Part_1_Data_Preparation.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide for preparing and cleaning a clothing dataset, including handling corrupt images and generating captions using a vision-language model.
| Tags: data-cleaning, image-processing, caption-generation, multimodal, dataset-preparation | Task Categories: multimodal |
Last modified: 2025-08-31
Tutorial.ipynb from meta-llama-cookbook
Summary: This cookbook provides a tutorial on breaking down a text document into manageable chunks and generating contextual keywords for each chunk using the Llama 3.1 model. It emphasizes the use of DeepInfra for model inference and guides users through the process of document preparation and keyword extraction.
| Tags: chunking, keyword-extraction, llama, deep-infra, text-processing | Task Categories: rag |
Last modified: 2025-08-31
Example_FinancialReport_RAG.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to parse financial report documents, generate contextual keywords, and evaluate the relevance of content through a retrieval-augmented generation (RAG) approach. It utilizes various libraries to handle document processing and embedding for effective information retrieval.
| Tags: rag, data-extraction, contextual-keywords, document-processing, evaluation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
using_externally_hosted_llms.ipynb from meta-llama-cookbook
Summary: This cookbook provides examples of how to use various externally hosted large language models (LLMs) such as Together, OpenAI, and Anyscale for querying. It demonstrates the integration of these models into applications by showcasing simple query examples.
| Tags: llama, OpenAI, querying, externally hosted models, AI cookbook | Task Categories: other |
Last modified: 2025-08-31
text_RAG_using_llama_on_together.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) using the Together API and Llama 3 model to enhance AI-generated storytelling based on movie data embeddings.
| Tags: rag, storytelling, embeddings, movie-data, together-api, llama-3 | Task Categories: rag |
Last modified: 2025-08-31
structured_text_extraction_from_images.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to extract structured data from images using a language vision model and a language model with JSON output capabilities. It specifically focuses on extracting line items from receipts and invoices.
| Tags: data-extraction, image-processing, json-output, receipt-analysis, structured-data | Task Categories: multimodal,other |
Last modified: 2025-08-31
pdf_to_podcast_using_llama_on_together.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to convert PDF documents into engaging podcast scripts using the Llama 3.1 model hosted on Together.ai. It provides a structured approach to analyze text, generate dialogue, and synthesize audio for a podcast format.
| Tags: podcast, text-to-speech, PDF, AI, dialogue generation, Llama, Together.ai | Task Categories: multimodal,other |
Last modified: 2025-08-31
multimodal_RAG_with_nvidia_investor_slide_deck.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize a multimodal Retrieval-Augmented Generation (RAG) approach to interact with Nvidia’s investor slide deck, enabling users to query and retrieve information effectively. It integrates text and image data to enhance the querying process and provide comprehensive responses.
| Tags: rag, multimodal, Nvidia, data-extraction, image-retrieval, API-integration, Llama | Task Categories: rag,multimodal |
Last modified: 2025-08-31
llama_contextual_RAG.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to implement Contextual Retrieval-Augmented Generation (RAG) using open-source models, focusing on enhancing document chunks with contextual information and hybrid search techniques. It provides a step-by-step guide for data ingestion and query processing to improve retrieval quality.
| Tags: rag, contextual-retrieval, data-processing, embedding, bm25, llama | Task Categories: rag,other |
Last modified: 2025-08-31
knowledge_graphs_with_structured_outputs.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to generate and visualize knowledge graphs using Large Language Models (LLMs) and JSON structured outputs. It utilizes the Together AI API to create knowledge graphs that represent relationships and components in a structured format.
| Tags: knowledge-graph, LLM, JSON, visualization, GraphViz, Together AI, structured-output | Task Categories: other |
Last modified: 2025-08-31
llamaindex_cookbook.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates the use of Llama3 with LlamaIndex for various applications including chat, retrieval-augmented generation (RAG), and structured data extraction. It provides practical examples and code snippets for implementing these functionalities.
| Tags: llama3, rag, data-extraction, chatbot, sql, agents, summarization | Task Categories: rag,agents,summarization,other |
Last modified: 2025-08-31
Building_Agentic_RAG_with_Llamaindex_L4_Building_a_Multi-Document_Agent.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to build a multi-document retrieval-augmented generation (RAG) agent using Llama 3 and LlamaIndex. It provides tools for querying and summarizing multiple research papers effectively.
| Tags: rag, multi-document, llama-index, querying, summarization, agent | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
Building_Agentic_RAG_with_Llamaindex_L3_Building_an_Agent_Reasoning_Loop.ipynb from meta-llama-cookbook
Summary: This AI cookbook demonstrates how to build an agent reasoning loop using Llama 3 and LlamaIndex, enabling complex queries over documents while maintaining memory. It provides tools for vector querying and summarization of documents, specifically focusing on the MetaGPT paper.
| Tags: rag, agent reasoning, document querying, LlamaIndex, MetaGPT, vector search, summarization | Task Categories: rag,agents |
Last modified: 2025-08-31
Building_Agentic_RAG_with_Llamaindex_L2_Tool_Calling.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize Llama 3 for building an agentic retrieval-augmented generation (RAG) system using LlamaIndex. It includes examples of function execution, vector searches, and summarization techniques.
| Tags: rag, function-calling, vector-search, summarization, llama-index, metaGPT | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
langgraph_tool_calling_agent.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to build a tool-calling agent using the LangGraph library and Llama 3, integrating various multimodal capabilities such as web search, image generation, and text-to-speech functionalities. It provides a structured approach to creating agents that can utilize tools effectively in response to user queries.
| Tags: tool-calling, multimodal, Llama3, LangGraph, agent, image-generation, text-to-speech | Task Categories: agents,multimodal |
Last modified: 2025-08-31
langgraph_rag_agent_local.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to build a local Retrieval-Augmented Generation (RAG) agent using LangGraph and Llama 3, integrating various retrieval and grading mechanisms. It focuses on advanced RAG techniques, including routing, fallback, and self-correction to enhance the performance of language models in answering user queries.
| Tags: rag, langchain, llama3, agents, retrieval, evaluation, self-correction | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
langgraph_rag_agent.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to build an advanced Retrieval-Augmented Generation (RAG) agent using LangGraph and Llama 3, incorporating routing, fallback, and self-correction mechanisms. It provides practical code examples for integrating various components to enhance LLM performance in question answering tasks.
| Tags: rag, llama-3, langchain, document-retrieval, evaluation | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
meta_lamini.ipynb from meta-llama-cookbook
Summary: This cookbook provides a comprehensive guide on tuning the Llama 3 model for SQL query generation using Lamini Memory Tuning, aiming to enhance accuracy significantly. It utilizes the ‘nba_roster’ database to demonstrate the process of reducing hallucinations and improving performance in text-to-SQL tasks.
| Tags: text-to-SQL, Llama 3, fine-tuning, Lamini, NBA database, evaluation | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
llama3_cookbook_groq.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize the Llama 3 family of large language models with LlamaIndex for various applications, including retrieval-augmented generation (RAG), chat engines, and structured data extraction. It provides practical code examples for integrating these models into different workflows.
| Tags: llama3, rag, data-extraction, chatbot, sql, agents, summarization | Task Categories: rag,agents,summarization,other |
Last modified: 2025-08-31
rag-langchain-presidential-speeches.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) using the Groq API and LangChain to analyze presidential speeches. It focuses on creating vector embeddings for speech transcripts and retrieving relevant excerpts to enhance responses from a language model.
| Tags: rag, presidential-speeches, langchain, groq, vector-embeddings, data-retrieval, text-analysis | Task Categories: rag |
Last modified: 2025-08-31
parallel-tool-use.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize the Groq API for parallel tool use in AI applications, specifically for retrieving weather data based on user queries. It showcases the integration of function calls within a chat model to enhance user interaction.
| Tags: groq, weather-api, tool-integration, chatbot, python | Task Categories: agents,other |
Last modified: 2025-08-31
llama3-stock-market-function-calling.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to use Llama 3 with Groq’s LangChain integration to perform real-time stock market analysis using the yfinance API. It provides functions for retrieving stock information and historical prices based on user queries.
| Tags: stock-analysis, yfinance, function-calling, langchain, llama3, data-visualization | Task Categories: agents,other |
Last modified: 2025-08-31
SDOH-Json-mode.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to extract and structure social determinants of health from clinical notes using the Groq API’s JSON mode, enabling better analytics and patient outreach. It showcases the integration of AI with healthcare data to derive meaningful insights from unstructured text.
| Tags: social-determinants, healthcare-analytics, data-extraction, AI-in-healthcare, bigquery, json | Task Categories: rag,classification |
Last modified: 2025-08-31
json-mode-function-calling-for-sql.ipynb from meta-llama-cookbook
Summary: This cookbook demonstrates how to utilize the Groq API for generating SQL queries to interact with DuckDB, focusing on function calling and JSON mode for improved query handling. It provides practical examples and guidelines for querying data stored in CSV files.
| Tags: SQL, DuckDB, Groq API, function calling, data querying, CSV | Task Categories: rag,agents |
Last modified: 2025-08-31
Function-Calling-101-Ecommerce.ipynb from meta-llama-cookbook
Summary: This cookbook provides a practical guide for implementing function calling in an eCommerce context using the Groq API and a language model. It demonstrates how to create orders and retrieve product information through structured function calls.
| Tags: function-calling, eCommerce, API-integration, Groq, order-management, product-retrieval | Task Categories: agents |
Last modified: 2025-08-31
Vertex_tool_calling_for_Llama_4.ipynb from meta-llama-cookbook
Summary: This cookbook provides a tutorial on using the OpenAI SDK and Vertex AI SDK in Python to make function calls via the Llama 4 Maverick model, specifically focusing on a currency exchange function as an example.
| Tags: function-calling, currency-exchange, OpenAI, Vertex AI, Llama 4, API integration, Python | Task Categories: agents,other |
Last modified: 2025-08-31
Vertex_JSON_mode_for_Llama_4.ipynb from meta-llama-cookbook
Summary: This cookbook provides a guide on using the Llama 4 Maverick model on Vertex AI to generate structured outputs, specifically for sentiment analysis of product reviews. It demonstrates how to set up the environment and utilize both OpenAI and Vertex AI SDKs for generating consistent JSON responses.
| Tags: sentiment-analysis, structured-outputs, vertex-ai, openai-sdk, llama | Task Categories: classification |
Last modified: 2025-08-31
azure_api_example.ipynb from meta-llama-cookbook
Summary: This cookbook provides examples of how to utilize the Llama 3.1 APIs offered by Microsoft Azure, including making HTTP requests and integrating with LangChain and Gradio for building chatbots. It covers deployment steps, API usage, and creating conversational agents with memory.
| Tags: Azure, Llama 3.1, API, LangChain, Gradio, chatbot, memory | Task Categories: other |
Last modified: 2025-08-31
react_llama_3_bedrock_wk.ipynb from meta-llama-cookbook
Summary: This cookbook provides techniques for integrating language models with various tools to enhance their reasoning and acting capabilities, particularly through the ReAct framework. It demonstrates how to utilize these models for tasks such as information retrieval and executing Python commands.
| Tags: ReAct, agents, information-retrieval, Python-execution, langchain, LLMs | Task Categories: agents,rag |
Last modified: 2025-08-31
prompt_engineering_with_llama_2_on_amazon_bedrock.ipynb from meta-llama-cookbook
Summary: This cookbook provides an interactive guide to prompt engineering with Llama 2 using Amazon Bedrock and LangChain, focusing on best practices for generating desired responses from large language models. It includes code examples for various tasks such as sentiment analysis, chat completions, and mathematical problem-solving.
| Tags: prompt engineering, Llama 2, Amazon Bedrock, LangChain, sentiment analysis, chatbot, code examples | Task Categories: rag,classification,other |
Last modified: 2025-08-31
getting_started_llama_3_on_amazon_bedrock.ipynb from meta-llama-cookbook
Summary: This cookbook provides a practical guide to using Amazon Bedrock with Llama models, focusing on setting up AWS credentials, listing available models, and invoking them for inference. It includes code examples for comparing responses from different model versions.
| Tags: AWS, Bedrock, Llama, inference, model-comparison, Python, boto3 | Task Categories: evaluation,other |
Last modified: 2025-08-31
tgi_messages_api_demo.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to transition from OpenAI models to open-source LLMs using the Text Generation Inference (TGI) API, allowing users to leverage the benefits of open-source models without significant code restructuring. It provides step-by-step instructions for creating inference endpoints, querying them, and integrating with popular frameworks like LangChain and LlamaIndex.
| Tags: open-source, text-generation, langchain, llama-index, Hugging Face | Task Categories: rag,agents |
Last modified: 2025-08-31
structured_generation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement structured generation in a retrieval-augmented generation (RAG) system, highlighting supporting source snippets in the output. It utilizes the Hugging Face Inference API and the Outlines library for structured text generation.
| Tags: rag, structured-generation, huggingface, json, text-generation, outlines, pydantic | Task Categories: rag,other |
Last modified: 2025-08-31
stable_diffusion_interpolation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use Stable Diffusion for image interpolation, allowing for smooth transitions between images based on latent space navigation. It provides practical examples and code snippets for generating intermediate images.
| Tags: Stable Diffusion, image interpolation, latent space, image generation, data augmentation, media production | Task Categories: other |
Last modified: 2025-08-31
semantic_segmentation_fine_tuning_inference.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide on fine-tuning a semantic segmentation model using a custom dataset, specifically focusing on sidewalk images. It includes steps for data preparation, model training, and deployment through an inference API.
| Tags: semantic-segmentation, fine-tuning, transformers, image-processing, Hugging Face | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
semantic_reranking_elasticsearch.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement semantic reranking using a Hugging Face model uploaded to an Elasticsearch cluster. It guides users through the process of indexing data and querying with a text similarity model.
| Tags: Elasticsearch, Hugging Face, semantic reranking, text similarity, data indexing, Python | Task Categories: other |
Last modified: 2025-08-31
semantic_cache_chroma_vector_database.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates the integration of a semantic caching system with a RAG (Retrieval-Augmented Generation) architecture using ChromaDB and Sentence Transformers. It aims to enhance performance by storing previously asked questions and their answers to reduce redundant database queries.
| Tags: rag, semantic-cache, chromaDB, sentence-transformers, performance-optimization | Task Categories: rag |
Last modified: 2025-08-31
rag_zephyr_langchain.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a simple Retrieval-Augmented Generation (RAG) system using the Hugging Face Zephyr model and LangChain to address GitHub issues. It provides a step-by-step guide on setting up the environment, loading data, and implementing the RAG approach without the need for model fine-tuning.
| Tags: rag, Hugging Face, LangChain, GitHub issues, text-generation, retrieval | Task Categories: rag |
Last modified: 2025-08-31
rag_with_unstructured_data.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide on building a Retrieval-Augmented Generation (RAG) system using various document types and the Unstructured library for data preprocessing. It integrates multiple technologies including Hugging Face models and LangChain for effective document management and question answering.
| Tags: rag, data-preprocessing, document-management, langchain, huggingface, text-generation | Task Categories: rag |
Last modified: 2025-08-31
rag_with_sql_reranker.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a simple retrieval-augmented generation (RAG) system that extracts information from an SQL database using Jina Reranker v2 and Mistral 7B Instruct. It guides users through the process of ranking SQL table definitions based on user queries and generating SQL queries to retrieve data.
| Tags: rag, sql, data-extraction, jina-reranker, mistral, llama-index, python | Task Categories: rag |
Last modified: 2025-08-31
rag_with_knowledge_graphs_neo4j.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to enhance reasoning capabilities using knowledge graphs in conjunction with embeddings for retrieval-augmented generation (RAG). It provides practical examples of building a knowledge graph with Neo4j and extracting insights using natural language queries.
| Tags: rag, knowledge-graph, neo4j, langchain, data-extraction, embeddings | Task Categories: rag,other |
Last modified: 2025-08-31
rag_with_hugging_face_gemma_mongodb.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using the Gemma model, MongoDB, and open-source models. It provides a step-by-step guide on data preparation, embedding generation, and querying the database for relevant information.
| Tags: rag, data-ingestion, embedding, mongodb, transformers, sentence-embedding, querying | Task Categories: rag |
Last modified: 2025-08-31
rag_with_hugging_face_gemma_elasticsearch.ipynb from huggingface-cookbook
Summary: This cookbook guides users in building a Retrieval-Augmented Generation (RAG) system using Elasticsearch and Hugging Face models, allowing for flexible vectorization options. It provides step-by-step instructions for setting up the environment, loading datasets, and indexing data for efficient retrieval.
| Tags: rag, elasticsearch, hugging-face, data-ingestion, vectorization | Task Categories: rag |
Last modified: 2025-08-31
rag_with_hf_and_milvus.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using Hugging Face and Milvus. It guides users through the process of retrieving relevant documents from a vector database and generating answers using a language model.
| Tags: rag, Hugging Face, Milvus, vector database, document retrieval, language model, text generation | Task Categories: rag |
Last modified: 2025-08-31
rag_llamaindex_librarian.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on creating a lightweight RAG (Retrieval-Augmented Generation) eBook assistant using LlamaIndex and Ollama. It guides users through the process of setting up a local environment to query eBooks effectively.
| Tags: rag, ebook-assistant, llama-index, ollama, local-models, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
rag_evaluation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to evaluate Retrieval Augmented Generation (RAG) systems by constructing a synthetic evaluation dataset and using LLMs to assess the accuracy of the system. It provides a comprehensive approach to benchmarking RAG systems and highlights the importance of monitoring performance improvements.
| Tags: rag, evaluation, llm, data-generation, accuracy-assessment | Task Categories: rag,evaluation |
Last modified: 2025-08-31
prompt_tuning_peft.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide on how to use the PEFT library for prompt tuning of pre-trained models, specifically focusing on the Bloom family of models. It includes code examples and explanations for training models on different datasets while maintaining the original model’s weights.
| Tags: prompt-tuning, fine-tuning, transformers, PEFT, Bloom | Task Categories: fine-tuning |
Last modified: 2025-08-31
phoenix_observability_on_hf_spaces.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to set up the Phoenix observability dashboard on Hugging Face Spaces for tracking LLM applications. It provides step-by-step instructions for instrumenting applications using OpenAI and CrewAI to enable observability and tracing of model calls.
| Tags: observability, tracing, LLM, Hugging Face, OpenTelemetry, CrewAI, Phoenix | Task Categories: agents,other |
Last modified: 2025-08-31
multimodal_rag_using_document_retrieval_and_vlms.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a multimodal retrieval-augmented generation (RAG) system by integrating document retrieval models with visual language models. It focuses on enhancing query responses using both textual and visual data without relying on complex document processing pipelines.
| Tags: rag, multimodal, document-retrieval, visual-language-models, image-processing, transformers | Task Categories: rag,multimodal |
Last modified: 2025-08-31
multiagent_web_assistant.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide to building a multi-agent web browser system that collaborates to solve problems using internet resources. It demonstrates how to create and manage agents that can perform web searches and fetch webpage content in a structured manner.
| Tags: multi-agent, web browsing, information retrieval, transformers, DuckDuckGo, markdown | Task Categories: agents |
Last modified: 2025-08-31
multiagent_rag_system.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to building a multi-agent retrieval-augmented generation (RAG) system that combines the strengths of retrieval and generation models. It demonstrates how to set up various agents for web searching, document retrieval, and image generation using the Hugging Face Transformers and Langchain libraries.
| Tags: multi-agent, RAG, document-retrieval, image-generation, Hugging Face, Langchain | Task Categories: rag,agents,multimodal |
Last modified: 2025-08-31
llm_judge.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use a large language model (LLM) as a judge to automate the evaluation of model outputs based on human feedback. It includes methods for assessing the correlation between human ratings and LLM-generated scores.
| Tags: LLM, evaluation, feedback, correlation, automation, data-science | Task Categories: evaluation |
Last modified: 2025-08-31
llm_gateway_pii_detection.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use a wrapper for a large language model (LLM) API to clean personal identifiable information (PII) from text data before processing it. It utilizes the Cohere API and a dataset from AI4Privacy to showcase the PII cleaning functionality.
| Tags: PII detection, data privacy, API integration, Cohere, text processing, data cleaning | Task Categories: summarization,other |
Last modified: 2025-08-31
labelling_feedback_setfit.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use SetFit for zero-shot text classification and provides suggestions for data labeling in Argilla. It guides users through creating a dataset, training classifiers, and visualizing suggestions to enhance the labeling process.
| Tags: SetFit, Argilla, text-classification, zero-shot, data-labeling, MLOps | Task Categories: classification |
Last modified: 2025-08-31
issues_in_text_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a quick guide to using Cleanlab for identifying issues in a text dataset, specifically focusing on intent classification of customer service requests. It demonstrates how to extract text embeddings using a transformer model and apply a logistic regression model to detect potential label errors, outliers, and near-duplicates in the dataset.
| Tags: Cleanlab, text classification, data quality, outlier detection, label issues, transformer models, logistic regression | Task Categories: classification |
Last modified: 2025-08-31
information_extraction_haystack_nuextract.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to automate information extraction from text data using language models and the Haystack framework. It provides a structured approach to extracting specific information from given text or URLs.
| Tags: information-extraction, haystack, nuextract, data-extraction, pipeline | Task Categories: rag,other |
Last modified: 2025-08-31
generate_preference_dataset_distilabel.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to generate a synthetic preference dataset using the Distilabel framework, integrating various components for data loading, text generation, and evaluation. It provides a structured approach to create datasets suitable for reinforcement learning from human feedback (RLHF) and other preference-based learning tasks.
| Tags: preference-dataset, text-generation, evaluation, distilabel, argilla | Task Categories: evaluation,other |
Last modified: 2025-08-31
fine_tuning_vlm_trl.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune the Qwen2-VL-7B Vision Language Model using the Hugging Face ecosystem, particularly focusing on visual question answering with chart images. It provides step-by-step instructions, including dataset preparation, model configuration, and training processes.
| Tags: fine-tuning, visual-language-model, Hugging Face, ChartQA, multimodal, Qwen2-VL | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vit_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning a Vision Transformer (ViT) model on a custom biomedical dataset. It includes steps for dataset loading, image transformations, model configuration, and training with evaluation metrics.
| Tags: fine-tuning, Vision Transformer, biomedical, image classification, Hugging Face | Task Categories: fine-tuning,classification,evaluation |
Last modified: 2025-08-31
fine_tuning_llm_to_generate_persian_product_catalogs_in_json_format.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune a large language model to generate structured JSON outputs for Persian product catalogs from unstructured titles and descriptions. It utilizes efficient training techniques to optimize the model for customer-level GPU usage.
| Tags: fine-tuning, json-generation, persian-language, structured-output, llama, peft | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine_tuning_detr_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning a DETR model for object detection using a custom dataset, specifically Fashionpedia. It also covers deployment to Hugging Face Spaces and integration with Gradio API for real-world applications.
| Tags: object-detection, fine-tuning, Hugging Face, Gradio, Fashionpedia, transformers | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_code_llm_on_single_gpu.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide for fine-tuning a code language model (LLM) on a single GPU, focusing on adapting the model to specific coding styles and practices. It demonstrates how to efficiently utilize resources while training on a custom dataset derived from public GitHub repositories.
| Tags: fine-tuning, code generation, transformers, Hugging Face, GPU training, custom dataset | Task Categories: fine-tuning |
Last modified: 2025-08-31
faiss_with_hf_datasets_and_clip.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use Hugging Face’s Transformers and Datasets libraries along with FAISS for embedding multimodal data and performing similarity searches. It utilizes the CLIP model to extract features from both text and images, enabling effective retrieval of similar items based on embeddings.
| Tags: similarity-search, embedding, CLIP, FAISS, transformers, multimodal, Hugging Face | Task Categories: multimodal |
Last modified: 2025-08-31
enterprise_hub_serverless_inference_api.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to using Hugging Face’s serverless inference API for various tasks, including text generation, image creation, and text-to-speech conversion. It aims to help users quickly get started with machine learning models through simple API calls.
| Tags: Hugging Face, API, text-generation, image-generation, text-to-speech, multimodal | Task Categories: multimodal,other |
Last modified: 2025-08-31
enterprise_dedicated_endpoints.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to creating and managing dedicated inference endpoints using Hugging Face’s platform, enabling users to deploy machine learning models for text and image generation. It covers the setup, management, and API interaction for various models, including large language models and image generation models.
| Tags: inference-endpoints, text-generation, image-generation, Hugging Face, API, dedicated-endpoints | Task Categories: multimodal |
Last modified: 2025-08-31
enterprise_cookbook_gradio.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to create interactive web applications for machine learning models using Gradio, focusing on audio transcription and text organization. It provides step-by-step instructions for building demos that can be shared and deployed on Hugging Face Spaces.
| Tags: gradio, audio-transcription, text-organization, Hugging Face, interactive-demos, machine-learning | Task Categories: multimodal,other |
Last modified: 2025-08-31
enterprise_cookbook_argilla.ipynb from huggingface-cookbook
Summary: This cookbook provides a systematic workflow for evaluating large language model (LLM) outputs and creating training data for code generation tasks. It demonstrates how to assess LLM performance without fine-tuning and create high-quality test and training datasets.
| Tags: code-generation, evaluation, data-annotation, transformers, huggingface | Task Categories: evaluation,other |
Last modified: 2025-08-31
code_search.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use vector embeddings and Qdrant to navigate a codebase and find relevant code snippets using natural language queries. It provides a practical implementation of embedding models for code similarity search.
| Tags: code-search, vector-embeddings, NLP, Qdrant, code-similarity, machine-learning | Task Categories: other |
Last modified: 2025-08-31
clean_dataset_judges_distilabel.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use large language models as evaluators to clean existing preference datasets by providing AI feedback on data quality. It integrates various components from the Distilabel framework to streamline the data cleaning process.
| Tags: data-cleaning, AI-feedback, preference-datasets, distilabel, huggingface | Task Categories: evaluation,other |
Last modified: 2025-08-31
benchmarking_tgi.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide for benchmarking the TGI (Text Generation Inference) tool, detailing various configuration options and their implications for performance. It aims to help users optimize their setup for efficient text generation tasks.
| Tags: benchmarking, TGI, performance, text-generation, configuration | Task Categories: evaluation |
Last modified: 2025-08-31
automatic_embedding_tei_inference_endpoints.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide to embedding documents for semantic search using Hugging Face’s inference endpoints. It demonstrates how to load a dataset, create an inference endpoint, and process documents asynchronously to generate embeddings.
| Tags: embedding, semantic-search, Hugging Face, asyncio, inference-endpoints, datasets, text-embeddings | Task Categories: rag |
Last modified: 2025-08-31
annotate_text_data_transformers_via_active_learning.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use active learning to improve a fine-tuned Hugging Face Transformer text classification model while minimizing the total number of labels collected from human annotators. It provides practical code examples for implementing active learning strategies with multi-annotated text data.
| Tags: active learning, text classification, transformers, Hugging Face, data annotation, machine learning | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
analyzing_art_with_hf_and_fiftyone.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to analyze art styles using multimodal embeddings and the FiftyOne library, leveraging datasets from Hugging Face. It includes techniques for computing similarity, uniqueness, and visualizations of art data.
| Tags: art-analysis, multimodal, fiftyone, embeddings, similarity, uniqueness, visualization | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
agents.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build intelligent agents using Transformers Agents, capable of performing tasks like image generation and web searching. It showcases the integration of various tools to enhance the capabilities of large language models.
| Tags: transformers, agents, image-generation, web-search, langchain, multimodal | Task Categories: agents,multimodal |
Last modified: 2025-08-31
agent_text_to_sql.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build an intelligent agent that can perform SQL queries using natural language input, enhancing the robustness of SQL query generation through critical evaluation and error correction. It utilizes the Transformers library to integrate SQLAlchemy for database interactions.
| Tags: sql, agents, transformers, error-correction, database | Task Categories: agents |
Last modified: 2025-08-31
agent_rag.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to implementing a Retrieval-Augmented Generation (RAG) agent that enhances information retrieval through self-querying techniques. It leverages various libraries to process documents, create embeddings, and evaluate responses based on a knowledge base.
| Tags: rag, self-query, document-retrieval, langchain, evaluation, knowledge-base | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
agent_data_analyst.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide to creating an AI agent for data analysis, specifically using the Titanic dataset to extract insights and visualize data trends.
| Tags: data-analysis, AI-agent, Titanic-dataset, visualization, transformers, machine-learning, Python | Task Categories: agents,other |
Last modified: 2025-08-31
advanced_rag.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide on building an advanced Retrieval-Augmented Generation (RAG) system using LangChain with HuggingFace documentation as the knowledge base. It covers various components and techniques to optimize the performance of RAG systems.
| Tags: rag, langchain, huggingface, text-processing, data-retrieval, machine-learning | Task Categories: rag |
Last modified: 2025-08-31
semantic_segmentation_fine_tuning_inference.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide for fine-tuning a semantic segmentation model using a custom dataset of labeled sidewalk images. It also demonstrates how to deploy the trained model using a serverless inference API.
| Tags: semantic-segmentation, fine-tuning, transformers, Hugging Face, image-processing, model-deployment | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
fine_tuning_vit_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning the Vision Transformer (ViT) model on a custom biomedical dataset, including data loading, transformation, model configuration, and evaluation. It emphasizes practical steps for implementing image classification tasks using deep learning techniques.
| Tags: fine-tuning, image classification, Vision Transformer, biomedical data, Hugging Face | Task Categories: fine-tuning,evaluation,classification |
Last modified: 2025-08-31
fine_tuning_detr_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning the DETR model for object detection using a custom dataset, specifically Fashionpedia. It includes steps for data preparation, model training, and deployment using Gradio.
| Tags: object-detection, fine-tuning, DETR, Fashionpedia, Gradio, transformers, image-processing | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_code_llm_on_single_gpu.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide on how to fine-tune a code language model on a single GPU using specific datasets and parameters. It emphasizes optimizing the training process to fit within the constraints of available resources while enhancing the model’s contextual awareness for specific coding tasks.
| Tags: fine-tuning, code generation, transformers, Hugging Face, GPU optimization, machine learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
agents.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to create agents using Transformers Agents, enabling the integration of various tools to solve specific problems. It showcases the capabilities of these agents in multimodal tasks such as image generation and web searching.
| Tags: transformers, agents, image-generation, web-search, multimodal, langchain | Task Categories: agents,multimodal |
Last modified: 2025-08-31
agent_data_analyst.ipynb from huggingface-cookbook
Summary: This cookbook provides a framework for creating an AI agent capable of analyzing data, specifically using the Titanic dataset to predict survival rates and visualize trends through plots.
| Tags: data-analysis, machine-learning, titanic, visualization, agents, python | Task Categories: agents,evaluation |
Last modified: 2025-08-31
structured_generation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system that highlights the sources of answers provided by a language model. It utilizes structured generation techniques to ensure outputs follow specific patterns and formats.
| Tags: rag, structured-generation, huggingface, text-generation, json, pydantic, data-extraction | Task Categories: rag |
Last modified: 2025-08-31
rag_zephyr_langchain.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to quickly build a retrieval-augmented generation (RAG) system for GitHub issues using the EEVE Korean model and LangChain. It provides a practical guide for integrating external data sources to enhance the capabilities of large language models.
| Tags: rag, langchain, github, text-generation, korean-model, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
multiagent_web_assistant.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on creating a multi-agent web browser system that allows multiple agents to collaborate in solving problems using web resources. It demonstrates how to manage and control web search agents effectively within a hierarchical structure.
| Tags: multi-agent, web browsing, Hugging Face, collaboration, transformers, API integration, Python | Task Categories: agents |
Last modified: 2025-08-31
ko_rag_with_knowledge_graphs_neo4j.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to enhance retrieval-augmented generation (RAG) inference using knowledge graphs, specifically with Neo4j and LangChain. It provides practical implementations for building a knowledge graph from research publications and querying it using natural language.
| Tags: rag, knowledge-graph, neo4j, langchain, data-integration, text-query | Task Categories: rag,other |
Last modified: 2025-08-31
faiss_with_hf_datasets_and_clip.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to generate and index embeddings for multimodal data using the CLIP model, 🤗Transformers, and FAISS, enabling similarity search across text and images. It provides practical examples of loading datasets, processing images and text, and retrieving similar examples based on embeddings.
| Tags: embedding, similarity-search, CLIP, transformers, FAISS, multimodal, datasets | Task Categories: multimodal |
Last modified: 2025-08-31
advanced_ko_rag.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to implementing advanced Retrieval-Augmented Generation (RAG) techniques using Hugging Face and LangChain. It includes practical examples and code snippets to facilitate the integration of various AI models and libraries.
| Tags: rag, Hugging Face, LangChain, text-generation, NLP, Python | Task Categories: rag,other |
Last modified: 2025-08-31
structured_generation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) using structured generation techniques, highlighting source snippets that support the generated answers. It provides practical examples of using the Hugging Face inference API and the outlines library for structured text generation.
| Tags: rag, structured-generation, text-generation, huggingface, outlines, json, pydantic | Task Categories: rag,other |
Last modified: 2025-08-31
llm_judge.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use a large language model (LLM) as a judge to automate the evaluation of responses to user questions. It provides a framework for assessing the quality of model outputs using human feedback as a baseline.
| Tags: LLM-as-a-judge, evaluation, feedback, correlation, datasets, automated-assessment | Task Categories: evaluation |
Last modified: 2025-08-31
vector_search_with_hub_as_backend.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide for performing vector similarity searches on datasets hosted on the Hugging Face Hub using DuckDB as a backend. It demonstrates how to create embeddings for text data and perform similarity searches both with and without indexing.
| Tags: vector-search, embeddings, duckdb, sentence-transformers, Hugging Face, similarity-search | Task Categories: other |
Last modified: 2025-08-31
trl_grpo_reasoning_advanced_reward.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates advanced techniques for fine-tuning a model using Group Relative Policy Optimization (GRPO) for mathematical reasoning tasks. It employs a multi-reward training system to enhance model performance on the GSM8K dataset.
| Tags: GRPO, fine-tuning, mathematical reasoning, multi-reward training, transformers, GSM8K, LoRA | Task Categories: fine-tuning |
Last modified: 2025-08-31
tgi_messages_api_demo.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to transition from OpenAI models to open LLMs using the Text Generation Inference (TGI) Messages API, allowing for seamless integration with existing workflows. It provides practical examples of creating inference endpoints, querying models, and utilizing LangChain and LlamaIndex for various tasks.
| Tags: TGI, open-source, text-generation, LangChain, LlamaIndex, API | Task Categories: rag,agents |
Last modified: 2025-08-31
structured_generation_vision_language_models.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use the SmolVLM-Instruct model to extract structured information from images using vision language models. It provides a step-by-step guide to setting up the model, processing images, and generating structured outputs in JSON format.
| Tags: structured-generation, image-analysis, vision-language-models, HuggingFace, data-extraction, transformers | Task Categories: multimodal,other |
Last modified: 2025-08-31
structured_generation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) systems that provide answers while highlighting supporting snippets from source documents. It showcases structured generation techniques to enforce output formats and constraints.
| Tags: rag, structured-generation, text-generation, huggingface, pydantic, json | Task Categories: rag |
Last modified: 2025-08-31
stable_diffusion_interpolation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use Stable Diffusion for image interpolation, allowing for the generation of intermediate images that transition smoothly between two given images. It provides practical examples and code snippets for implementing latent space walking to create visually appealing transitions.
| Tags: image-interpolation, stable-diffusion, latent-space, generative-models, data-augmentation, content-generation | Task Categories: other |
Last modified: 2025-08-31
semantic_segmentation_fine_tuning_inference.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning a semantic segmentation model using the Segformer architecture on a custom dataset of sidewalk images. It includes steps for data preparation, model training, and deployment via an inference API.
| Tags: semantic-segmentation, fine-tuning, transformers, image-processing, Hugging Face | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
semantic_reranking_elasticsearch.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement semantic reranking in Elasticsearch by uploading a model from Hugging Face. It guides users through the process of indexing data, creating an inference endpoint, and querying data using a text similarity retriever.
| Tags: semantic reranking, Elasticsearch, Hugging Face, text similarity, data indexing, Eland, API integration | Task Categories: other |
Last modified: 2025-08-31
semantic_cache_chroma_vector_database.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates the implementation of a semantic cache system to enhance a Retrieval-Augmented Generation (RAG) solution using Chroma DB and various AI libraries. It focuses on optimizing user query handling by storing and retrieving similar requests efficiently, thereby improving response times and reducing redundant processing.
| Tags: rag, semantic-cache, chroma-db, transformers, sentence-transformers, faiss, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
search_and_learn.ipynb from huggingface-cookbook
Summary: This cookbook provides a framework for enhancing the performance of Instruct LLMs by extending inference time to solve complex problems through a search-and-learn approach. It demonstrates how smaller models can outperform larger ones when given sufficient reasoning time.
| Tags: LLM, search-and-learn, inference, complex-problems, chatbot, performance-enhancement | Task Categories: agents,evaluation,other |
Last modified: 2025-08-31
rag_zephyr_langchain.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Retrieval Augmented Generation (RAG) system using GitHub issues and the Hugging Face Zephyr model with LangChain. It provides a practical approach to enhance language model responses by integrating external data without the need for model fine-tuning.
| Tags: rag, langchain, huggingface, text-generation, data-retrieval, github-issues | Task Categories: rag |
Last modified: 2025-08-31
rag_with_unstructured_data.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on building a Retrieval-Augmented Generation (RAG) system using various document types for pest management. It demonstrates how to preprocess unstructured data and integrate it with open-source models for embeddings and text generation.
| Tags: rag, data-preprocessing, text-generation, langchain, unstructured-data, pest-management | Task Categories: rag,other |
Last modified: 2025-08-31
rag_with_sql_reranker.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to create a Retrieval Augmented Generation (RAG) system that utilizes an SQL database for information retrieval, leveraging Jina Reranker and Mistral models to generate SQL queries and natural language answers. It provides a practical guide for integrating AI models with structured data sources to enhance query responses.
| Tags: rag, sql, data-retrieval, jina-reranker, mistral, llama-index, natural-language-processing | Task Categories: rag |
Last modified: 2025-08-31
rag_with_knowledge_graphs_neo4j.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to enhance reasoning and explainability in language models by integrating knowledge graphs with embeddings. It provides practical implementation steps for building a knowledge graph in Neo4j related to research publications and extracting insights using natural language queries.
| Tags: rag, knowledge-graphs, neo4j, langchain, data-extraction, embeddings | Task Categories: rag,other |
Last modified: 2025-08-31
rag_with_hugging_face_gemma_mongodb.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide to building a Retrieval-Augmented Generation (RAG) system using the Gemma model, MongoDB, and open-source models. It covers data preparation, embedding generation, and querying techniques to enhance the retrieval of relevant information.
| Tags: rag, mongodb, data-preparation, embedding, sentence-transformers, transformers, querying | Task Categories: rag |
Last modified: 2025-08-31
rag_with_hugging_face_gemma_elasticsearch.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to building a Retrieval-Augmented Generation (RAG) system using Elasticsearch and Hugging Face models, allowing users to choose between Elasticsearch vectorization and self-vectorization for data processing. It includes detailed steps for library installation, data preparation, and embedding generation, culminating in a functional search system for movie plots.
| Tags: rag, elasticsearch, hugging-face, data-ingestion, text-embedding, vector-search | Task Categories: rag |
Last modified: 2025-08-31
rag_with_hf_and_milvus.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) pipeline using Hugging Face and Milvus, enabling efficient document retrieval and answer generation. It provides step-by-step instructions for setting up the environment, loading documents, creating embeddings, and generating responses using a language model.
| Tags: rag, milvus, huggingface, document-retrieval, language-model | Task Categories: rag |
Last modified: 2025-08-31
rag_llamaindex_librarian.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a RAG-based ‘librarian’ for managing a local ebook library using LlamaIndex and Ollama. It focuses on leveraging lightweight, open-source tools to facilitate local execution of LLMs.
| Tags: rag, ebook-library, llama-index, ollama, local-execution, information-retrieval | Task Categories: rag |
Last modified: 2025-08-31
rag_evaluation.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to evaluate Retrieval Augmented Generation (RAG) systems by creating a synthetic evaluation dataset and utilizing LLMs to assess the accuracy of generated question-answer pairs. It emphasizes the importance of benchmarking and monitoring performance improvements in RAG systems.
| Tags: rag, evaluation, question-answering, llm, dataset-generation, performance-monitoring | Task Categories: rag,evaluation |
Last modified: 2025-08-31
prompt_tuning_peft.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to apply prompt tuning using the PEFT library on a pre-trained language model. It guides users through the process of training models with different datasets while maintaining the integrity of the foundational model.
| Tags: prompt tuning, fine-tuning, transformers, PEFT, language models, Hugging Face, text generation | Task Categories: fine-tuning |
Last modified: 2025-08-31
phoenix_observability_on_hf_spaces.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide to setting up a Phoenix observability dashboard on Hugging Face Spaces for tracing LLM applications, enabling AI engineers to visualize and evaluate their models effectively. It includes instructions for instrumenting applications with OpenAI and CrewAI for enhanced observability.
| Tags: observability, tracing, LLM, Hugging Face, OpenTelemetry, AI Engineering, Phoenix | Task Categories: agents,evaluation |
Last modified: 2025-08-31
optuna_hpo_with_transformers.ipynb from huggingface-cookbook
Summary: This cookbook provides a systematic approach to hyperparameter optimization for fine-tuning a lightweight BERT model on the IMDB dataset for text classification. It utilizes Optuna for automated hyperparameter search to enhance model performance.
| Tags: hyperparameter-optimization, BERT, text-classification, Optuna, transformers, IMDB, machine-learning | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
multimodal_rag_using_document_retrieval_and_vlms.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Multimodal Retrieval-Augmented Generation (RAG) system by integrating document retrieval with Vision Language Models (VLMs). It provides a practical approach to enhance query responses using both text-based documents and visual data.
| Tags: rag, multimodal, document-retrieval, vision-language-models, image-processing, transformers | Task Categories: rag,multimodal |
Last modified: 2025-08-31
multimodal_rag_using_document_retrieval_and_smol_vlm.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build a Multimodal Retrieval-Augmented Generation (RAG) system using lightweight models that can run on consumer GPUs, specifically integrating ColSmolVLM for document retrieval and SmolVLM as the vision-language model. It provides practical code examples and explanations for implementing the system in a Google Colab environment.
| Tags: multimodal, RAG, ColSmolVLM, SmolVLM, document-retrieval, vision-language-models | Task Categories: rag,multimodal |
Last modified: 2025-08-31
multimodal_rag_using_document_retrieval_and_reranker_and_vlms.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates the integration of multimodal retrieval-augmented generation (RAG) systems using ColQwen2 for document retrieval, MonoQwen2-VL for reranking, and Qwen2-VL as the vision language model. It is optimized for use on consumer GPUs and aims to enhance query responses by combining text and visual data.
| Tags: rag, multimodal, document-retrieval, vision-language-model, consumer-gpu, image-processing | Task Categories: rag,multimodal |
Last modified: 2025-08-31
multiagent_web_assistant.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on creating a multi-agent web browser system that utilizes several agents to collaborate in solving problems using web searches. It demonstrates how to set up a hierarchy of agents, including a managed web search agent and a code interpreter tool.
| Tags: multi-agent, web browsing, collaboration, Hugging Face, tool integration, AI agents | Task Categories: agents |
Last modified: 2025-08-31
multiagent_rag_system.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates the creation of a multi-agent Retrieval-Augmented Generation (RAG) system that combines retrieval-based systems with generative models. It showcases how multiple agents can work together to retrieve relevant information and generate outputs based on user queries.
| Tags: rag, multi-agent, information-retrieval, image-generation, text-processing, langchain | Task Categories: rag,agents,multimodal |
Last modified: 2025-08-31
mongodb_smolagents_multi_micro_agents.ipynb from huggingface-cookbook
Summary: This cookbook implements a multi-agent system for managing product orders, inventory, and deliveries using MongoDB and a language model. It demonstrates how to set up agents for various tasks such as checking stock, updating inventory, and processing orders.
| Tags: order management, inventory, mongodb, agents, smolagents, data persistence, delivery status | Task Categories: agents |
Last modified: 2025-08-31
mlflow_ray_serve.ipynb from huggingface-cookbook
Summary: This cookbook provides a streamlined approach to deploying machine learning models from a model registry using MLflow and Ray Serve, focusing on reducing boilerplate code and enabling dynamic model version selection. It emphasizes the importance of efficient model serving in production environments.
| Tags: model serving, MLflow, Ray Serve, deployment, translation, API | Task Categories: other |
Last modified: 2025-08-31
medical_rag_and_reasoning.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates the use of the HuatuoGPT-o1 model for medical question answering through Retrieval-Augmented Generation (RAG) and reasoning. It provides a structured approach to generating detailed medical responses based on a dataset of patient-doctor interactions.
| Tags: medical, rag, question-answering, transformers, healthcare, large-language-model | Task Categories: rag |
Last modified: 2025-08-31
llm_judge_evaluating_ai_search_engines_with_judges_library.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to evaluate AI search engines using the judges library, which provides tools for assessing the correctness and quality of AI-generated responses. It utilizes various AI models to generate answers to queries from a dataset and evaluates their performance.
| Tags: AI evaluation, search engines, judges, natural language processing, data analysis | Task Categories: evaluation,rag |
Last modified: 2025-08-31
llm_judge.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use a large language model (LLM) as an automated judge for evaluating the quality of responses to user questions. It provides a framework for setting up the evaluation process, including the creation of a human evaluation dataset and the use of LLMs to score answers based on their relevance and helpfulness.
| Tags: evaluation, LLM, feedback, human-judgment, automated-scoring, data-analysis | Task Categories: evaluation |
Last modified: 2025-08-31
llm_gateway_pii_detection.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use the LLM Gateway for scrubbing Personal Identifiable Information (PII) before making API calls to LLM providers. It leverages the Cohere Command R+ model and a PII dataset to showcase effective data privacy practices in AI applications.
| Tags: PII detection, data privacy, Cohere, LLM Gateway, summarization, data scrubbing | Task Categories: summarization,other |
Last modified: 2025-08-31
labelling_feedback_setfit.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on using SetFit for zero-shot text classification, specifically for sentiment and topic labeling tasks within the Argilla framework. It guides users through creating a dataset, training classifiers, and generating suggestions for data annotation.
| Tags: SetFit, Argilla, text-classification, zero-shot, data-annotation, machine-learning | Task Categories: classification |
Last modified: 2025-08-31
issues_in_text_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a quickstart tutorial on using Cleanlab to detect issues in a text dataset, specifically focusing on intent classification of customer service requests. It demonstrates how to extract text embeddings using a pretrained transformer model and identify problems such as mislabeled data, outliers, and near duplicates.
| Tags: data-cleaning, text-classification, machine-learning, data-quality, cleanlab, customer-service, intent-detection | Task Categories: classification |
Last modified: 2025-08-31
information_extraction_haystack_nuextract.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to automate information extraction from textual data using language models, specifically utilizing the Haystack framework and the NuExtract model. It provides a structured approach to extract specific information from text or URLs based on user-defined templates.
| Tags: information-extraction, data-extraction, haystack, nuextract, pipelines, components | Task Categories: rag,other |
Last modified: 2025-08-31
generate_preference_dataset_distilabel.ipynb from huggingface-cookbook
Summary: This cookbook provides a tutorial on generating a synthetic preference dataset using the distilabel framework, integrating various components for data loading, text generation, and evaluation. It demonstrates how to utilize Hugging Face’s inference API alongside Argilla for human feedback on data quality.
| Tags: preference-dataset, text-generation, evaluation, distilabel, Hugging Face | Task Categories: evaluation,other |
Last modified: 2025-08-31
finetune_t5_for_search_tag_generation.ipynb from huggingface-cookbook
Summary: This cookbook provides an end-to-end implementation of a GitHub tag generator using the T5-small model fine-tuned on a custom dataset with PEFT (LoRA). It demonstrates how to automatically generate relevant tags from GitHub repository descriptions to enhance discoverability.
| Tags: GitHub, tag generation, T5, fine-tuning, LoRA, transformers, NLP | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine_tuning_vlm_trl.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune a Vision Language Model (VLM) using the Hugging Face ecosystem, specifically leveraging the Transformer Reinforcement Learning library (TRL). It focuses on enhancing the model’s capabilities in visual question-answering by training on the ChartQA dataset, which includes various chart types and corresponding queries.
| Tags: fine-tuning, Vision Language Model, Hugging Face, ChartQA, multimodal, transformers, visual question-answering | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vlm_object_detection_grounding.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning a Vision-Language Model (VLM) for object detection grounding using the TRL framework. It demonstrates how to leverage the PaliGemma model with the RefCOCO dataset to enhance object detection capabilities through natural language grounding.
| Tags: object detection, fine-tuning, Vision-Language Model, grounding, transformers, RefCOCO, multimodal | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vlm_mpo.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune a Vision Language Model (VLM) using Mixed Preference Optimization (MPO) with the Transformer Reinforcement Learning (TRL) library. It focuses on training a model to prefer certain outputs based on a dataset of prompts and images.
| Tags: fine-tuning, vision-language model, mixed preference optimization, transformers, huggingface | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vlm_grpo_trl.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to post-train a Vision Language Model (VLM) using GRPO for reasoning capabilities within the Hugging Face ecosystem. It utilizes a dataset containing images and problem descriptions to fine-tune the model for improved reasoning and solution generation.
| Tags: fine-tuning, vision-language-model, reasoning, transformers, Hugging Face, GRPO | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vlm_dpo_smolvlm_instruct.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide to fine-tuning the SmolVLM Vision Language Model using Direct Preference Optimization (DPO) with the TRL library on consumer-grade GPUs. It demonstrates how to tailor VLMs to align with desired outputs using a preference dataset.
| Tags: fine-tuning, Vision Language Model, DPO, transformers, multimodal, Hugging Face | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_vit_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide for fine-tuning a Vision Transformer model on a custom biomedical dataset, detailing the steps for data preparation, model configuration, and training. It includes visualization and evaluation techniques to assess model performance.
| Tags: fine-tuning, Vision Transformer, biomedical, image classification, model evaluation, Hugging Face | Task Categories: fine-tuning,classification,evaluation |
Last modified: 2025-08-31
fine_tuning_smol_vlm_sft_trl.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide to fine-tune the SmolVLM Vision Language Model using the ChartQA dataset, enabling customization for visual question-answering tasks. It leverages the Hugging Face ecosystem and the Transformer Reinforcement Learning library (TRL) to facilitate the process on consumer GPUs.
| Tags: fine-tuning, Vision Language Model, ChartQA, multimodal, Hugging Face, TRL, GPU | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_llm_to_generate_persian_product_catalogs_in_json_format.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune a large language model to generate structured Persian product catalogs in JSON format from unstructured product titles and descriptions. It utilizes the PEFT library for efficient fine-tuning and employs the Vllm inference engine for optimized performance.
| Tags: fine-tuning, LLM, JSON, data-extraction, Persian, Vllm, PEFT | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine_tuning_llm_grpo_trl.ipynb from huggingface-cookbook
Summary: This cookbook guides users through the process of post-training a Large Language Model (LLM) using Group Relative Policy Optimization (GRPO) for enhanced reasoning capabilities, particularly in mathematical problem-solving. It provides practical code examples and explanations for implementing GRPO within the Hugging Face ecosystem.
| Tags: fine-tuning, GRPO, transformers, mathematical reasoning, Hugging Face | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine_tuning_granite_vision_sft_trl.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide to fine-tune IBM’s Granite Vision 3.1 2B model using the Geometric Perception dataset, which includes tasks involving both images and text. It leverages the Hugging Face ecosystem and the Transformer Reinforcement Learning library (TRL) for efficient training on consumer GPUs.
| Tags: fine-tuning, multimodal, transformers, image-processing, Hugging Face | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_detr_custom_dataset.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning the DETR object detection model on a custom dataset of fashion images, utilizing the Hugging Face ecosystem. It also covers deployment as a Gradio Space and interaction through the Gradio API.
| Tags: object detection, fine-tuning, Hugging Face, Gradio, Fashionpedia, transformers | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
fine_tuning_code_llm_on_single_gpu.ipynb from huggingface-cookbook
Summary: This cookbook provides a guide on fine-tuning a code language model (LLM) on custom code bases using a single GPU. It demonstrates how to optimize the training process to enhance the model’s contextual awareness and adapt it to specific organizational needs.
| Tags: fine-tuning, code generation, transformers, Hugging Face, GPU optimization, machine learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
fine_tune_chatbot_docs_synthetic.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to fine-tune a language model to create a domain-specific Question & Answering chatbot using synthetic data generated from documentation. It focuses on leveraging the Meta Synthetic Data Kit and efficient training techniques to adapt the model to a niche domain.
| Tags: fine-tuning, chatbot, synthetic-data, question-answering, language-model | Task Categories: fine-tuning |
Last modified: 2025-08-31
faiss_with_hf_datasets_and_clip.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to create and index embeddings from a multimodal dataset using the CLIP model, enabling similarity search across text and images. It utilizes Hugging Face’s libraries for feature extraction and FAISS for efficient indexing and retrieval.
| Tags: embedding, similarity-search, CLIP, FAISS, transformers, multimodal, feature-extraction | Task Categories: multimodal |
Last modified: 2025-08-31
enterprise_hub_serverless_inference_api.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use the Hugging Face Serverless Inference API for various tasks, including text generation, image creation, and speech synthesis. It provides practical examples and code snippets to help users get started with machine learning models.
| Tags: Hugging Face, API, text-generation, image-generation, speech-synthesis, multimodal | Task Categories: multimodal,other |
Last modified: 2025-08-31
enterprise_dedicated_endpoints.ipynb from huggingface-cookbook
Summary: This cookbook provides a comprehensive guide to creating and managing dedicated inference endpoints using the Hugging Face Hub, enabling users to deploy machine learning models for text and image generation. It covers both programmatic and UI-based approaches to set up inference APIs tailored to specific needs.
| Tags: inference-endpoints, text-generation, image-generation, Hugging Face, API, dedicated | Task Categories: multimodal |
Last modified: 2025-08-31
enterprise_cookbook_gradio.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to create interactive web demos for machine learning models using Gradio, focusing on audio transcription and text organization. It provides step-by-step examples of building interfaces for various tasks, including greeting users and transcribing audio to text.
| Tags: gradio, audio-transcription, text-organization, interactive-demos, machine-learning | Task Categories: multimodal,other |
Last modified: 2025-08-31
enterprise_cookbook_argilla.ipynb from huggingface-cookbook
Summary: This AI cookbook demonstrates a systematic workflow for evaluating LLM outputs and creating training data for code generation tasks using Argilla and Hugging Face tools. It guides users through downloading datasets, prompting models, and setting up an annotation interface for quality assessment.
| Tags: code generation, data annotation, LLM evaluation, Hugging Face, Argilla, transformers | Task Categories: evaluation,fine-tuning |
Last modified: 2025-08-31
code_search.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use vector embeddings for navigating a codebase and finding relevant code snippets through natural semantic queries. It employs two models for natural language processing and code similarity search.
| Tags: code search, vector embeddings, NLP, Qdrant, code similarity, machine learning | Task Categories: other |
Last modified: 2025-08-31
clean_dataset_judges_distilabel.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to clean an existing preference dataset using LLMs as judges, providing AI feedback on data quality. It integrates various components from the distilabel framework to facilitate the evaluation and curation of datasets.
| Tags: dataset-cleaning, LLM-evaluation, distilabel, data-quality, argilla | Task Categories: evaluation,other |
Last modified: 2025-08-31
benchmarking_tgi.ipynb from huggingface-cookbook
Summary: This cookbook provides guidance on how to benchmark the TGI (Text Generation Inference) tool effectively. It includes command-line instructions and settings to optimize performance for various use cases.
| Tags: benchmarking, TGI, performance, text-generation, AI-cookbook | Task Categories: evaluation |
Last modified: 2025-08-31
automatic_embedding_tei_inference_endpoints.ipynb from huggingface-cookbook
Summary: This cookbook provides a step-by-step guide to embedding documents for semantic search using Hugging Face’s Inference Endpoints. It demonstrates how to utilize a specific dataset and model to efficiently create embeddings and manage them through an API-based approach.
| Tags: embedding, semantic-search, Hugging Face, API, jina, datasets, inference | Task Categories: rag |
Last modified: 2025-08-31
annotate_text_data_transformers_via_active_learning.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to use active learning to optimize the labeling process for text classification tasks using Hugging Face Transformers. It focuses on minimizing the number of labels needed from human annotators while improving model performance.
| Tags: active learning, text classification, transformers, Cleanlab, Hugging Face, data annotation, machine learning | Task Categories: classification |
Last modified: 2025-08-31
analyzing_art_with_hf_and_fiftyone.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to analyze artistic styles using multimodal embeddings with the FiftyOne library and Hugging Face datasets. It includes code for loading datasets, computing similarities, and visualizing uniqueness among artworks.
| Tags: art-analysis, multimodal, embeddings, fiftyone, huggingface, similarity-computation, visualization | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
agents.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build agents using the smolagents library, enabling the integration of various tools for tasks such as web browsing and image generation. It provides practical examples and code snippets for creating multimodal agents that leverage large language models (LLMs).
| Tags: agents, image-generation, web-search, smolagents, multimodal | Task Categories: agents,multimodal |
Last modified: 2025-08-31
agent_text_to_sql.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to implement an agent that utilizes SQL for text-to-SQL tasks, enhancing performance through automatic error correction. It provides a practical example of creating SQL tables and executing queries using an agent system.
| Tags: text-to-SQL, agents, sqlalchemy, error-correction, data-management | Task Categories: agents |
Last modified: 2025-08-31
agent_rag.ipynb from huggingface-cookbook
Summary: This cookbook provides advanced techniques for implementing Retrieval-Augmented Generation (RAG) using an agent that reformulates queries and critiques retrieval results to enhance the accuracy of responses based on a knowledge base. It emphasizes the importance of semantic similarity and iterative retrieval in improving the quality of generated answers.
| Tags: rag, query-reformulation, self-query, document-retrieval, huggingface | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
agent_data_analyst.ipynb from huggingface-cookbook
Summary: This cookbook provides a framework for creating an autonomous data analysis agent that can extract insights from datasets, specifically using the Titanic dataset as an example. It demonstrates how to set up the agent, perform data analysis, and visualize results using popular data science libraries.
| Tags: data-analysis, agents, titanic, machine-learning, data-visualization, python, autonomous | Task Categories: agents,other |
Last modified: 2025-08-31
advanced_rag.ipynb from huggingface-cookbook
Summary: This cookbook demonstrates how to build an advanced Retrieval Augmented Generation (RAG) system using LangChain to answer user queries based on a specific knowledge base, in this case, the Hugging Face documentation. It covers the installation of necessary libraries, document processing, embedding, and visualization of results.
| Tags: rag, langchain, document-retrieval, text-generation, embedding, data-visualization | Task Categories: rag |
Last modified: 2025-08-31
Llama_Nemotron_VL_nano_8B.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a walkthrough for using the Llama Nemotron Nano VL model for Optical Character Recognition (OCR) and document understanding tasks. It includes code examples for processing images and extracting information using the model.
| Tags: OCR, document-understanding, NVIDIA, image-processing, API-integration, data-extraction | Task Categories: multimodal,rag |
Last modified: 2025-08-31
quickstart.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a framework for generating synthetic evaluation datasets using the NeMo Retriever. It includes instructions for preparing input data, running the pipeline, and analyzing the output results.
| Tags: synthetic-data, evaluation, nemo, data-generation, jsonl, squad | Task Categories: evaluation,other |
Last modified: 2025-08-31
4_adding_safety_guardrails.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive guide on implementing safety guardrails in AI applications using NeMo Microservices, focusing on content safety checks and model integration.
| Tags: safety, guardrails, NVIDIA, NeMo, content-safety, AI-integration | Task Categories: agents,evaluation |
Last modified: 2025-08-31
3_model_evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for evaluating AI models using the NeMo Evaluator, focusing on establishing baseline accuracy and assessing customized models. It includes code snippets for setting up evaluation jobs and retrieving results.
| Tags: model evaluation, NeMo, LoRA, custom models, accuracy benchmarking | Task Categories: evaluation,fine-tuning |
Last modified: 2025-08-31
2_finetuning_and_inference.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for fine-tuning a model using NeMo Customizer and running inference on the customized model with NVIDIA NIM. It includes steps for data preparation, namespace creation, and job management for model customization.
| Tags: fine-tuning, NVIDIA, NeMo, customization, machine learning, model deployment, inference | Task Categories: fine-tuning |
Last modified: 2025-08-31
1_data_preparation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for preparing datasets for fine-tuning and evaluating language models, specifically focusing on tool calling with NeMo Microservices. It includes code for downloading datasets, normalizing data types, and converting examples into a format suitable for model training and evaluation.
| Tags: fine-tuning, evaluation, tool-calling, dataset-preparation, NeMo | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
3_evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a guide for evaluating custom models using the NeMo Evaluator, focusing on embedding models and their performance on the BEIR benchmark. It includes setup instructions, configuration details, and evaluation job management.
| Tags: model evaluation, NeMo, embedding, BEIR, AI benchmarking, retrieval-augmented generation, configurations | Task Categories: evaluation |
Last modified: 2025-08-31
2_finetuning_and_inference.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for fine-tuning a language model using NVIDIA’s NeMo framework, including data preparation, namespace management, and model deployment. It covers the entire workflow from data upload to running inference on the customized model.
| Tags: fine-tuning, NeMo, model deployment, customization, NVIDIA | Task Categories: fine-tuning |
Last modified: 2025-08-31
1_data_preparation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a step-by-step guide for preparing the SPECTER dataset for fine-tuning embedding models using NeMo Microservices. It includes data loading, splitting, and saving processes to facilitate model training.
| Tags: SPECTER, embedding, fine-tuning, data-preparation, NeMo, Hugging Face, dataset | Task Categories: fine-tuning |
Last modified: 2025-08-31
Parallel_Rails_Tutorial.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to configuring and using the NeMo Guardrails Microservice for parallel execution of input and output rails, enhancing performance in AI applications. It includes detailed instructions on setting up guardrails configurations and best practices for deployment.
| Tags: parallel execution, NeMo Guardrails, configuration, AI safety, microservices, NVIDIA | Task Categories: agents,other |
Last modified: 2025-08-31
3-seeding-with-a-dataset.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to seed synthetic data generation using the NeMo Data Designer with an external dataset. It provides step-by-step instructions for configuring the Data Designer client and generating synthetic patient data based on a given dataset.
| Tags: synthetic data, data generation, NeMo, data designer, python, datasets, microservices | Task Categories: other |
Last modified: 2025-08-31
2-structured-outputs-and-jinja-expressions.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates the use of NeMo Data Designer for generating structured datasets using Pydantic data models and Jinja expressions. It focuses on creating a product review dataset with specific schemas and constraints.
| Tags: data-generation, structured-outputs, Jinja-expressions, Pydantic, NeMo, data-designer, product-reviews | Task Categories: other |
Last modified: 2025-08-31
1-the-basics.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates the use of NeMo Data Designer to generate synthetic product review datasets through a series of configurable sampling columns and prompts for a language model.
| Tags: data-generation, synthetic-data, NeMo, product-reviews, data-designer | Task Categories: other |
Last modified: 2025-08-31
generate-rag-evaluation-dataset.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for generating diverse evaluation datasets for Retrieval-Augmented Generation (RAG) systems, focusing on creating question-answer pairs with varying difficulty levels and reasoning types. It includes instructions for processing documents, configuring categorical distributions, and evaluating the quality of generated pairs.
| Tags: rag, data-generation, question-answering, evaluation, neural-networks, data-designer | Task Categories: rag,evaluation |
Last modified: 2025-08-31
Getting_Started_With_NeMo_Auditor.ipynb from nvidia-generativeai-examples
Summary: The NeMo Auditor cookbook provides a comprehensive guide to auditing large language models (LLMs) by running various audit jobs to identify vulnerabilities. It outlines the steps needed to set up the environment, deploy the microservice, and analyze the results of the audits.
| Tags: NVIDIA, NeMo, auditing, LLMs, Docker, microservices | Task Categories: evaluation |
Last modified: 2025-08-31
Reliability_Scoring_Win_Tie_Loss.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a framework for evaluating the reliability of human annotations against quality control standards. It includes methods for calculating metrics such as reliability, flag mismatch percentage, and overall accuracy based on evaluator responses.
| Tags: reliability, evaluation, human-annotation, quality-control, metrics | Task Categories: evaluation |
Last modified: 2025-08-31
end2end_tutorial.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive tutorial on using the NeMo Evaluator for various evaluation types, including agentic and LLM evaluations on academic benchmarks. It includes code examples for deploying models, setting up datasets, and running evaluations.
| Tags: evaluation, llm, agentic, huggingface, nemo, dataset | Task Categories: evaluation,agents |
Last modified: 2025-08-31
live_evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to perform live evaluations using the NeMo Evaluator Microservice, focusing on string checking and evaluating medical summaries with a custom LLM-as-a-judge. It provides practical examples and necessary configurations for setting up the environment.
| Tags: live-evaluation, NVIDIA, NeMo, LLM, medical-summaries, evaluation | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
LLM As a Judge.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a step-by-step guide for creating a custom evaluation setup using the NVIDIA NeMo Evaluator Microservice, specifically for the LLM-as-a-Judge task. It covers the process of setting up evaluation targets, configurations, and submitting jobs to evaluate language models.
| Tags: NVIDIA, NeMo, evaluation, LLM, custom-evaluation, huggingface | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
NeMo_Evaluator_Retriever_and_RAG_Evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to evaluating Retriever and Retrieval Augmented Generation (RAG) models using the NeMo Evaluator microservice. It includes setup instructions, example configurations, and code snippets for implementing various evaluation tasks on datasets like FiQA.
| Tags: retrieval, evaluation, rag, NVIDIA, NeMo, FiQA, embedding | Task Categories: evaluation,rag |
Last modified: 2025-08-31
llm-as-a-judge-notebook.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide on implementing a Custom LLM-as-a-Judge using NeMo Microservices for evaluating medical consultation summaries. It outlines the necessary configurations, API integrations, and evaluation metrics for assessing the quality of generated summaries.
| Tags: evaluation, custom-llm, neMo, summarization, API-integration, medical-data | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
Detailed Thinking Mode with Llama 3.3 Nemotron Super 49B.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to utilize the Llama 3.3 Nemotron Super 49B model with detailed thinking modes for various reasoning tasks. It provides examples of how to toggle between detailed thinking on and off to optimize the model’s performance for different applications.
| Tags: Llama 3.3, detailed thinking, NVIDIA, AI agents, reasoning, OpenAI | Task Categories: agents,other |
Last modified: 2025-08-31
RAG_Chain_Server_API_Client.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates how to create a generative AI chatbot using NVIDIA’s LLM and a REST FastAPI server to answer questions based on uploaded documents. It includes methods for uploading documents and generating responses using a knowledge base.
| Tags: rag, chatbot, NVIDIA, FastAPI, document-upload, llama-2, knowledge-base | Task Categories: rag |
Last modified: 2025-08-31
medical-device-training-assistant-notebook.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a guide for using the NVIDIA Medical Device Training Assistant, which leverages Retrieval Augmented Generation (RAG) to enhance training experiences for medical device operators. It allows users to interact with medical device instructions through a conversational AI interface.
| Tags: rag, medical-device-training, conversational-ai, docker, NVIDIA, healthcare, langchain | Task Categories: rag |
Last modified: 2025-08-31
generate_test_sqlite.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a Python notebook for generating a sample SQLite database filled with appointment times for a healthcare appointment assistant. It demonstrates how to create and populate a database using random data for various appointment types and providers.
| Tags: SQLite, database, healthcare, appointment scheduling, Python, data generation | Task Categories: other |
Last modified: 2025-08-31
test_chain_server.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates how to implement a simple server that generates responses to user queries using a specified API. It showcases the use of Python libraries to handle HTTP requests and process JSON data.
| Tags: API, response-generation, Python, requests, JSON, healthcare, agentic | Task Categories: agents |
Last modified: 2025-08-31
lora.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to fine-tuning the StarCoder2 model using the NeMo framework, focusing on Parameter-Efficient Fine-Tuning (PEFT) techniques like LoRA. It includes detailed instructions for setting up the environment, preparing datasets, and executing training and evaluation processes.
| Tags: fine-tuning, StarCoder2, NeMo, LoRA, NVIDIA, transformers | Task Categories: fine-tuning |
Last modified: 2025-08-31
inference.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to efficiently fine-tune the StarCoder2 model using LoRA and subsequently export it as an optimized TensorRT-LLM engine for accelerated inference. It provides practical code examples for deploying the model to Triton Inference Server.
| Tags: StarCoder2, TensorRT, inference, fine-tuning, NVIDIA, Triton, LoRA | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
slm_pretraining_sft.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to building and fine-tuning a Small Language Model (SLM) from scratch using the NeMo framework. It covers the steps for pre-training, generating text, and improving the model’s performance through supervised fine-tuning techniques.
| Tags: language-modeling, fine-tuning, NeMo, Hugging Face, text-generation, SLM, GPT | Task Categories: fine-tuning |
Last modified: 2025-08-31
megatron_gpt_eval_server.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a step-by-step guide to launching a Megatron GPT server for text generation and fine-tuning language models using the NeMo framework. It includes instructions for converting .nemo files to ensure compatibility with the evaluation script.
| Tags: Megatron GPT, NeMo, fine-tuning, language model, text generation, evaluation | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
sft.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for fine-tuning the Gemma model for instruction following tasks. It includes detailed instructions on setting up the training environment, customizing the model, and deploying it for optimized inference on NVIDIA GPUs.
| Tags: fine-tuning, instruction-following, NVIDIA, Gemma, NeMo, model-deployment | Task Categories: fine-tuning |
Last modified: 2025-08-31
lora.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to fine-tuning the Gemma model using Low-rank adapter tuning (LoRA) within the NVIDIA NeMo framework. It includes steps for data preparation, model configuration, training, and deployment to optimize inference performance on NVIDIA GPUs.
| Tags: fine-tuning, LoRA, NVIDIA NeMo, Gemma, model deployment, LLM optimization | Task Categories: fine-tuning |
Last modified: 2025-08-31
lora.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for fine-tuning the CodeGemma model using Low-rank adapter tuning (LoRA) on the Alpaca Python Code Instructions Dataset. It covers the necessary steps for customization and deployment on NVIDIA GPUs, including exporting the model to TensorRT-LLM for optimized inference performance.
| Tags: fine-tuning, LoRA, CodeGemma, NVIDIA, Python, model deployment, TensorRT | Task Categories: fine-tuning |
Last modified: 2025-08-31
synthetic_data_generation_nemo.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive guide for generating synthetic data for fine-tuning text retrievers using large language models. It includes code examples for chunking text, generating queries, and saving results in a structured format.
| Tags: synthetic-data, retriever-customization, fine-tuning, NVIDIA, text-retrieval, query-generation | Task Categories: fine-tuning,rag |
Last modified: 2025-08-31
retriever_customization.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for fine-tuning a retriever model using synthetic data generation and hard negative mining techniques. It also includes evaluation methods to assess the performance of the fine-tuned model against benchmarks.
| Tags: fine-tuning, retrieval, hard-negative-mining, NVIDIA, evaluation, Nemo | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
rapids_notebook.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates how to build a developer chatbot using RAPIDS cuDF source code and API documentation, leveraging Llama3 for natural language processing and FAISS for efficient document retrieval. It provides a step-by-step guide for developers to interact with the cuDF framework effectively.
| Tags: rag, developer chatbot, cuDF, NVIDIA, Langchain, FAISS, Llama3 | Task Categories: rag |
Last modified: 2025-08-31
pdfspeak.ipynb from nvidia-generativeai-examples
Summary: The AI cookbook provides a comprehensive guide for utilizing NVIDIA’s PDFSpeak solution, which enables users to interact with PDF documents using advanced AI technologies. It demonstrates how to extract and analyze content from PDFs, including text, tables, charts, and images, while also integrating speech capabilities.
| Tags: pdf-extraction, multimodal, NVIDIA, AI, data-analysis, speech-interaction | Task Categories: rag,multimodal |
Last modified: 2025-08-31
python_client_usage.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a quick start guide for using the NV-Ingest Python API to interact with an NV-Ingest cluster, focusing on job submission and multimodal data extraction. It includes code examples for configuring tasks, submitting jobs, and retrieving results.
| Tags: NV-Ingest, Python API, multimodal extraction, data processing, job submission | Task Categories: multimodal,other |
Last modified: 2025-08-31
cli_client_usage.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a quick start guide for using the NV-Ingest CLI client to process PDF documents, including tasks such as text extraction, image filtering, and batch processing. It outlines the necessary commands and configurations to interact with an NV-Ingest cluster effectively.
| Tags: NV-Ingest, CLI, data-extraction, batch-processing, PDF, multimodal | Task Categories: multimodal,other |
Last modified: 2025-08-31
05_complexquery_advancedRAG.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive guide for implementing a Retrieval-Augmented Generation (RAG) system using various document loaders and embedding models. It focuses on processing and embedding documents to facilitate advanced querying and chatbot functionalities.
| Tags: rag, document-embedding, chatbot, langchain, NVIDIA, evaluation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
04_Human_Like_RAG_Evaluation-AIP.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates how to use the Llama 2 model to evaluate the quality of answers generated by a Retrieval-Augmented Generation (RAG) system. It provides a structured approach to scoring responses based on their relevance, accuracy, and helpfulness.
| Tags: evaluation, rag, llama, human-like scoring, text analysis | Task Categories: evaluation,rag |
Last modified: 2025-08-31
03_eval_ragas.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for evaluating question-answering pipelines using the Ragas framework, leveraging NVIDIA’s Llama 70B model for reference-free evaluation. It includes code for setting up the environment, downloading datasets, and running various evaluation metrics.
| Tags: evaluation, rag, NVIDIA, LLM, metrics, question-answering | Task Categories: evaluation |
Last modified: 2025-08-31
02_filling_RAG_outputs_for_Evaluation.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive guide to building a Retrieval-Augmented Generation (RAG) pipeline using LangChain and NVIDIA’s AI tools. It includes detailed instructions for loading documents, embedding models, and generating responses based on user queries.
| Tags: rag, chatbot, langchain, NVIDIA, document-embedding, prompt-engineering, evaluation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
01_synthetic_data_generation.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates the process of generating synthetic question-answer pairs using large language models (LLMs) on a dataset of PDF documents. It utilizes the LangChain library for document loading and processing, and integrates with NVIDIA’s AI services for generating responses.
| Tags: synthetic-data, question-answering, langchain, NVIDIA, data-generation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
video_3_langchain_copilot_with_NIM_HF_FAISS_deployed_locally.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to create a Retrieval Augmented Generation (RAG) application using local deployment of LLM and embedding models, along with a vector database for document retrieval. It provides step-by-step instructions for processing PDF documents, generating embeddings, and building a chat interface for user interaction.
| Tags: rag, document-retrieval, embedding-model, vector-database, gradio, langchain, NVIDIA | Task Categories: rag |
Last modified: 2025-08-31
3_Synthetic_QA_Generation.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates the use of Large Language Models to generate synthetic question-answer pairs from 10-K filings, facilitating the evaluation of Retrieval-Augmented Generation systems in financial contexts.
| Tags: rag, synthetic-data, financial-analysis, data-extraction, question-answering | Task Categories: rag,evaluation |
Last modified: 2025-08-31
2_SEC_Data_Preparation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a framework for extracting structured data from SEC filings in XBRL format, facilitating the creation of a Graph-based Retrieval-Augmented Generation (GraphRAG) system. It includes functions for parsing HTML content and saving extracted sections in JSON format for further analysis.
| Tags: rag, data-extraction, financial-documents, json, XBRL, BeautifulSoup | Task Categories: rag,other |
Last modified: 2025-08-31
1_SEC_Data_Collection.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a method for downloading and processing SEC filings, extracting specific sections, and saving them in JSON format for further analysis. It is designed to support the development of a Graph-based Retrieval-Augmented Generation (GraphRAG) system for financial documents.
| Tags: SEC filings, data-extraction, JSON, financial analysis, GraphRAG | Task Categories: rag,other |
Last modified: 2025-08-31
05_Link_Prediction.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide for predicting relationships in knowledge graphs using various machine learning models, including TransE and TransR. It demonstrates how to read triplet data, train models, and suggest potential links based on graph structures.
| Tags: knowledge-graph, link-prediction, machine-learning, pykeen, networkx, NMF, data-science | Task Categories: rag,other |
Last modified: 2025-08-31
04_Evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to evaluating Retrieval-Augmented Generation (RAG) pipelines using Ragas and NVIDIA’s Nemotron-340b-reward model, focusing on efficient, reference-free evaluations that correlate with human judgment.
| Tags: rag, evaluation, NVIDIA, Ragas, LLM, reward-models, data-evaluation | Task Categories: evaluation |
Last modified: 2025-08-31
03_Dynamic_Database.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to connect a knowledge graph retrieval-augmented generation (RAG) agent to a dynamically updating database using ArangoDB. It emphasizes the importance of maintaining a persistent database for handling changes in knowledge graphs while ensuring performance is not compromised.
| Tags: knowledge graph, RAG, ArangoDB, dynamic database, NVIDIA, cuGraph, data management | Task Categories: rag,agents |
Last modified: 2025-08-31
02_LLM_Finetuning.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to fine-tuning a smaller Large Language Model (LLM) for triplet prediction using NVIDIA NeMo and deploying it with NVIDIA Inference Microservices (NIM). It covers dataset preparation, model fine-tuning, and deployment processes.
| Tags: fine-tuning, LLM, NVIDIA NeMo, triplet prediction, model deployment, NVIDIA NIM | Task Categories: fine-tuning |
Last modified: 2025-08-31
01_Graph_Triplet_Extraction.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to extract graph triplets from SEC 10-K filings using NVIDIA’s AI endpoints, transforming unstructured text into structured knowledge for financial analysis. It automates the extraction process, enabling enhanced risk assessment and compliance insights.
| Tags: rag, data-extraction, financial-analysis, knowledge-graph, NVIDIA, SEC-filings | Task Categories: rag,other |
Last modified: 2025-08-31
cyber-dev-day.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a hands-on tutorial for developing a cybersecurity vulnerability analysis tool using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques. It aims to enhance the efficiency of analyzing Common Vulnerabilities and Exposures (CVEs) in specific projects and containers.
| Tags: cybersecurity, CVE analysis, LLMs, RAG, vulnerability assessment, automation | Task Categories: rag,agents |
Last modified: 2025-08-31
dfp_azure_training.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook outlines the process of building and running a Digital Finger Printing (DFP) pipeline using Azure logs to train an autoencoder model for user behavior recognition. The trained model is intended for generating anomaly scores to assist security teams in detecting abnormal behavior.
| Tags: digital-fingerprinting, autoencoder, anomaly-detection, Azure, Morpheus, machine-learning | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
dfp_azure_chatbot.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to building and running a Digital Fingerprinting (DFP) pipeline for inference on Azure logs, leveraging pretrained models to generate anomaly scores. It also integrates a language model for natural language explanations and triage of detected anomalies.
| Tags: anomaly-detection, NLP, Azure, Morpheus, MLFlow, data-pipeline | Task Categories: rag,other |
Last modified: 2025-08-31
nvidia_nim_langgraph_glean_example.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook demonstrates how to create an enterprise chatbot that utilizes NVIDIA’s LLMs and Glean’s knowledge base to answer user queries. It provides a practical example of integrating various AI components to build a responsive agent capable of handling internal company questions.
| Tags: enterprise, chatbot, NVIDIA, Glean, RAG, LLM, knowledge base | Task Categories: rag,agents |
Last modified: 2025-08-31
DLI_Lab_Shutdown.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides scripts for shutting down various components of a 5G lab environment, including traffic generators, servers, user equipment, and network functions. It uses Python subprocess commands to manage processes effectively.
| Tags: 5G, networking, shutdown, Python, subprocess, automation, lab management | Task Categories: other |
Last modified: 2025-08-31
DLI_Lab_Setup.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a comprehensive guide for setting up a 5G network simulator using open-source tools, including the Open Air Interface and FlexRIC, to manage bandwidth allocation. It includes detailed instructions for initializing the network, configuring components, and generating traffic using the Iperf tool.
| Tags: 5G, network simulation, Open Air Interface, FlexRIC, Iperf, bandwidth allocation, traffic generation | Task Categories: other |
Last modified: 2025-08-31
intro_agents.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides an introduction to building LLM-based agents using LangGraph and LangChain, focusing on integrating NVIDIA NIM endpoints and defining tools for agent workflows. It includes practical examples of invoking models and using custom tools for various tasks.
| Tags: NVIDIA, LLM, agents, LangChain, tool integration, modular workflows, Python | Task Categories: agents |
Last modified: 2025-08-31
agentic_pipeline-DLI.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to building a 5G network configuration agent using LangGraph and LangChain, focusing on error detection and network reconfiguration. It outlines the architecture, key components, and implementation details necessary for creating a functional workflow that dynamically adjusts network parameters based on real-time log analysis.
| Tags: 5G, network-configuration, LangGraph, LangChain, agents, real-time-monitoring | Task Categories: agents |
Last modified: 2025-08-31
Automatic_5G_Network_Lab_Setup.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a guide for automating 5G network configurations using NVIDIA’s Generative AI solutions. It includes instructions for setting up the environment and managing configurations effectively.
| Tags: 5G, NVIDIA, AI, network-configuration, automation, yaml, API-key | Task Categories: agents |
Last modified: 2025-08-31
ai-podcast-assistant-phi4-mulitmodal.ipynb from nvidia-generativeai-examples
Summary: Classification failed.
| Tags: | Task Categories: other |
Last modified: 2025-08-31
vanna_with_NVIDIA.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to optimize the Vanna text-to-SQL pipeline using NVIDIA NIM and NeMo Retriever for efficient analytics on Steam game datasets. It includes data preparation, processing, and integration with various AI tools for enhanced querying capabilities.
| Tags: text-to-sql, data-preparation, NVIDIA, Vanna, Steam-dataset, analytics, langchain | Task Categories: rag,fine-tuning |
Last modified: 2025-08-31
04_Human_Like_RAG_Evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to use the Llama 3 70B Instruct model to evaluate the outputs of a Retrieval-Augmented Generation (RAG) system. It provides a structured approach to generating human-like evaluation scores for the answers produced by the RAG pipeline.
| Tags: evaluation, rag, llama, human-like scoring, data-analysis, machine-learning | Task Categories: evaluation,rag |
Last modified: 2025-08-31
03_eval_ragas.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a framework for evaluating question-answering pipelines using LLMs, specifically leveraging the Llama 3 70B Instruct model from the NVIDIA API. It aims to improve evaluation metrics by utilizing less annotated data while correlating better with human judgment.
| Tags: evaluation, llm, ragas, NVIDIA, question-answering, metrics, langchain | Task Categories: evaluation |
Last modified: 2025-08-31
02_filling_RAG_outputs_for_Evaluation.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a step-by-step guide to using a deployed Retrieval-Augmented Generation (RAG) pipeline for document ingestion and answer generation. It demonstrates how to interact with the Chain Server API to populate RAG outputs with relevant contexts and generated answers.
| Tags: rag, evaluation, document-ingestion, api-integration, data-processing, json | Task Categories: rag,evaluation |
Last modified: 2025-08-31
01_synthetic_data_generation.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates the use of large language models (LLMs) to generate question-answer pairs from a dataset of PDF files, specifically NVIDIA blogs. It utilizes the LangChain library for document loading and processing, enabling efficient handling of various data formats.
| Tags: rag, question-answering, langchain, NVIDIA, data-generation, pdf-processing | Task Categories: rag,evaluation |
Last modified: 2025-08-31
llamaindex_basic_RAG.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to utilize LlamaIndex with NVIDIA’s API Catalog to create a retrieval-augmented generation (RAG) application. It provides step-by-step instructions for setting up the environment, configuring models, and executing queries to retrieve and rank information.
| Tags: rag, nvidia, llama-index, query-engine, retrieval, embedding | Task Categories: rag |
Last modified: 2025-08-31
langchain_basic_RAG.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to build a retrieval-augmented generation (RAG) application using LangChain with NVIDIA’s hosted models for chat, embedding, and reranking. It provides step-by-step instructions for setting up the environment, loading data, and implementing a query-response system.
| Tags: rag, NVIDIA, langchain, embedding, retrieval, AI | Task Categories: rag |
Last modified: 2025-08-31
agentic_rag_with_nemo_retriever_nim.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to implementing a retrieval-augmented generation (RAG) pipeline using NVIDIA’s NeMo Retriever and LangChain framework. It focuses on enhancing the capabilities of large language models (LLMs) by integrating various retrieval strategies and evaluation mechanisms to ensure accurate and relevant responses.
| Tags: rag, NVIDIA, langchain, retrieval, evaluation, LLM, agentic | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
using_nims_with_guardrails.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a comprehensive guide to deploying NVIDIA NIM microservices integrated with NeMo Guardrails to secure generative AI applications. It includes code snippets and configurations to prevent malicious use of AI models by filtering sensitive queries.
| Tags: NVIDIA, NeMo Guardrails, generative AI, security, NIM microservices, deployment, embedding | Task Categories: rag,agents |
Last modified: 2025-08-31
RAG_for_HTML_docs_with_Langchain_NVIDIA_AI_Endpoints.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using NVIDIA AI Endpoints and LangChain to query the NVIDIA Triton documentation. It involves loading web pages, chunking the data, generating embeddings, and creating chat chains for querying the vector store.
| Tags: rag, NVIDIA, LangChain, embeddings, FAISS, documentation, chatbot | Task Categories: rag |
Last modified: 2025-08-31
RAG_Langchain_with_Local_NIM.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using NVIDIA’s NIM microservices and the Llama3-8b-instruct model. It showcases the process of creating a vector store from web pages and querying it using chat chains.
| Tags: rag, NVIDIA, LangChain, embeddings, vector store, Llama3 | Task Categories: rag |
Last modified: 2025-08-31
using_nemo_guardrails_with_LangChain_RAG.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to integrate NeMo Guardrails with a Retrieval-Augmented Generation (RAG) pipeline using LangChain and NVIDIA NIMs. It provides step-by-step instructions for setting up the environment, loading documents, and implementing a RAG system that ensures safe and accurate responses from language models.
| Tags: rag, neural-networks, NVIDIA, langchain, guardrails, text-processing, AI-integration | Task Categories: rag,other |
Last modified: 2025-08-31
NIM_tool_call_HumanInTheLoop_MultiAgents.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to integrate human-in-the-loop functionality into a multi-agent pipeline using NVIDIA’s AI models for generating promotional content and images. It provides a structured approach to creating agents that can handle specific tasks related to social media promotion.
| Tags: human-in-the-loop, multi-agents, NVIDIA, content-creation, image-generation | Task Categories: agents,multimodal |
Last modified: 2025-08-31
LangGraph_HandlingAgent_IntermediateSteps.ipynb from nvidia-generativeai-examples
Summary: This cookbook demonstrates how to build a LangChain agent executor using NVIDIA’s API and various tools, including a FAISS retriever and Wikipedia integration. It provides a step-by-step guide for setting up the environment, processing text data, and utilizing the agent for information retrieval.
| Tags: langchain, NVIDIA, agent-executor, FAISS, Wikipedia, text-processing, RAG | Task Categories: rag,agents |
Last modified: 2025-08-31
Chat_with_nvidia_financial_reports.ipynb from nvidia-generativeai-examples
Summary: This AI cookbook provides a guide for setting up a retrieval-augmented generation (RAG) system to interact with NVIDIA financial reports using Langchain and Milvus as a vector store. It includes code for installing necessary packages, extracting data from HTML, and generating answers based on user queries.
| Tags: rag, NVIDIA, financial-reports, langchain, data-extraction, vectorstore | Task Categories: rag |
Last modified: 2025-08-31
Agent_use_tools_leveraging_NVIDIA_AI_endpoints.ipynb from nvidia-generativeai-examples
Summary: This cookbook provides a framework for building a multimodal AI agent that utilizes NVIDIA’s AI Catalog for image reasoning tasks. It integrates various tools for image captioning and tabular data extraction from images, enabling users to interact with the agent through a simple web interface.
| Tags: NVIDIA AI, image-captioning, tabular-data-extraction, Gradio, LangChain, multimodal | Task Categories: agents,multimodal |
Last modified: 2025-08-31
train_gptj_smp_tensor_parallel.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tune the GPT-J-6B model using the Tensor Parallelism feature of the SageMaker Model Parallel Library. It demonstrates the process of preparing datasets, training, and deploying the model effectively on AWS infrastructure.
| Tags: GPT-J, SageMaker, fine-tuning, transformers, Tensor Parallelism, deep learning, AWS | Task Categories: fine-tuning |
Last modified: 2025-08-31
deploy_gptj_DJLModel.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to deploy a fine-tuned GPT-J model on Amazon SageMaker using the Deep Java Library (DJL) for efficient inference. It covers the steps for model preparation, deployment, and inference using SageMaker’s capabilities.
| Tags: GPT-J, SageMaker, DJL, model-deployment, fine-tuning, text-generation | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
intro_to_llm_deployment.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to deploying large language models on AWS SageMaker using the DeepSpeed container. It demonstrates the process of setting up the environment, deploying the GPT-J model, and making predictions with it.
| Tags: SageMaker, GPT-J, model deployment, DeepSpeed, AI, inference, cloud computing | Task Categories: classification,other |
Last modified: 2025-08-31
djl_accelerate_deploy_g5_12x_GPT_NeoX.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to deploy the GPT-NeoX-20B model on AWS SageMaker using DJLServing and Hugging Face Accelerate for efficient model parallel inference. It provides step-by-step instructions for setting up the environment, configuring the model, and invoking the endpoint for inference.
| Tags: SageMaker, GPT-NeoX, model deployment, DJLServing, Hugging Face, DeepSpeed, inference | Task Categories: other |
Last modified: 2025-08-31
Finetuning_LLaMa-2.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for fine-tuning LLaMA 2 models using the SageMaker JumpStart platform, specifically focusing on instruction tuning with the Dolly dataset. It includes steps for dataset preparation, model training, and deployment for inference.
| Tags: fine-tuning, LLaMA 2, SageMaker, instruction tuning, Dolly dataset, model deployment | Task Categories: fine-tuning,summarization |
Last modified: 2025-08-31
Deploy_pretrained_LLaMa-2.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to deploy and fine-tune the pre-trained LLaMA 2 model using the SageMaker Python SDK. It provides code examples for model deployment, prediction, and response handling.
| Tags: LLaMA 2, SageMaker, fine-tuning, model deployment, text generation | Task Categories: fine-tuning |
Last modified: 2025-08-31
falcon-7b-instruct-bf16-in-context-learning.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a practical guide for using Amazon SageMaker to deploy and interact with machine learning models, specifically focusing on generating responses based on customer-agent conversations. It includes code examples for setting up a predictor, invoking endpoints, and processing responses.
| Tags: sagemaker, customer-support, ai-cookbook, predictor, json | Task Categories: agents,summarization |
Last modified: 2025-08-31
stable-diffusion-inference.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to use Amazon SageMaker JumpStart to generate images from text prompts using Stable Diffusion models. It provides guidance on deploying models, running inference, and fine-tuning for specific datasets.
| Tags: image-generation, text-to-image, sagemaker, stable-diffusion, machine-learning | Task Categories: multimodal |
Last modified: 2025-08-31
stable-diffusion-finetune.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to fine-tune a Stable Diffusion model for generating images from text prompts using Amazon SageMaker JumpStart. It provides step-by-step guidance on setting up the environment, training the model, and deploying it for inference.
| Tags: fine-tuning, image-generation, text-to-image, sagemaker, stable-diffusion | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
Run_My_PlayGround.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a guide for setting up and running a Jupyter notebook environment using Amazon SageMaker, focusing on integrating various libraries for data processing and visualization. It includes code snippets for establishing connections to AWS services and displaying interactive content within a notebook interface.
| Tags: sagemaker, jupyter, aws, data-processing, interactive-visualization | Task Categories: other |
Last modified: 2025-08-31
falcon-40b-qlora-finetune-summarize.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to fine-tune the Falcon-40B model using QLoRA and Hugging Face’s PEFT library for the task of summarization. It provides step-by-step instructions for setting up the environment, preparing the dataset, and training the model.
| Tags: fine-tuning, summarization, transformers, QLoRA, Hugging Face, datasets, PEFT | Task Categories: fine-tuning,summarization |
Last modified: 2025-08-31
RAG-with-Llama-2-on-Studio.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates the construction of a Retrieval Augmented Generation (RAG) question-answering system using Llama 2 and LangChain, integrated with Pinecone for embedding storage and retrieval. It provides a comprehensive guide for setting up and deploying the model in a SageMaker environment.
| Tags: rag, llama, langchain, pinecone, question-answering, sagemaker | Task Categories: rag |
Last modified: 2025-08-31
Multilingual_Chatbot_using_E5_embedding_Meta_llama2_7b_chat.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to build a multilingual chatbot using the Llama-2-7b model and E5 multilingual embeddings in Amazon SageMaker. It utilizes retrieval-augmented generation (RAG) techniques to answer questions in English, Spanish, and Italian based on a dataset of Amazon SageMaker FAQs.
| Tags: multilingual, chatbot, SageMaker, embeddings, RAG, question-answering, E5 | Task Categories: rag |
Last modified: 2025-08-31
qwen2-chat-training.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide to fine-tune the Qwen 2 model using PyTorch and the Transformers library. It includes installation instructions, model training commands, and example code for generating text responses.
| Tags: fine-tuning, Qwen 2, transformers, PyTorch, language model, text generation, AI cookbook | Task Categories: fine-tuning |
Last modified: 2025-08-31
train_gpt_neo.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning the GPT-Neo language model using Amazon SageMaker, leveraging distributed training techniques for efficiency. It includes code snippets for data preparation, model configuration, and training execution.
| Tags: GPT-Neo, fine-tuning, SageMaker, distributed training, NLP, transformers | Task Categories: fine-tuning |
Last modified: 2025-08-31
djl_deploy_GPT_Neo.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to deploying the GPT-Neo model on AWS SageMaker using DJLServing and Hugging Face Accelerate for efficient model parallel inference. It covers the setup, model loading, and endpoint creation for serving the model in a production environment.
| Tags: SageMaker, GPT-Neo, model-serving, DeepSpeed, Hugging Face, AI deployment, cloud-computing | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
llm-finetune-separate-with-registry.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning a Llama2 7B model using LoRA techniques on Amazon SageMaker, while ensuring proper model governance through the SageMaker Model Registry. It includes detailed code examples and setup instructions for managing both adapter and base models separately.
| Tags: fine-tuning, SageMaker, Llama2, LoRA, model governance, transformers | Task Categories: fine-tuning |
Last modified: 2025-08-31
llm-finetune-combined-with-registry.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning a Llama2 model using LoRA techniques on Amazon SageMaker, while also implementing model governance through the SageMaker Model Registry. It includes detailed code examples and best practices for managing model artifacts effectively.
| Tags: fine-tuning, SageMaker, Llama2, LoRA, model governance, transformers | Task Categories: fine-tuning |
Last modified: 2025-08-31
query-llm.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to implement Retrieval Augmented Generation (RAG) techniques to query a language model using AWS services. It provides a step-by-step guide for setting up the necessary components and executing queries to generate responses based on context retrieved from a vector store.
| Tags: rag, aws, sagemaker, opensearch, llm, text-generation, data-retrieval | Task Categories: rag |
Last modified: 2025-08-31
prompt-distance-outliers.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to perform outlier analysis on prompt embeddings using AWS Glue and PySpark. It calculates z-scores to identify outliers based on the distance from prompt embeddings to reference embedding centroids.
| Tags: outlier-analysis, aws-glue, pyspark, z-score, embedding | Task Categories: rag,evaluation |
Last modified: 2025-08-31
embed-prompt-distance.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook demonstrates how to use AWS Glue and PySpark for processing and analyzing embeddings from text data. It includes steps for reading data, transforming it, applying PCA for dimensionality reduction, and clustering using KMeans, along with evaluation metrics for clustering performance.
| Tags: AWS Glue, PySpark, clustering, KMeans, PCA, data processing, embeddings | Task Categories: rag,evaluation |
Last modified: 2025-08-31
drift-embed.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates a method for detecting drift in embedding vectors using PCA for dimensionality reduction and KMeans for clustering. It establishes a baseline for comparison against new embedding data to identify changes in the underlying reference data.
| Tags: drift-detection, embedding-vectors, PCA, KMeans, machine-learning, data-analysis, baseline-comparison | Task Categories: rag |
Last modified: 2025-08-31
drift-embed-pyspark.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide for using AWS Glue and PySpark to process and analyze embedding data, including dimensionality reduction and clustering techniques. It demonstrates how to read data from S3, apply PCA for feature reduction, and utilize KMeans for clustering analysis.
| Tags: AWS Glue, PySpark, data processing, clustering, PCA, machine learning, embeddings | Task Categories: rag,evaluation |
Last modified: 2025-08-31
drift-analysis.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a method for detecting drift in embedding vectors using PCA and KMeans clustering. It outlines how to establish a baseline and compare it with newer sets of embeddings to identify changes in data distribution.
| Tags: drift-detection, embedding-analysis, PCA, KMeans, data-visualization, AWS, boto3 | Task Categories: rag,evaluation |
Last modified: 2025-08-31
distance-analysis.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a method for analyzing the distance between prompt embeddings and reference embedding centroids using AWS services and Python libraries. It includes data retrieval from DynamoDB and visualization of statistical metrics using Seaborn and Matplotlib.
| Tags: embedding-analysis, dynamodb, data-visualization, seaborn, matplotlib, aws, pandas | Task Categories: rag |
Last modified: 2025-08-31
finserv-llama2-aoss-chatbot.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to building a context-aware chatbot for financial services using the Llama2 model via Amazon SageMaker and integrating it with Amazon OpenSearch Serverless for vector search capabilities. It includes setup instructions, code examples, and best practices for deploying machine learning models in a production environment.
| Tags: chatbot, financial services, SageMaker, OpenSearch, vector search, Llama2, rag | Task Categories: rag,agents |
Last modified: 2025-08-31
sm-llama3-sftt-llama3-fine-tuning.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide for fine-tuning the Llama-3 language model using Amazon SageMaker with techniques such as FSDP and Q-LORA. It includes instructions for preparing datasets, configuring training parameters, and deploying the model effectively.
| Tags: fine-tuning, SageMaker, Llama-3, Q-LORA, FSDP, transformers, machine learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
deploypretrained-Code-LLaMa.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for deploying the pre-trained Code LLaMa model using Amazon SageMaker, focusing on code generation tasks. It includes installation instructions, code snippets, and examples of querying the model for generating various code outputs.
| Tags: code generation, SageMaker, LLaMa, langchain, AWS, machine learning | Task Categories: other |
Last modified: 2025-08-31
qwen2-chat-inference.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide to deploying the Qwen2 (0.5B parameter size) model as a SageMaker endpoint, enabling users to interact with the model for inference tasks. It includes installation of necessary libraries, configuration of model parameters, and deployment instructions.
| Tags: SageMaker, Qwen2, model-deployment, AWS, inference, machine-learning | Task Categories: other |
Last modified: 2025-08-31
Deploy_stable-diffusion-XL-model.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide to deploying the Stable Diffusion XL model using Amazon SageMaker. It includes necessary installations, imports, and code to set up the model in a cloud environment.
| Tags: stable-diffusion, image-generation, sagemaker, aws, deployment, ml | Task Categories: multimodal |
Last modified: 2025-08-31
Deploy_falcon-7b-instruct-bf16.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide to deploying the Falcon 7B Instruct model using Amazon SageMaker. It includes code snippets for setting up the environment, listing available models, and deploying the selected model to a SageMaker endpoint.
| Tags: SageMaker, Falcon 7B, model deployment, AWS, text generation, machine learning | Task Categories: other |
Last modified: 2025-08-31
sagemaker-finetuning.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for fine-tuning the LLaMA 2 model using Amazon SageMaker with a custom medical dataset. It includes steps for data preparation, model training, and evaluation, leveraging SageMaker’s capabilities for efficient model deployment.
| Tags: fine-tuning, LLaMA 2, SageMaker, transformers, medical dataset, model training, AWS | Task Categories: fine-tuning |
Last modified: 2025-08-31
cot_prompting.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook demonstrates how to utilize Amazon SageMaker for generating answers to mathematical and logical questions using a pre-trained model. It showcases the process of invoking an endpoint and handling responses for various types of queries.
| Tags: sagemaker, chain-of-thought, prompt-engineering, mathematical-reasoning, AI-cookbook, text-generation | Task Categories: other |
Last modified: 2025-08-31
advanced-code-generation-mixtral-8x7b-instruct.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides examples of generating Python code for various tasks using the Mixtral 8x7B model on Amazon SageMaker. It includes scripts for hyperparameter tuning, AWS CDK configurations, and code conversion between Java and Python.
| Tags: code-generation, AWS, SageMaker, hyperparameter-tuning, CDK, Java-to-Python, machine-learning | Task Categories: other |
Last modified: 2025-08-31
AdvancedCodeGenerationUsingCodeLlama70B.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to deploy the Code Llama 70 B model using the Amazon SageMaker SDK for code generation tasks. It provides examples of generating Python code for various machine learning applications.
| Tags: code generation, SageMaker, Python, machine learning, deep learning, model deployment, hyperparameter tuning | Task Categories: other |
Last modified: 2025-08-31
deepseek-r1-distilled-performance-evaluation-report.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for deploying and evaluating the performance of DeepSeek-R1 distilled models on Amazon SageMaker. It focuses on key performance metrics such as end-to-end latency, throughput, and resource efficiency to ensure optimal deployment in real-world applications.
| Tags: DeepSeek, SageMaker, performance-evaluation, latency, throughput, AI-models, cloud-deployment | Task Categories: evaluation |
Last modified: 2025-08-31
quantize_llms_on_sagemaker.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to perform Post-Training Quantization (PTQ) on large language models using Amazon SageMaker, focusing on compressing model size and improving inference performance without additional fine-tuning.
| Tags: quantization, sagemaker, llama, model-compression, inference-performance, ptq | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
text2sql.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook demonstrates how to build a natural language to SQL application using a generative AI model, specifically Code Llama, deployed on AWS SageMaker. It guides users through querying structured data from a PostgreSQL database using natural language prompts, facilitating easier access to data insights for non-technical users.
| Tags: natural-language-processing, sql-generation, aws-sagemaker, code-generation, data-querying, langchain | Task Categories: rag,other |
Last modified: 2025-08-31
Langchain_text_to_image.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates the process of extracting text from a blog post, summarizing it, and then generating an image based on the summary using Langchain and SageMaker endpoints. It showcases the integration of text processing and image generation in a seamless workflow.
| Tags: text-summarization, image-generation, langchain, sagemaker, data-extraction, multimodal | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
flant5xl_text_summarization_langchain.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a comprehensive guide for deploying large language models for text summarization using AWS SageMaker and the LangChain library. It covers various methods of summarization, including basic prompting and advanced techniques like map-reduce for handling larger documents.
| Tags: text-summarization, AWS SageMaker, LangChain, Flan T5, map-reduce, abstractive summarization, extractive summarization | Task Categories: summarization |
Last modified: 2025-08-31
ai21_text_summarization_langchain.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to implementing text summarization using the AI21 Summary API in conjunction with the LangChain library and AWS SageMaker. It covers various methods for summarizing text, including basic prompting, prompt templates, and advanced techniques like map-reduce for large documents.
| Tags: text-summarization, langchain, sagemaker, AI21, map-reduce, prompting | Task Categories: summarization |
Last modified: 2025-08-31
2_rag_chatbot_flant5.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to build a Retrieval Augmented Generation (RAG) chatbot using the LangChain framework, integrating various components for data retrieval and conversational AI. It covers the installation of necessary libraries, deployment of models on SageMaker, and the construction of a chatbot with memory capabilities.
| Tags: rag, chatbot, langchain, sagemaker, data-retrieval, transformers | Task Categories: rag,agents,other |
Last modified: 2025-08-31
1_deploy-flan-t5-xl.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a step-by-step guide to deploying the FLAN-T5-XL model using Amazon SageMaker. It includes essential setup, configuration, and deployment instructions for creating an inference endpoint.
| Tags: SageMaker, FLAN-T5-XL, deployment, inference, text-generation, AWS, machine-learning | Task Categories: rag |
Last modified: 2025-08-31
1-hello-world-sm-studio-to-agentcore.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for creating and deploying AI agents using Amazon Bedrock AgentCore Runtime and SageMaker. It covers the setup, configuration, and invocation of AI agents powered by SageMaker AI endpoints.
| Tags: AI agents, SageMaker, Bedrock, deployment, cloud computing, boto3, agentcore | Task Categories: agents |
Last modified: 2025-08-31
9-cleanup.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides instructions for cleaning up resources related to AI agents in AWS, specifically focusing on the deletion of gateways and SageMaker endpoints. It utilizes the Boto3 library to interact with AWS services for resource management.
| Tags: AWS, Boto3, cleanup, SageMaker, resource-management, AI agents | Task Categories: agents |
Last modified: 2025-08-31
3-agentcore-runtime.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to hosting Model Context Protocol (MCP) servers on Amazon Bedrock AgentCore Runtime, enabling seamless interaction with Amazon SageMaker AI endpoints for demand forecasting. It covers the implementation of tools, local testing, and deployment processes.
| Tags: MCP, Amazon SageMaker, AgentCore, demand forecasting, Python SDK, AWS, AI tools | Task Categories: agents |
Last modified: 2025-08-31
2-agentcore-gateway.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to creating and managing an Amazon Bedrock AgentCore Gateway, enabling users to transform Smithy APIs into managed MCP servers. It includes steps for setting up the gateway, configuring IAM roles, and integrating with SageMaker endpoints for demand forecasting.
| Tags: agentcore, SageMaker, MCP, AWS, Smithy, API integration, demand forecasting | Task Categories: agents |
Last modified: 2025-08-31
1-demand_forecasting.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to generating synthetic demand forecasting data, training an XGBoost model on Amazon SageMaker, and deploying the model for real-time inference. It covers the entire workflow from data preparation to model deployment.
| Tags: demand forecasting, XGBoost, SageMaker, time series, machine learning, data preparation, model deployment | Task Categories: other |
Last modified: 2025-08-31
strands-agents-sagemaker-as-tool.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to utilize the Strands Agents Python SDK to create an agent that interacts with an Amazon SageMaker AI endpoint for generating predictions. It provides a structured approach to integrating AI models as tools within a Python environment.
| Tags: SageMaker, agents, prediction, AWS, Python, MCP, structured-data | Task Categories: agents |
Last modified: 2025-08-31
demand_forecasting.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to generate synthetic demand forecasting data, train an XGBoost model on Amazon SageMaker, and deploy the model for real-time inference. It covers the entire workflow from data generation to model deployment.
| Tags: demand forecasting, XGBoost, SageMaker, time series, model deployment, feature engineering | Task Categories: other |
Last modified: 2025-08-31
Blog1-CrewAI-DeekSeek.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to build and deploy an intelligent agent system using DeepSeek R1 and CrewAI on Amazon SageMaker, focusing on research and writing tasks. It provides a step-by-step guide for setting up the environment, deploying models, and orchestrating agents to perform complex workflows.
| Tags: deepseek, crewai, sagemaker, intelligent agents, research, writing, llama | Task Categories: agents,rag |
Last modified: 2025-08-31
voyageai-rag-claude3.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook demonstrates how to implement a retrieval-augmented generation (RAG) stack using Voyage AI embedding models within AWS services. It guides users through the process of embedding queries and documents, indexing them in OpenSearch, and utilizing a language model for generating responses based on retrieved context.
| Tags: rag, embedding, OpenSearch, AWS, langchain, document-processing, query-embedding | Task Categories: rag |
Last modified: 2025-08-31
gemma3-4b-it.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook demonstrates how to set up and execute a fine-tuning training job using the ModelTrainer API from the SageMaker SDK. It provides step-by-step instructions for configuring the training environment and integrating with Weights & Biases for tracking metrics.
| Tags: fine-tuning, SageMaker, ModelTrainer, wandb, training, Python, AI | Task Categories: fine-tuning |
Last modified: 2025-08-31
verl-on-sagemaker.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to implementing the veRL algorithm on AWS SageMaker, focusing on building and training models using reinforcement learning techniques. It includes steps for setting up the environment, preprocessing data, and executing training jobs in a cloud-based infrastructure.
| Tags: reinforcement-learning, SageMaker, veRL, model-training, AWS, docker | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
tutorial.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a comprehensive tutorial on using Ray for distributed training and resource management in machine learning applications. It includes examples of creating remote classes, managing GPU resources, and implementing custom dispatch functions for worker groups.
| Tags: distributed training, Ray, GPU management, Megatron, parallel processing, actor model | Task Categories: agents,fine-tuning,other |
Last modified: 2025-08-31
model-trainer-notebook.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for performing reinforcement learning with large language models using Amazon SageMaker and PyTorch. It details the steps for preparing datasets, configuring training parameters, and executing training jobs in a cloud environment.
| Tags: reinforcement learning, SageMaker, PyTorch, fine-tuning, large language models, training | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
launch-training-job.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a guide for launching a training job using Hugging Face’s GRPOTrainer with Accelerate for multi-GPU training on Amazon SageMaker. It includes code for setting up the environment, defining the model trainer, and starting the training job.
| Tags: reinforcement-learning, SageMaker, HuggingFace, multi-GPU, training | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
model-trainer-notebook.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for fine-tuning a language model using Direct Preference Optimization (DPO) on Amazon SageMaker. It includes detailed steps for data preparation, model training, and integration with SageMaker services.
| Tags: fine-tuning, SageMaker, transformers, DPO, model training, data preparation, Python | Task Categories: fine-tuning |
Last modified: 2025-08-31
finetune_gpt_oss_hyperpod_recipes_tj.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning the GPT-OSS models using SageMaker HyperPod recipes and training jobs. It includes code snippets for setting up the environment, preprocessing datasets, and executing training jobs on AWS SageMaker.
| Tags: fine-tuning, GPT-OSS, SageMaker, transformers, AWS, machine learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
finetune_gpt_oss_hyperpod_recipes_eks.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a guide for fine-tuning the GPT-OSS models using SageMaker HyperPod recipes on EKS. It includes code snippets for dataset preparation, model training, and environment setup.
| Tags: fine-tuning, GPT-OSS, SageMaker, HyperPod, EKS, transformers, machine learning | Task Categories: fine-tuning |
Last modified: 2025-08-31
finetune_gpt_oss.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide for fine-tuning and deploying OpenAI’s GPT-OSS models using Amazon SageMaker. It covers the entire workflow from data preparation to model training and deployment.
| Tags: fine-tuning, SageMaker, GPT-OSS, Hugging Face, transformers, model deployment, AI | Task Categories: fine-tuning |
Last modified: 2025-08-31
model-trainer-notebook.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning a large language model (LLM) using PyTorch and Amazon SageMaker. It includes detailed steps for data preparation, model configuration, and training job execution.
| Tags: fine-tuning, SageMaker, PyTorch, transformers, LLM, model-training | Task Categories: fine-tuning |
Last modified: 2025-08-31
distributed training in unified studio.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a comprehensive guide to fine-tuning a large language model (LLM) using Amazon SageMaker with PyTorch and FSDP. It includes steps for data preparation, model configuration, and executing the training job in a distributed environment.
| Tags: fine-tuning, SageMaker, PyTorch, distributed training, LLM | Task Categories: fine-tuning |
Last modified: 2025-08-31
flux-fine-tune-sagemaker.ipynb from amazon-sagemaker-generativeai
Summary: This cookbook provides a guide for fine-tuning a model using the DreamBooth technique with Hugging Face Diffusers on AWS SageMaker. It includes steps for downloading a dataset, configuring the training environment, and executing the training job.
| Tags: fine-tuning, DreamBooth, Hugging Face, SageMaker, image generation, training | Task Categories: fine-tuning |
Last modified: 2025-08-31
smus_pipelines_preprocess_train_evaluate_model.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a comprehensive guide for orchestrating machine learning workflows using Amazon SageMaker Pipelines, focusing on data preprocessing, model training, and evaluation. It demonstrates how to set up a pipeline for a regression task using the Abalone dataset, including steps for data handling and model management.
| Tags: SageMaker, pipelines, machine learning, data preprocessing, model training, evaluation, AWS | Task Categories: other |
Last modified: 2025-08-31
smus_pipelines_preprocess_train_evaluate_batch_transform.ipynb from amazon-sagemaker-generativeai
Summary: This AI cookbook provides a comprehensive guide for orchestrating machine learning workflows using Amazon SageMaker Pipelines, focusing on data preprocessing, model training, and evaluation. It demonstrates how to set up a pipeline for a regression task using the Abalone dataset, including steps for data handling and model management.
| Tags: SageMaker, pipelines, machine learning, data preprocessing, model training, evaluation, Abalone dataset | Task Categories: other |
Last modified: 2025-08-31
fiddler-model-monitoring.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for implementing model monitoring and optimization for a travel agency’s search ranking model using Fiddler and SageMaker. It includes steps for authentication, project creation, model specification, and data publishing.
| Tags: model monitoring, SageMaker, Fiddler, ranking model, data publishing, travel agency, user experience | Task Categories: other |
Last modified: 2025-09-02
comet-intro.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a comprehensive guide for setting up and training a convolutional neural network using TensorFlow and Keras on the CIFAR-10 dataset. It integrates with Comet for experiment tracking and logging, showcasing how to manage model training and evaluation effectively.
| Tags: tensorflow, keras, image-classification, comet-ml, cifar-10, neural-networks, experiment-tracking | Task Categories: classification |
Last modified: 2025-09-02
fraud-detection-comet-sagemaker.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for building, tracking, and evaluating machine learning models for credit card fraud detection using Comet ML and Amazon SageMaker. It covers environment setup, dataset tracking, and model training and evaluation processes.
| Tags: fraud detection, Comet ML, SageMaker, machine learning, dataset tracking, model evaluation | Task Categories: classification |
Last modified: 2025-09-02
evaluating-agents-opik-sagemaker.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide on building, tracking, and evaluating AI agents using SageMaker AI endpoints and the CrewAI framework, integrated with Comet Opik for performance tracking. It includes practical examples and code snippets for deploying models and creating agents for recipe suggestion and research.
| Tags: SageMaker, AI agents, evaluation, recipe generation, Comet Opik, Python | Task Categories: agents,evaluation |
Last modified: 2025-09-02
strands-agents.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for building AI agents using the Strands Agents SDK, focusing on integrating various models and tools to automate tasks effectively. It includes examples of financial analysis, data extraction, and budget optimization through specialized agents.
| Tags: AI agents, automation, financial analysis, data extraction, budget optimization, Strands SDK, Python | Task Categories: agents |
Last modified: 2025-09-02
1-optional-Strands-lab-only-dependencies.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides instructions for setting up and configuring Strands agents using Amazon SageMaker, including dependency installation and knowledge base creation. It is designed for users participating in a specific workshop focused on generative AI applications.
| Tags: SageMaker, Strands, agents, knowledge-base, dependency-installation, generative-ai | Task Categories: agents |
Last modified: 2025-09-02
lakera.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a hands-on guide to implementing runtime security for a Generative AI chat agent using Lakera Guard, focusing on detecting and defending against prompt injections and ensuring content safety.
| Tags: AI security, prompt injection, Generative AI, Lakera Guard, SageMaker, chat agent, runtime security | Task Categories: agents,other |
Last modified: 2025-08-31
deepchecks.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a step-by-step guide to implementing a Q&A application using the Deepchecks platform, focusing on version comparison and evaluation of a RAG-based bot for medical inquiries. It includes code snippets for setting up the environment, logging interactions, and updating configurations.
| Tags: Q&A, Deepchecks, SageMaker, RAG, evaluation, version-comparison, medical | Task Categories: rag,evaluation |
Last modified: 2025-08-31
comet-opik.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a step-by-step guide to building a geography chatbot using the Llama model hosted on SageMaker, along with methods for evaluating the chatbot’s performance using Opik metrics. It covers setting up the environment, creating datasets, and automating evaluations.
| Tags: rag, chatbot, evaluation, sagemaker, opik, llama, geography | Task Categories: rag,evaluation |
Last modified: 2025-08-31
05.01_fine-tuning-pipeline.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for fine-tuning and evaluating large language models (LLMs) using Amazon SageMaker Pipelines and MLflow. It streamlines the ML lifecycle by integrating experiment tracking, model versioning, and deployment processes.
| Tags: fine-tuning, MLflow, SageMaker, LLM, experiment tracking, model deployment | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
04.01_bedrock_guardrails_apply_guardrail_api.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to implement Bedrock Guardrails for a fine-tuned model to ensure compliance with medical content policies and filter harmful information. It provides code examples for creating and applying guardrails to validate inputs and outputs in generative AI applications.
| Tags: guardrails, content-filtering, medical-compliance, sagemaker, AI-safety, fine-tuning | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
03.01_foundation_model_evaluation_lighteval.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for evaluating fine-tuned models using SageMaker and LightEval metrics on the medical-o1-reasoning dataset. It demonstrates how to generate summaries and assess model performance through automated metrics.
| Tags: fine-tuning, evaluation, summarization, SageMaker, LightEval, medical dataset, AI models | Task Categories: fine-tuning,evaluation,summarization |
Last modified: 2025-08-31
02.01_finetune_deepseekr1.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning a large language model (LLM) using Amazon SageMaker, focusing on the integration of various libraries and tools for efficient model training. It includes steps for data preparation, model configuration, and deployment, making it suitable for practitioners looking to enhance LLM capabilities.
| Tags: fine-tuning, SageMaker, LLM, transformers, data-preparation, model-training | Task Categories: fine-tuning |
Last modified: 2025-08-31
01.01_search_and_deploy_huggingface_llm.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide for deploying the DeepSeek-R1-Distill-Llama-8B model on Amazon SageMaker, including setup, model downloading, and inference configuration.
| Tags: sagemaker, llama, model-deployment, inference, AWS, deep-learning | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
lakera.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a hands-on guide to implementing runtime security for a Generative AI chat agent using Lakera Guard, focusing on detecting and defending against prompt injections and ensuring content safety.
| Tags: runtime security, prompt injection, generative AI, Lakera Guard, chat agents, AWS SageMaker | Task Categories: agents,other |
Last modified: 2025-08-31
fiddler.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for optimizing user search experiences in an online travel agency using Fiddler and SageMaker. It includes steps for model creation, data publishing, and integration of a chatbot assistant to enhance user interactions.
| Tags: Fiddler, SageMaker, model-monitoring, search-ranking, chatbot, data-publishing | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
deepchecks.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a tutorial for implementing a Q&A application using the Deepchecks platform, focusing on version comparison and interaction logging for a medical condition dataset. It guides users through setting up the environment, logging interactions, and improving model performance based on evaluation results.
| Tags: Q&A, GVHD, Deepchecks, evaluation, interaction logging, RAG, SageMaker | Task Categories: rag,evaluation |
Last modified: 2025-08-31
comet-opik.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to building and evaluating a geography chatbot using the Llama model hosted on SageMaker, integrating with Opik for performance metrics. It covers the setup, dataset creation, and automated evaluation processes.
| Tags: rag, chatbot, evaluation, sagemaker, opik, llama, geography | Task Categories: rag,evaluation |
Last modified: 2025-08-31
comet-intro.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for integrating Comet with SageMaker to build and fine-tune a convolutional neural network for image classification using the CIFAR-10 dataset. It includes steps for data preprocessing, model building, training, and logging experiment metrics.
| Tags: image-classification, comet, sagemaker, tensorflow, neural-networks, cifar-10 | Task Categories: fine-tuning,classification |
Last modified: 2025-08-31
delete-sagemaker-endpoint.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides instructions for deleting a SageMaker AI endpoint to avoid incurring unwanted charges. It includes code snippets for using the Boto3 library to manage AWS resources effectively.
| Tags: SageMaker, AWS, boto3, cleanup, AI endpoints, cost management | Task Categories: agents |
Last modified: 2025-08-31
2-text2sql-langchain.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to create a natural language interface for querying an Amazon Athena database using LangChain and AWS Bedrock. It allows users to convert plain English questions into SQL queries and retrieve results in an understandable format.
| Tags: text-to-SQL, natural-language-processing, AWS, LangChain, Athena, data-query | Task Categories: agents |
Last modified: 2025-08-31
1-create-db-tables.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a step-by-step guide to creating a Glue database and loading data from Excel files into S3, followed by creating external tables in Amazon Athena. It demonstrates the integration of AWS services for data processing and querying.
| Tags: AWS, Glue, Athena, data-processing, S3, Excel | Task Categories: agents,other |
Last modified: 2025-08-31
text2dsl-mcp.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to leverage Large Language Models (LLMs) to convert natural language queries into OpenSearch DSL queries for retrieving security findings from Amazon GuardDuty logs.
| Tags: OpenSearch, GuardDuty, natural-language-processing, DSL, AWS, LLM, data-retrieval | Task Categories: agents,rag |
Last modified: 2025-08-31
support-system.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates the creation of a multi-agent system for triaging and resolving support tickets using LangGraph and AWS Bedrock. It includes various agents designed to classify issues, manage accounts, provide documentation, and handle technical problems.
| Tags: support tickets, multi-agent system, AWS Bedrock, LangGraph, classification, automation | Task Categories: agents,classification |
Last modified: 2025-08-31
strands-agents-sagemaker-as-tool-forged-image-detection.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide for detecting tampered images using a computer vision model deployed on AWS. It includes steps for training a Convolutional Neural Network (CNN) and creating an agent to automate the detection process.
| Tags: image-detection, fraud-detection, computer-vision, AWS, CNN, agents | Task Categories: agents,classification |
Last modified: 2025-08-31
mcp-exploration.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a practical guide for implementing the Model Context Protocol (MCP) to create AI agents that can interact with various tools and data sources. It demonstrates how to set up a client-server architecture using MCP for enhanced context-aware AI applications.
| Tags: MCP, AI agents, client-server, context-aware, Python, langchain, tool integration | Task Categories: agents |
Last modified: 2025-08-31
strands_agent_evaluation.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a comprehensive guide for building and evaluating agents using the strands and flotorch-eval packages, focusing on key metrics for assessing agent performance. It includes installation instructions, code examples, and evaluation methodologies to ensure effective agent functionality.
| Tags: agent-evaluation, flotorch-eval, strands, python, metrics, asyncio | Task Categories: agents,evaluation |
Last modified: 2025-08-31
crewai_agent_evaluation.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to building and evaluating AI agents using the CrewAI and Flotorch-Eval frameworks, focusing on metrics that assess agent performance and system efficiency. It includes code examples for setting up tracing, defining evaluation metrics, and executing agent tasks.
| Tags: AI agents, evaluation, flotorch-eval, crewai, AWS Bedrock, OpenTelemetry | Task Categories: agents,evaluation |
Last modified: 2025-08-31
mlflow-langgraph-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to create a multi-agent travel assistant using LangGraph and Sagemaker MLFlow, focusing on researching, writing, and editing travel content.
| Tags: travel-assistant, multi-agent, langchain, sagemaker, mlflow, content-creation, automation | Task Categories: agents |
Last modified: 2025-08-31
mlflow-crewAI-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to integrate MLflow with Amazon SageMaker to monitor and trace workflows of multi-agent AI systems using CrewAI. It provides insights into agent executions, tool usage, and LLM calls for improved observability and debugging.
| Tags: MLflow, SageMaker, CrewAI, observability, multi-agent, AI systems, monitoring | Task Categories: agents |
Last modified: 2025-08-31
strands-langfuse-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide for integrating Langfuse with Strands Agents SDK to enhance observability in AI applications. It demonstrates how to set up tracing and utilize various tools for generating insights from AWS documentation.
| Tags: observability, AI agents, Langfuse, Strands, AWS integration, OpenTelemetry | Task Categories: agents,rag |
Last modified: 2025-08-31
litellm-langfuse-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to integrate Langfuse with LiteLLM for observability and analytics in LLM applications, focusing on creating an autonomous agent that can interact with users and utilize external tools for tasks like weather retrieval and translation.
| Tags: observability, langfuse, autonomous agents, weather retrieval, translation, LLM integration, analytics | Task Categories: agents |
Last modified: 2025-08-31
litellm-langfuse-observability-enhanced.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to integrate LiteLLM with Langfuse for observability in LLM applications, focusing on building an autonomous agent that can interact with users and external tools. It provides code examples for setting up API keys, invoking LLMs, and implementing tool functions for tasks like weather retrieval and text translation.
| Tags: observability, autonomous agents, weather API, text translation, Langfuse, LiteLLM, AWS | Task Categories: agents |
Last modified: 2025-08-31
crewAI-langfuse-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to integrate Langfuse observability into LLM applications using CrewAI, enabling tracking and analysis of model performance and interactions. It provides a step-by-step guide for setting up the environment and creating agents that can perform tasks like generating poetry based on user queries.
| Tags: observability, LLM, CrewAI, Langfuse, agents, poetry-generation, SaaS | Task Categories: agents |
Last modified: 2025-08-31
strands-agents_memory.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a framework for creating personalized agents that remember user preferences and conduct web searches based on those preferences. It emphasizes ethical guidelines and constraints to ensure user privacy.
| Tags: personalized agents, memory, web search, user preferences, ethical AI | Task Categories: agents |
Last modified: 2025-08-31
strands-agents-agentcore-runtime.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for deploying AI agents using Amazon Bedrock AgentCore, focusing on the operational aspects of managing AI agents in production environments. It outlines the necessary steps to prepare, configure, and deploy agents while ensuring scalability and security.
| Tags: AI agents, Amazon Bedrock, deployment, serverless, scalability, cloud computing, AWS | Task Categories: agents |
Last modified: 2025-08-31
smolagents-example.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to build and utilize autonomous agents using the smolagents library, which integrates with various LLMs like Amazon Bedrock and SageMaker. It provides examples of creating agents that can perform tasks such as web searches and model retrieval from the Hugging Face Hub.
| Tags: autonomous agents, smolagents, LLM integration, Hugging Face, tool calling, Python | Task Categories: agents |
Last modified: 2025-08-31
openai_agents_sdk_tutorial.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide for using the OpenAI Agents SDK with Amazon Bedrock, including setting up the environment, creating agents, and running examples. It demonstrates how to convert OpenAI tools for use with Bedrock and includes practical code snippets.
| Tags: openai, agents, amazon bedrock, python, weather tool, sdk | Task Categories: agents |
Last modified: 2025-08-31
langgraph-sequential-agent-teams.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to build a sequential multi-agent travel assistant using LangGraph, enabling the generation of articles on attractions and activities in various locations.
| Tags: travel-assistant, multi-agent, content-generation, langchain, AWS, SageMaker, LangGraph | Task Categories: agents |
Last modified: 2025-08-31
langgraph-hierarchical-agent-teams.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a framework for building hierarchical agent teams that can perform web research and document writing tasks. It utilizes various tools and utilities to facilitate the interaction between agents and enhance their performance in complex tasks.
| Tags: hierarchical agents, web scraping, document writing, langchain, multi-agent systems, AI tools | Task Categories: agents,rag |
Last modified: 2025-08-31
crewai-travel-flows.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook demonstrates how to create and manage AI workflows using CrewAI, focusing on travel research and content generation. It showcases the integration of various tools and agents to streamline the process of gathering information and producing engaging travel content.
| Tags: AI workflows, travel research, content generation, agents, DuckDuckGo API, Amazon Bedrock, Crews | Task Categories: agents,rag |
Last modified: 2025-08-31
crewai-travel-agent-sequential.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to build a multi-agent travel assistant using the CrewAI framework, focusing on generating articles about attractions and activities in specific locations.
| Tags: multi-agent, travel-assistant, content-generation, LLM, CrewAI, article-writing, research | Task Categories: agents |
Last modified: 2025-08-31
crewAI-travel-agent-hierarchical.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to create a multi-agent travel assistant using the CrewAI framework, focusing on generating articles about attractions and activities in specific locations.
| Tags: travel-assistant, multi-agent, content-generation, crewAI, article-writing, research | Task Categories: agents |
Last modified: 2025-08-31
crewAI-langfuse-observability.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide for integrating Langfuse observability into LLM applications using CrewAI, enabling tracking, monitoring, and analysis of model performance and interactions. It includes setup instructions, API key configuration, and example code for creating agents that utilize LLMs for specific tasks.
| Tags: observability, LLM, Langfuse, CrewAI, API integration, agent-based, monitoring | Task Categories: agents |
Last modified: 2025-08-31
agno-ai-logistics.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a guide for creating a logistics assistant agent using the Agno library, focusing on shipment tracking and route optimization. It includes sample code for implementing tools that handle specific logistics queries.
| Tags: logistics, agent-building, route-optimization, shipment-tracking, agno | Task Categories: agents |
Last modified: 2025-08-31
orchestrator_workers.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates an orchestrator-workers workflow for dynamically breaking down complex tasks and delegating them to worker LLMs, allowing for flexible and efficient content generation and analysis.
| Tags: orchestrator, task-parallelization, content-generation, data-analysis, document-processing, LLM-integration | Task Categories: agents,other |
Last modified: 2025-08-31
evaluator_optimizer.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates an evaluator-optimizer workflow using LLMs to iteratively generate and evaluate code and content, enhancing the quality of outputs through feedback loops.
| Tags: evaluator-optimizer, LLM, feedback-loop, code-generation, content-writing, iterative-refinement | Task Categories: agents,evaluation |
Last modified: 2025-08-31
basic_workflows.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides workflows for leveraging language models to perform tasks such as data extraction, impact analysis, and customer support routing through prompt chaining, parallelization, and routing techniques.
| Tags: prompt-chaining, parallelization, routing, data-extraction, customer-support | Task Categories: agents,other |
Last modified: 2025-08-31
autonomous_agent.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a framework for creating autonomous agents that can perform tasks such as fetching weather information and translating text using defined tools. It illustrates how to implement a loop for continuous interaction and tool utilization in a conversational context.
| Tags: autonomous agents, weather API, text translation, SageMaker, LLM integration, tool utilization | Task Categories: agents |
Last modified: 2025-08-31
2-tool-calling-sagemaker.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide on how to implement tool calling with Amazon SageMaker AI, specifically focusing on creating a function to retrieve the most popular song for a given radio station. It includes setup instructions and code examples for integrating the function with a SageMaker endpoint.
| Tags: sagemaker, tool-calling, AI-assistant, function-integration, music-recommendation | Task Categories: agents |
Last modified: 2025-08-31
1-tool-calling-bedrock.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a guide on how to implement tool-assisted interactions with AI models using AWS Bedrock, allowing for dynamic querying and function calling based on user input.
| Tags: tool-calling, AWS Bedrock, function calling, AI agents, Python | Task Categories: agents |
Last modified: 2025-08-31
2-inference-sagemaker.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides instructions for performing inference using Amazon SageMaker with a deployed model endpoint. It includes examples of synchronous and asynchronous predictions using various payload configurations.
| Tags: sagemaker, inference, AI, predictor, json | Task Categories: agents |
Last modified: 2025-08-31
1-inference-bedrock.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides guidance on invoking various AI models from Amazon Bedrock, demonstrating how to interact with these models using Python code. It includes examples of using different prompts and configurations to obtain responses from the models.
| Tags: amazon-bedrock, ai-integration, python, model-invocation, generative-ai | Task Categories: agents |
Last modified: 2025-08-31
2-setup-sagemaker-endpoint.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a step-by-step guide to deploying a large language model (LLM) to Amazon SageMaker as a real-time endpoint. It includes necessary prerequisites, dependencies, and deployment instructions for machine learning practitioners.
| Tags: SageMaker, LLM, deployment, real-time, AI, boto3, model-serving | Task Categories: agents |
Last modified: 2025-08-31
1-required-dependencies.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides instructions for setting up the necessary dependencies to build DIY agents using Amazon SageMaker and Bedrock. It includes steps for uninstalling existing packages and installing required libraries to facilitate the workshop.
| Tags: dependencies, SageMaker, Bedrock, AI agents, workshop | Task Categories: agents |
Last modified: 2025-08-31
model-trainer-notebook.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning a language model using Direct Preference Optimization (DPO) on Amazon SageMaker. It includes code for data preparation, model training, and integration with SageMaker services.
| Tags: fine-tuning, SageMaker, transformers, DPO, model-training, data-preparation, Python | Task Categories: fine-tuning |
Last modified: 2025-08-31
model-trainer-fsdp-qlora.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning a large language model (LLM) using PyTorch and Amazon SageMaker’s ModelTrainer. It includes steps for data preparation, model configuration, and training job execution.
| Tags: fine-tuning, SageMaker, PyTorch, LLM, model training, FSDP, QLora | Task Categories: fine-tuning |
Last modified: 2025-08-31
model-trainer-fsdp-qlora.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning a large language model (LLM) using PyTorch and Amazon SageMaker. It includes detailed steps for data preparation, model training, and configuration management, leveraging SageMaker’s capabilities for distributed training.
| Tags: fine-tuning, SageMaker, PyTorch, transformers, LLM, distributed-training | Task Categories: fine-tuning |
Last modified: 2025-08-31
jumpstart-llama3.1-8b-instruct-ft.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning the Meta Llama 3.1 - 8B Instruct model using Amazon SageMaker Jumpstart, focusing on preparing datasets, training, and deploying the model for generating personalized marketing messages.
| Tags: fine-tuning, SageMaker, Llama, model deployment, personalized marketing, data preparation, AI cookbook | Task Categories: fine-tuning |
Last modified: 2025-08-31
sagemaker-inference-bedrock-guardrails-medical-theme.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to build a secure and compliant Retrieval-Augmented Generation (RAG) pipeline using Amazon SageMaker for inference, OpenSearch for vector-based retrieval, and Amazon Bedrock Guardrails for response filtering. It guides users through configuring AWS environments, applying guardrails, and ensuring compliance in medical contexts.
| Tags: rag, sagemaker, bedrock, opensearch, medical-compliance, guardrails, aws | Task Categories: rag |
Last modified: 2025-08-31
05-deploy-to-BR.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for importing and hosting fine-tuned AI models from Amazon SageMaker to Amazon Bedrock using the Bedrock Custom Model Import feature. It includes code snippets for setting up the environment, creating model import jobs, and sending prompts to the hosted models.
| Tags: SageMaker, Bedrock, model-import, fine-tuning, AI-deployment, transformers | Task Categories: fine-tuning,rag |
Last modified: 2025-08-31
04-evaluate.ipynb from generative-ai-on-amazon-sagemaker
Summary: This AI cookbook provides a comprehensive guide for deploying and evaluating language models using Amazon SageMaker and Bedrock. It includes code for setting up metrics to assess model performance and demonstrates the integration of various libraries for enhanced evaluation capabilities.
| Tags: evaluation, rag, sagemaker, langchain, metrics | Task Categories: evaluation,rag |
Last modified: 2025-08-31
03-deploy_and_evaluate_models.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to deploying and evaluating fine-tuned models using Amazon SageMaker, specifically focusing on the Llama model architecture. It includes code snippets for model deployment, message formatting, and performance evaluation.
| Tags: sagemaker, llama, fine-tuning, model-evaluation, deployment, AI | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
02-raft_finetune.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to fine-tuning the Llama 3.1 model using PyTorch FSDP and Q-Lora on Amazon SageMaker, leveraging Hugging Face libraries for efficient model training. It includes detailed instructions for setting up the environment, preparing datasets, and executing training jobs.
| Tags: fine-tuning, Llama, SageMaker, Q-Lora, FSDP, transformers, datasets | Task Categories: fine-tuning,rag |
Last modified: 2025-08-31
01-build_raft_dataset.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to building a Retrieval Augmented Fine-Tuning (RAFT) dataset using the PubMedQA dataset, aimed at enhancing question-answering tasks with domain-specific language models. It includes steps for data processing, model training, and evaluation using Amazon SageMaker.
| Tags: raft, question-answering, sagemaker, fine-tuning, data-processing | Task Categories: rag,fine-tuning,evaluation |
Last modified: 2025-08-31
02-embeddings-eval.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for fine-tuning embedding models using LangChain and evaluating their performance with similarity searches. It demonstrates the installation of necessary libraries, data loading, and the creation of vector databases for efficient querying.
| Tags: fine-tuning, embedding, evaluation, similarity-search, langchain, faiss | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
01-ft_embedding_with_sagemaker_eval.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates how to fine-tune a Sentence Transformer model using Amazon SageMaker with a focus on medical data from the PubMedQA dataset. It includes steps for data processing, model training, and preliminary evaluation.
| Tags: fine-tuning, sentence-transformers, SageMaker, PubMedQA, evaluation, machine-learning | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
SageMak-Embedding-Model-OpenSearch.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook demonstrates the implementation of a Retrieval Augmented Generation (RAG) solution using Amazon SageMaker and OpenSearch, focusing on the orchestration of the RAG pipeline and evaluation of its quality. It provides a comprehensive guide for building a conversational search application that leverages large language models to enhance information retrieval from enterprise knowledge bases.
| Tags: rag, sagemaker, opensearch, langchain, evaluation, generative-ai | Task Categories: rag,evaluation |
Last modified: 2025-08-31
building-an-experimental-rag-app.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide for implementing Retrieval-Augmented Generation (RAG) workflows using AWS services and LangChain. It includes code snippets for setting up dependencies, loading documents, and performing similarity searches with embeddings.
| Tags: rag, aws, langchain, embeddings, similarity-search | Task Categories: rag |
Last modified: 2025-08-31
prerequisites.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a comprehensive guide to setting up prerequisite components for deploying generative AI models using Amazon SageMaker and OpenSearch. It includes instructions for creating hosting endpoints for embedding and generation models, as well as configuring an OpenSearch domain.
| Tags: SageMaker, OpenSearch, embedding, generation, AWS, RAG | Task Categories: rag,other |
Last modified: 2025-08-31
br-custom-model-import-example.ipynb from generative-ai-on-amazon-sagemaker
Summary: This cookbook provides a step-by-step guide for importing a fine-tuned AI model from Amazon SageMaker to Amazon Bedrock using the Bedrock Custom Model Import feature. It includes code snippets for setting up the environment, managing model artifacts, and invoking the model for inference.
| Tags: sagemaker, bedrock, model-import, fine-tuning, AI, transformers | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
RLHF_locally.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides a training pipeline to fine-tune a generative model for creating IMDb reviews with positive sentiment using Reinforcement Learning from Human Feedback (RLHF). It includes configuration settings, model training, and evaluation processes. The implementation leverages popular libraries such as PyTorch and Transformers.
| Tags: RLHF, fine-tuning, transformers, text-generation, PyTorch | Task Categories: fine-tuning |
Last modified: 2025-08-31
09-api_gateway_managed_endpoint.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides examples for managing Amazon SageMaker endpoints using an API Gateway and Lambda authorizer, demonstrating how to interact with these services programmatically. It includes code snippets for setting up requests and utilizing a language model for various tasks.
| Tags: SageMaker, API Gateway, Lambda, langchain, endpoint management, Python, automation | Task Categories: agents,other |
Last modified: 2025-08-31
03-rag_langchain_jumpstart-apigateway.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) for question answering using custom datasets with the LangChain library and AWS SageMaker. It provides a template for building applications that leverage document embeddings and generative models to answer user queries based on specific information.
| Tags: rag, question-answering, langchain, sagemaker, embeddings, generative-ai | Task Categories: rag |
Last modified: 2025-08-31
02-langchain-basic-apigateway.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides a comprehensive guide to using LangChain with various AI models, particularly focusing on text embeddings and conversational agents. It includes code snippets for setting up models, processing text, and generating responses using AWS services.
| Tags: langchain, text-embedding, AWS, conversational AI, semantic similarity, API integration | Task Categories: rag,agents,other |
Last modified: 2025-08-31
01-rag_langchain_jumpstart.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to implement Retrieval-Augmented Generation (RAG) using the LangChain library to answer questions based on a custom dataset. It utilizes various language models and SageMaker endpoints to generate responses and manage embeddings.
| Tags: rag, question-answering, langchain, sagemaker, embeddings, text-generation | Task Categories: rag,other |
Last modified: 2025-08-31
00-langchain-basic.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This AI cookbook provides a comprehensive guide to using LangChain with AWS SageMaker for various natural language processing tasks, including text embedding and conversation handling. It demonstrates how to set up and utilize different models and embeddings for semantic similarity and conversational AI applications.
| Tags: langchain, sagemaker, text-embedding, conversation, semantic-similarity, AI-cookbook, NLP | Task Categories: rag,agents,other |
Last modified: 2025-08-31
huggingface-nlp-course-aws-optimized.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: Classification failed.
| Tags: | Task Categories: other |
Last modified: 2025-08-31
02-question_answering_langchain_jumpstart.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to use retrieval-augmented generation (RAG) techniques with various language models to answer questions based on a custom dataset. It provides a template for building question-answering applications using document embeddings and retrieval methods.
| Tags: rag, question-answering, langchain, sagemaker, text-generation, embeddings | Task Categories: rag,other |
Last modified: 2025-08-31
01-question_answering_jumpstart_ai21-apigateway.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to implement a retrieval-augmented generation (RAG) approach for question answering using Amazon SageMaker and various language models. It provides a template for deploying models and utilizing document embeddings to enhance response accuracy.
| Tags: rag, question-answering, sagemaker, document-embeddings, ai21 | Task Categories: rag |
Last modified: 2025-08-31
01-question_answerIng_jumpstart_knn.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to implement a Retrieval-Augmented Generation (RAG) approach for question answering using Amazon SageMaker and various large language models. It provides a template for deploying models and generating responses based on a custom dataset of documents.
| Tags: rag, question-answering, sagemaker, text-generation, embedding | Task Categories: rag |
Last modified: 2025-08-31
01-question_answerIng_jumpstart_knn-apigateway.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to implement a Retrieval-Augmented Generation (RAG) approach for question answering using a custom dataset in Amazon SageMaker. It utilizes large language models like Flan T5 XXL and BloomZ 7B1 to generate responses based on document embeddings.
| Tags: rag, question-answering, sagemaker, flan-t5, bloomz, embedding | Task Categories: rag |
Last modified: 2025-08-31
make-prediction.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to use AWS SageMaker to predict sentiment from text using a pre-trained model. It includes code for invoking the model endpoint and processing the predictions on a dataset.
| Tags: sentiment-analysis, AWS, SageMaker, boto3, text-prediction, data-processing | Task Categories: classification |
Last modified: 2025-08-31
explore-data.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides a step-by-step guide for downloading and processing financial sentiment data using Python and SageMaker. It includes code for data extraction, exploration, and basic sentiment analysis.
| Tags: financial-sentiment, data-exploration, sagemaker, pandas, csv-processing | Task Categories: classification |
Last modified: 2025-08-31
long-form-summarization.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to use AWS SageMaker and Cohere’s model for long-form text summarization and question generation. It provides a step-by-step guide to deploying a model, processing text, and generating summaries and QA pairs.
| Tags: long-form summarization, text processing, question generation, AWS SageMaker, Cohere | Task Categories: summarization |
Last modified: 2025-08-31
01-in-context-learning.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This AI cookbook provides a comprehensive guide for deploying a Cohere language model using AWS SageMaker, focusing on in-context learning for natural language understanding tasks. It includes code snippets for model deployment, text generation, and various prompt-based tasks.
| Tags: Cohere, SageMaker, NLP, text-generation, model-deployment, in-context-learning | Task Categories: classification,other |
Last modified: 2025-08-31
01-in-context-learning.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This AI cookbook demonstrates how to deploy a Hugging Face model using Amazon SageMaker for in-context learning and conversational AI tasks. It includes code for setting up the model, deploying it, and making inference requests to generate responses based on user queries.
| Tags: sagemaker, FLAN-T5, inference, conversational AI, deployment, Hugging Face | Task Categories: agents,summarization |
Last modified: 2025-08-31
00-prompt-enigeering-flan-t5-xxl.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This AI cookbook provides a comprehensive guide to deploying and utilizing the FLAN-T5 XXL FP16 model on AWS SageMaker, focusing on prompt engineering for various text generation tasks. It includes practical examples for querying the model with different prompts and configurations.
| Tags: text-generation, AWS, SageMaker, FLAN-T5, prompt-engineering, AI-cookbook, model-deployment | Task Categories: other |
Last modified: 2025-08-31
00-prompt-enigeering-flan-t5-xxl-apigateway.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This AI cookbook provides examples of prompt engineering for text generation using a foundation model, showcasing various tasks such as question answering, sentiment analysis, and translation. It demonstrates how to interact with a model endpoint using JSON payloads and logging responses.
| Tags: prompt-engineering, text-generation, API-integration, sentiment-analysis, question-answering, translation | Task Categories: other |
Last modified: 2025-08-31
02-img-downloader.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides a method for downloading images from the web to be used for fine-tuning Stable Diffusion models. It utilizes the Bing Image Downloader library to fetch images based on a specified query.
| Tags: image-download, stable-diffusion, fine-tuning, bing-image-downloader, data-collection | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
02-finetune.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to fine-tune a Stable Diffusion model using limited cat images and deploy it for image generation tasks. It provides a step-by-step guide on setting up the training environment, configuring hyperparameters, and deploying the model for inference.
| Tags: fine-tuning, image-generation, stable-diffusion, sagemaker, deep-learning, multimodal | Task Categories: fine-tuning,multimodal |
Last modified: 2025-08-31
01-txt2img-gen.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook demonstrates how to use AWS SageMaker to deploy a Stable Diffusion model for generating images from text prompts. It provides step-by-step instructions for setting up the environment, deploying the model, and invoking the endpoint to generate images.
| Tags: image-generation, stable-diffusion, sagemaker, text-to-image, aws | Task Categories: multimodal |
Last modified: 2025-08-31
00-txt2img-jumpstart.ipynb from sagemaker-jumpstart-generative-ai-examples
Summary: This cookbook provides a guide to deploying and using the Stable Diffusion model for text-to-image generation using Amazon SageMaker. It includes code examples for invoking the model endpoint and processing the generated images.
| Tags: Stable Diffusion, image generation, SageMaker, deep learning, AWS, multimodal, generative AI | Task Categories: multimodal |
Last modified: 2025-08-31
AIStudioHubAndProject.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide for creating and managing AI resources in Azure, including hubs, projects, AI services, and connections. It outlines the necessary steps to set up and deploy AI models and services effectively within the Azure ecosystem.
| Tags: Azure, AI Services, resource creation, machine learning, deployment, Cognitive Services, AI Search | Task Categories: other |
Last modified: 2025-08-31
tracing-with-llamaindex-advance-query-selector.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to utilize the Llama-Index framework with Azure AI models for advanced query processing in a Retrieval-Augmented Generation (RAG) application. It covers the integration of various AI models and tracing capabilities to enhance query handling and summarization tasks.
| Tags: rag, azure-ai, llama-index, query-processing, summarization, tracing, model-integration | Task Categories: rag,summarization |
Last modified: 2025-08-31
getting-started-with-llama-index.ipynb from azure-ai-samples
Summary: This cookbook provides a guide on how to use the Llama-Index library with models deployed from the Azure AI model catalog. It covers prerequisites, installation of dependencies, and examples of using Azure AI models for various tasks.
| Tags: azure-ai, llama-index, model-inference, embedding, python, tutorial, api | Task Categories: other |
Last modified: 2025-08-31
tracing-with-langchain.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to use the langchain-azure-ai package for tracing AI projects in Azure AI Foundry. It provides a step-by-step guide on setting up the environment, creating prompts, and integrating Azure AI models for generating and verifying poetry.
| Tags: Azure AI, LangChain, tracing, model inference, poetry generation, environment setup | Task Categories: other |
Last modified: 2025-08-31
getting-started-with-langchain-embeddings.ipynb from azure-ai-samples
Summary: This cookbook provides a tutorial on using the langchain-azure-ai package to implement embeddings with Azure AI Foundry. It guides users through the setup and execution of similarity searches using vector stores and documents.
| Tags: langchain, azure-ai, embeddings, similarity-search, vector-stores, tutorial | Task Categories: rag |
Last modified: 2025-08-31
getting-started-with-langchain-chat-models.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide to using the langchain-azure-ai package for building chat models with Azure AI Foundry. It includes examples of model invocation, prompt templates, and logging configurations.
| Tags: langchain, Azure AI, chat models, prompt engineering, logging, model invocation | Task Categories: agents,evaluation |
Last modified: 2025-08-31
inference-finetuned model-token reduction.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to perform inference using a fine-tuned model with function calling for token reduction scenarios. It provides practical examples of how to interact with the Azure OpenAI API to retrieve stock prices based on user queries.
| Tags: fine-tuning, function-calling, Azure OpenAI, token-reduction, stock-prices | Task Categories: fine-tuning |
Last modified: 2025-08-31
inference-finetuned model-hallucination.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to perform inference with a fine-tuned model using function calling, specifically addressing scenarios involving token reduction and hallucination. It provides practical code examples for interacting with the Azure OpenAI service to retrieve stock prices based on user queries.
| Tags: fine-tuning, function-calling, Azure OpenAI, stock-prices, token-reduction | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
finetuning-function calling-e2e application.ipynb from azure-ai-samples
Summary: This AI cookbook demonstrates how to implement function calling with Azure OpenAI to fetch stock prices using the yfinance library. It provides a structured approach to integrate external API calls into a conversational AI application.
| Tags: function-calling, API-integration, stock-prices, Azure-OpenAI, yfinance, json-processing, fine-tuning | Task Categories: fine-tuning,agents |
Last modified: 2025-08-31
fine-tuning-with-function-calling.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide for fine-tuning and deploying the gpt-35-turbo-0613 model using Azure OpenAI with function calling capabilities. It includes code snippets for preparing datasets, monitoring training jobs, and deploying the fine-tuned model.
| Tags: fine-tuning, Azure OpenAI, gpt-35-turbo, function calling, model deployment, training datasets | Task Categories: fine-tuning |
Last modified: 2025-08-31
evaluate_with_various_inputs.ipynb from azure-ai-samples
Summary: This cookbook provides a guide on how to evaluate AI responses using various input formats, including query-response pairs and conversations. It demonstrates the use of the Azure Evaluation SDK for assessing the performance of AI models based on user interactions.
| Tags: evaluation, query-response, conversations, Azure, SDK, jsonl, csv | Task Categories: evaluation |
Last modified: 2025-08-31
Evaluate_On_Cloud.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide for evaluating data generated by AI applications or large language models (LLMs) using Azure AI services. It demonstrates how to set up and execute evaluations remotely in the cloud, focusing on query and response pairs.
| Tags: Azure AI, evaluation, GPT-4, cloud evaluation, AI applications, data evaluation, LLM | Task Categories: evaluation |
Last modified: 2025-08-31
Evaluate_Base_Model_Endpoint.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to evaluate prompts against various model endpoints deployed on the Azure AI Platform using the Azure AI Evaluation APIs. It demonstrates how to utilize the Evaluate API to assess the responses generated by different LLM models.
| Tags: evaluation, Azure AI, model endpoints, LLM, Python | Task Categories: evaluation |
Last modified: 2025-08-31
Evaluate_App_Endpoint.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to evaluate an application endpoint using Azure AI Evaluation APIs, providing a step-by-step guide for users. It includes code examples for setting up the environment and utilizing various evaluators to assess the performance of a target function.
| Tags: azure-ai, evaluation, api, notebook, data-evaluation, python | Task Categories: evaluation |
Last modified: 2025-08-31
NLP_Evaluators.ipynb from azure-ai-samples
Summary: This cookbook provides a tutorial on using various NLP evaluators to assess the quality of generated text by comparing it to reference text. It covers the installation of necessary packages and demonstrates the use of evaluators such as BLEU, GLEU, METEOR, and ROUGE.
| Tags: NLP, evaluation, text-generation, Azure, BLEU, METEOR, ROUGE | Task Categories: evaluation |
Last modified: 2025-08-31
Custom_Evaluators_Privacy.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to evaluate an AzureOpenAI model deployment using a custom privacy evaluator. It demonstrates the use of specific Azure AI services and datasets to assess model performance in terms of privacy metrics.
| Tags: Azure AI, evaluation, privacy, custom evaluator, data assessment, machine learning | Task Categories: evaluation |
Last modified: 2025-08-31
Custom_Evaluators_Blocklisting.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to evaluate a target function using custom evaluators with Azure AI services. It provides step-by-step instructions for setting up the environment and executing the evaluation process.
| Tags: azure-ai, evaluation, custom-evaluators, data-evaluation, python | Task Categories: evaluation |
Last modified: 2025-08-31
Evaluate_SK_Chat_Completion_Agent.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide to creating and evaluating AI ChatCompletion agents using the Semantic Kernel framework in Azure AI Foundry. It includes code examples for setting up agents, handling user interactions, and evaluating performance metrics.
| Tags: AI agents, evaluation, Azure AI, Semantic Kernel, ChatCompletion, performance metrics, Python | Task Categories: agents,evaluation |
Last modified: 2025-08-31
Evaluate_SK_Azure_AI_Agent.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to evaluate an Azure AI agent’s performance in terms of intent resolution, tool call accuracy, and task adherence using the Semantic Kernel framework. It provides practical examples of creating an AI agent and assessing its capabilities through various evaluators.
| Tags: AI evaluation, Azure AI, Semantic Kernel, intent resolution, tool call accuracy, task adherence, agent development | Task Categories: evaluation,agents |
Last modified: 2025-08-31
Evaluate_Azure_AI_Agent_Quality.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide for evaluating AI agents using the Azure AI Agent Service, focusing on key metrics such as intent resolution, tool call accuracy, and task adherence. It includes code examples and setup instructions for creating and assessing an AI agent’s performance.
| Tags: AI evaluation, Azure AI, intent resolution, tool call accuracy, task adherence, agent performance, Azure Foundry | Task Categories: agents,evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluators_Response_Completeness.ipynb from azure-ai-samples
Summary: This AI cookbook provides a guide on using the Response Completeness Evaluator to assess the quality of agent responses against ground truth data. It includes code examples and setup instructions for evaluating AI-generated responses in Azure.
| Tags: response-evaluation, azure-ai, gpt-4o, agent-assessment, evaluation-metrics, json, data-completeness | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluator_Tool_Call_Accuracy.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to use the Tool Call Accuracy Evaluator to assess the performance of AI agents in utilizing tools effectively during conversations. It provides examples of tool calls and their evaluations based on relevance and parameter correctness.
| Tags: tool-call-evaluation, AI-agents, Azure, performance-assessment, evaluation-metrics, gpt-4o | Task Categories: evaluation,agents |
Last modified: 2025-08-31
AI_Judge_Evaluator_Task_Adherence.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to use the Task Adherence Evaluator to assess the performance of AI agents in adhering to user queries and tasks. It provides examples of both successful and failed adherence evaluations using Azure’s AI tools.
| Tags: task adherence, evaluation, azure, AI agents, performance assessment, gpt-4o | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluator_Intent_Resolution.ipynb from azure-ai-samples
Summary: This cookbook provides a guide on using the Intent Resolution Evaluator to assess how well an AI agent identifies and resolves user intents based on conversation data.
| Tags: intent-resolution, evaluation, azure-ai, customer-service, agent-assessment | Task Categories: evaluation,agents |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Ungrounded_Attr.ipynb from azure-ai-samples
Summary: This AI cookbook provides a step-by-step guide for evaluating ungrounded inference of human attributes in AI responses using Azure’s Ungrounded Attributes Evaluator. It focuses on assessing emotional states and protected classes based on user queries and AI responses.
| Tags: AI evaluation, ungrounded attributes, Azure AI, emotional state, protected class, safety evaluation, machine learning | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Text.ipynb from azure-ai-samples
Summary: This AI cookbook provides a comprehensive guide for simulating conversations targeting AzureOpenAI models and evaluating them for vulnerabilities related to Protected Material and Indirect Attack Jailbreak. It includes installation instructions, configuration setup, and code examples for conducting evaluations and simulations.
| Tags: AI safety, evaluation, AzureOpenAI, adversarial simulation, protected material, indirect attack, vulnerability assessment | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Image.ipynb from azure-ai-samples
Summary: This cookbook provides a tutorial for evaluating the quality and safety of multi-modal AI outputs, specifically focusing on text and image interactions using Azure AI services. It demonstrates how to implement various evaluators to assess potential risks in AI-generated content.
| Tags: Azure AI, safety evaluation, multi-modal, content safety, image evaluation, AI risks, evaluation metrics | Task Categories: evaluation,multimodal |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Content_Safety.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide to simulating text conversations and evaluating them for content safety using Azure OpenAI models. It outlines the necessary configurations, installations, and code implementations to effectively assess potential content harms in AI-generated conversations.
| Tags: content-safety, evaluation, Azure, simulator, AI, conversations, adversarial | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Code_Vuln.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to evaluate code vulnerabilities in various programming languages using Azure AI tools. It focuses on single-turn evaluations of user queries and responses to identify potential security risks in generated code.
| Tags: code-evaluation, security, azure-ai, vulnerability-assessment, sql-injection, programming-languages | Task Categories: evaluation |
Last modified: 2025-08-31
AI_Judge_Evaluators_Safety_Risks_Audio.ipynb from azure-ai-samples
Summary: This AI cookbook provides a comprehensive guide for evaluating safety in audio models using Azure AI services. It includes setup instructions, helper functions for speech synthesis, and methods for simulating adversarial conversations.
| Tags: Azure AI, audio evaluation, safety evaluation, speech synthesis, adversarial simulation | Task Categories: evaluation,multimodal |
Last modified: 2025-08-31
AI_Judge_Evaluators_Quality.ipynb from azure-ai-samples
Summary: This AI cookbook provides a step-by-step guide to evaluate prompts against various model endpoints deployed on Azure AI Platform using the Azure AI Evaluation SDK. It demonstrates how to set up the environment, install necessary packages, and utilize evaluators for assessing model responses.
| Tags: evaluation, azure-ai, prompt-evaluation, model-endpoints, python | Task Categories: evaluation |
Last modified: 2025-08-31
Simulate_Evaluate_Ungrounded_Attributes.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to simulate and evaluate ungrounded inference of human attributes using Azure OpenAI models. It includes installation, configuration, and execution of evaluation tasks.
| Tags: Azure, evaluation, ungrounded attributes, simulation, OpenAI, AI models | Task Categories: evaluation |
Last modified: 2025-08-31
Simulate_Evaluate_Groundedness.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide to simulating and evaluating the groundedness of AI model responses using the Azure AI Evaluation SDK. It emphasizes the importance of ensuring that AI outputs are based on reliable information.
| Tags: groundedness, evaluation, Azure AI, model assessment, simulation, AI trustworthiness | Task Categories: evaluation |
Last modified: 2025-08-31
Simulate_Evaluate_ContentSafety.ipynb from azure-ai-samples
Summary: This cookbook provides a guide for simulating multi-turn conversations with a deployed Azure OpenAI model and evaluating the results for content safety harms. It includes setup instructions, code examples, and evaluation metrics.
| Tags: content safety, evaluation, Azure OpenAI, simulator, multi-turn conversation, adversarial testing | Task Categories: evaluation |
Last modified: 2025-08-31
Simulate_Evaluate_Code_Vulnerability.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to simulate code generation and evaluate the generated code for vulnerabilities using Azure AI tools. It includes instructions for setting up the environment, running simulations, and evaluating results.
| Tags: code vulnerability, simulation, Azure AI, evaluation, notebook, adversarial testing | Task Categories: evaluation |
Last modified: 2025-08-31
Simulate_From_Input_Text.ipynb from azure-ai-samples
Summary: This AI cookbook provides a tutorial on simulating queries and responses using Azure OpenAI services, focusing on generating high-quality interactions from input text. It includes setup instructions, code examples, and evaluation methods for assessing the performance of the generated responses.
| Tags: azure, openai, simulation, evaluation, query-generation, text-processing | Task Categories: evaluation,rag |
Last modified: 2025-08-31
Simulate_From_Conversation_Starter.ipynb from azure-ai-samples
Summary: This cookbook provides a guide to simulate conversations using Azure AI services, specifically leveraging the Azure OpenAI Service to generate high-quality simulated data from predefined conversation starters. It includes setup instructions, code examples, and a structured approach to implementing a conversation simulator.
| Tags: azure, simulator, conversation, AI, OpenAI, data-generation, evaluation | Task Categories: evaluation,agents |
Last modified: 2025-08-31
Simulate_From_Azure_Search_Index.ipynb from azure-ai-samples
Summary: This AI cookbook demonstrates how to simulate queries and responses using Azure’s AI services, specifically leveraging the Azure OpenAI Service and Azure Search. It provides a structured approach to generate high-quality interactions with data stored in Azure Search using large language models.
| Tags: azure, openai, search, simulation, llm, data-query, evaluation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
Simulate_Adversarial.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide to using the Azure AI Adversarial Simulator for simulating adversarial question-answering scenarios against an online endpoint. It includes setup instructions, code examples, and integration with Azure AI services.
| Tags: adversarial, simulation, Azure AI, question-answering, evaluation, tutorial | Task Categories: evaluation |
Last modified: 2025-08-31
Azure_OpenAI_Graders.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide for evaluating large language models using Azure OpenAI Graders, focusing on various evaluation metrics and grading techniques. It demonstrates how to set up and utilize different graders to assess model outputs effectively.
| Tags: evaluation, Azure OpenAI, grading, text similarity, model evaluation, AI tutorial | Task Categories: evaluation |
Last modified: 2025-08-31
AI_RedTeaming_MCS_Agent.ipynb from azure-ai-samples
Summary: This cookbook provides a comprehensive guide on using Azure AI Evaluation’s AI Red Teaming Agent to assess the safety and resilience of Copilot Studio-created agents against adversarial prompt attacks. It includes setup instructions, code examples, and details on various risk categories and attack strategies.
| Tags: AI Red Teaming, Azure AI, adversarial attacks, safety evaluation, Copilot Studio, risk assessment | Task Categories: evaluation,agents |
Last modified: 2025-08-31
AI_RedTeaming.ipynb from azure-ai-samples
Summary: This AI cookbook provides a comprehensive guide on using Azure’s AI Red Teaming Agent to assess the safety and resilience of AI systems against adversarial prompt attacks. It details the setup, execution, and evaluation of various risk categories and attack strategies to identify potential safety issues in generative AI models.
| Tags: AI Red Teaming, Azure, adversarial attacks, safety evaluation, risk assessment, generative AI, Python | Task Categories: evaluation |
Last modified: 2025-08-31
video_chunk_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to process video chunks using the GPT-4 Turbo with Vision API, enabling sequential analysis of video content. It provides a structured approach to extract scene information from video segments and generate a comprehensive breakdown.
| Tags: video-analysis, GPT-4, Azure, multimodal, scene-detection, API-integration | Task Categories: multimodal |
Last modified: 2025-08-31
video_chunk_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a step-by-step guide for processing video chunks using the GPT-4 Turbo with Vision API, enabling sequential analysis of video content. It includes setup instructions, code for downloading and processing videos, and integration with Azure services.
| Tags: video-processing, GPT-4, Azure, API, multimodal, video-analysis, chunk-processing | Task Categories: multimodal |
Last modified: 2025-08-31
video_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a guide for analyzing and optimizing advertisement videos using the GPT-4 Turbo with Vision API. It demonstrates how to extract key features from videos and summarize their content effectively.
| Tags: GPT-4, video analysis, advertisement, summarization, Azure OpenAI, multimodal | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
video_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a guide for utilizing the GPT-4 Turbo with Vision API to analyze and summarize advertisement videos. It includes setup instructions, code examples, and a structured approach to processing video content.
| Tags: GPT-4, video-analysis, advertisement, Azure, API, summarization, multimodal | Task Categories: multimodal,summarization |
Last modified: 2025-08-31
rag_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to enhance the capabilities of GPT-4 Turbo with Vision by integrating custom data to augment image inputs. It provides a practical example of using Azure services to process images and retrieve relevant information.
| Tags: rag, image-processing, Azure, GPT-4, multimodal, API-integration, data-augmentation | Task Categories: rag,multimodal |
Last modified: 2025-08-31
multiple_images_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to utilize the GPT-4 Turbo with Vision API for defect detection by comparing images. It provides a structured approach to managing multiple image inputs and generating responses based on visual analysis.
| Tags: defect detection, image comparison, GPT-4 Turbo, Azure OpenAI, multimodal processing, API integration | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
face_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to utilize Azure’s face API in conjunction with GPT-4 Turbo with Vision to assess the quality of face images based on specific criteria.
| Tags: face-recognition, image-evaluation, GPT-4, Azure, API-integration, multimodal | Task Categories: multimodal,evaluation |
Last modified: 2025-08-31
enhancement_grounding_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a guide for applying grounding techniques to image inputs using the GPT-4 Turbo with Vision API. It includes code samples for setting up the environment, processing images, and generating descriptive text based on visual content.
| Tags: GPT-4, image-processing, grounding, Azure, API, multimodal, computer-vision | Task Categories: multimodal |
Last modified: 2025-08-31
enhancement_OCR_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a practical guide for integrating Optical Character Recognition (OCR) with image inputs using the GPT-4 Turbo with Vision API. It includes setup instructions, code examples, and usage scenarios for enhancing AI capabilities with visual data.
| Tags: OCR, GPT-4, Azure, image-processing, AI-assistant, multimodal | Task Categories: multimodal |
Last modified: 2025-08-31
basic_chatcompletions_example_restapi.ipynb from azure-ai-samples
Summary: This cookbook provides a sample implementation for processing images using the GPT-4 Turbo with Vision API, focusing on generating descriptive tags for images. It includes setup instructions, code snippets, and error handling for API calls.
| Tags: GPT-4, image-tagging, API, Azure, multimodal, image-processing, Python | Task Categories: multimodal |
Last modified: 2025-08-31
multi-agent.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to build a multi-agent framework using the Azure OpenAI Assistant API, focusing on generating and analyzing images through collaborative AI agents. It serves as a guide for developers to create sophisticated applications that leverage multiple AI capabilities.
| Tags: azure-openai, multi-agent, image-generation, image-analysis, AI-assistants, generative-AI | Task Categories: agents,multimodal |
Last modified: 2025-08-31
assistants_function_calling_with_bing_search.ipynb from azure-ai-samples
Summary: This AI cookbook demonstrates how to integrate Bing Search APIs with Azure OpenAI models to provide up-to-date information from the web. It includes code snippets for performing searches, managing threads, and handling messages within the context of an assistant.
| Tags: Bing Search, Azure OpenAI, function calling, web data, AI assistant, real-time information | Task Categories: agents,rag |
Last modified: 2025-08-31
assistant-wind_farm.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to create a Wind Turbine Farm Management Assistant using Azure OpenAI services, allowing users to interact with the assistant for maintenance and operational queries. It showcases the integration of various tools and APIs to facilitate data retrieval and processing.
| Tags: AI assistant, Azure OpenAI, wind turbine management, data processing, multimodal interaction, code interpreter | Task Categories: agents,multimodal |
Last modified: 2025-08-31
assistant-personal_finance.ipynb from azure-ai-samples
Summary: This AI cookbook provides a comprehensive guide for creating a personal financial assistant using Azure OpenAI services, integrating stock price retrieval and email functionalities. It demonstrates how to manage user interactions and process financial queries effectively.
| Tags: personal finance, Azure OpenAI, stock price retrieval, email integration, function calling, portfolio management | Task Categories: agents,rag |
Last modified: 2025-08-31
assistant-math_tutor.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to create a Math Tutor assistant using Azure OpenAI services, showcasing the use of threads, messages, and runs for interactive problem-solving. It provides practical examples of processing user queries and generating responses, including visual outputs.
| Tags: Azure OpenAI, math tutor, interactive assistant, image processing, API integration | Task Categories: agents,multimodal |
Last modified: 2025-08-31
assistant-failed_banks.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to create an AI assistant that can analyze data about failed banks using Azure OpenAI services. It showcases the integration of code interpretation and function calling to process user queries and generate visual outputs.
| Tags: Azure OpenAI, data-analysis, code-interpreter, visualization, assistant-tools, CSV-processing | Task Categories: agents,multimodal |
Last modified: 2025-08-31
agent-sales-analyst.ipynb from azure-ai-samples
Summary: This cookbook demonstrates how to utilize Azure OpenAI to analyze sales data by converting Excel files into Markdown format, uploading them for processing, and generating insights through an AI agent. It showcases the integration of Azure tools for efficient data analysis workflows.
| Tags: Azure OpenAI, data analysis, Excel, Markdown, AI agents, file processing, sales insights | Task Categories: agents |
Last modified: 2025-08-31
agent-investment_advisor.ipynb from azure-ai-samples
Summary: This AI cookbook demonstrates the creation of an investment advisor agent that utilizes real-time stock data and portfolio analysis to assist users in managing their investments. It integrates various tools such as function calling and code interpretation to streamline decision-making processes.
| Tags: investment, AI agent, portfolio analysis, function calling, code interpreter, data visualization, yfinance | Task Categories: agents |
Last modified: 2025-08-31
template.ipynb from azure-ai-samples
Summary: This AI cookbook serves as a template for users to set up and utilize Azure AI services. It includes installation instructions, variable declarations, and a structure for parameterization.
| Tags: Azure, AI services, template, notebook, parameterization, tutorial, installation | Task Categories: other |
Last modified: 2025-08-31
Topic_Modeling.ipynb from cohere-examples
Summary: This AI cookbook demonstrates how to perform topic modeling using the BERTopic library and visualize the results with Altair. It includes steps for data preparation, embedding generation, clustering, and interactive visualization of topics derived from a dataset.
| Tags: topic-modeling, data-visualization, clustering, python, machine-learning, natural-language-processing | Task Categories: other |
Last modified: 2025-08-31
06_multi_agent_with_genie.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a comprehensive guide for building, evaluating, and deploying AI agents using MLflow within a Databricks environment. It includes detailed instructions for logging agent configurations and metrics, facilitating iterative development and deployment.
| Tags: mlflow, databricks, agents, evaluation, deployment, python | Task Categories: agents,evaluation |
Last modified: 2025-08-31
05_tool_calling_agent.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a structured approach to building, evaluating, and deploying AI agents using MLflow and Databricks. It includes code snippets and configurations for integrating various tools and managing agent workflows effectively.
| Tags: mlflow, databricks, agents, evaluation, vector-search, function-calling | Task Categories: agents,rag,evaluation |
Last modified: 2025-08-31
04_create_tools.ipynb from databricks-genai-cookbook
Summary: This AI cookbook provides a structured approach to creating and deploying tools for an agent using Databricks and MLflow. It includes code for SKU translation and testing, along with integration into Unity Catalog.
| Tags: databricks, mlflow, sku-translation, unity-catalog, python, testing | Task Categories: agents |
Last modified: 2025-08-31
03_create_synthetic_eval.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a framework for creating synthetic evaluation data for a Retrieval-Augmented Generation (RAG) chatbot that interacts with Databricks users regarding Spark. It includes steps for configuring the environment, generating evaluation datasets, and managing data storage in a Delta Table.
| Tags: synthetic-data, evaluation, databricks, spark, rag, agents | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
02_agent_setup.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a structured approach to configuring and managing agent storage in a Databricks environment using MLflow. It guides users through the setup of an AgentStorageConfig class and the validation of storage locations for code, metadata, and evaluation data.
| Tags: agent configuration, MLflow, Databricks, Unity Catalog, data management, Pydantic | Task Categories: agents |
Last modified: 2025-08-31
01_data_pipeline.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a comprehensive guide to building a data pipeline for transforming unstructured documents into a vector index suitable for retrieval by an AI agent. It includes configuration steps, code examples, and best practices for optimizing the data pipeline’s performance and quality.
| Tags: data-pipeline, vector-index, document-processing, retrieval-augmented-generation, databricks, mlflow, spark | Task Categories: rag,agents,other |
Last modified: 2025-08-31
Mosaic-AI-Agents-10-Minute-Demo.ipynb from databricks-genai-cookbook
Summary: This cookbook provides a comprehensive guide for deploying a Retrieval-Augmented Generation (RAG) application using the Mosaic AI Agent Framework and evaluating its performance with MLflow. It includes detailed instructions for setting up necessary resources, logging models, and deploying applications for stakeholder feedback.
| Tags: rag, Mosaic AI, MLflow, agent evaluation, data management | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
Tool_use_with_Toolhouse.ipynb from together-ai-cookbook
Summary: Classification failed.
| Tags: | Task Categories: other |
Last modified: 2025-08-31
Contextual_RAG_on_Union.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide to building a Contextual Retrieval-Augmented Generation (RAG) workflow using Together AI on the Union platform. It covers web scraping, embedding generation, and serving functionalities to create a cohesive application ready for enterprise deployment.
| Tags: rag, web-scraping, embedding, contextual-chunks, vector-database, production-grade, union | Task Categories: rag |
Last modified: 2025-08-31
Together_Code_Interpreter.ipynb from together-ai-cookbook
Summary: The Together Code Interpreter (TCI) cookbook provides examples and instructions for executing Python code and shell commands in a secure environment, facilitating data analysis, visualization, and script execution. It demonstrates how to maintain state across executions and interact with uploaded files.
| Tags: data analysis, Python, visualization, file interaction, code execution | Task Categories: other |
Last modified: 2025-08-31
Thinking_Augmented_Generation.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to enhance the performance of smaller AI models by integrating reasoning capabilities from larger models. It specifically showcases the use of the DeepSeek-R1 model to generate reasoning tokens that improve responses from the Mistral Small model.
| Tags: thinking-augmented-generation, AI-cookbook, model-integration, DeepSeek-R1, Mistral-Small | Task Categories: agents |
Last modified: 2025-08-31
Summarization_LongContext_Finetuning.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide to fine-tuning LLMs for long context summarization tasks, including dataset preparation, model training, and evaluation metrics. It demonstrates how to improve summarization capabilities of LLMs by fine-tuning them on specific datasets and comparing their performance against baseline models.
| Tags: fine-tuning, summarization, evaluation, long-context, LLM | Task Categories: fine-tuning,summarization,evaluation |
Last modified: 2025-08-31
Summarization_Evaluation.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to summarize legislative text using large language models (LLMs) and evaluate the summaries with BERTScore. It includes steps for fetching text, crafting summarization prompts, and visualizing summary quality.
| Tags: summarization, evaluation, BERTScore, LLMs, text-processing | Task Categories: summarization,evaluation |
Last modified: 2025-08-31
Structured_Text_Extraction_from_Images.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to extract structured data from images using a language vision model and a language model with JSON capabilities. It focuses on processing receipt images to identify items, prices, and quantities in a structured format.
| Tags: data-extraction, image-processing, json, receipt-analysis, structured-data | Task Categories: multimodal,rag |
Last modified: 2025-08-31
Semantic_Search.ipynb from together-ai-cookbook
Summary: This cookbook provides a guide to implementing semantic search over a dataset of movies using embeddings to rank movies based on their relevance to user queries. It demonstrates how to generate embeddings for movie data and compare them against user queries to find the most semantically similar movies.
| Tags: semantic search, embeddings, cosine similarity, movie dataset, user query | Task Categories: rag |
Last modified: 2025-08-31
Search_with_Reranking.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to enhance semantic search results using a reranker model, specifically focusing on improving the relevance of retrieved documents based on a given query. It provides a practical implementation using the Together API and various embedding models.
| Tags: semantic-search, reranking, embedding, API, movie-dataset, similarity-scoring, Python | Task Categories: rag,evaluation |
Last modified: 2025-08-31
RAG_with_Reasoning_Models.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to use a reasoning model to answer questions based on contextual information retrieved from a legislative document. It includes steps for fetching, processing, embedding, and querying the text to provide informed responses.
| Tags: rag, question-answering, text-processing, embedding, contextual-retrieval, reasoning-models | Task Categories: rag |
Last modified: 2025-08-31
PDF_to_Podcast.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide to transforming PDF documents into engaging podcast scripts using AI. It outlines the necessary setup, code, and methodologies for extracting content and generating dialogue between a host and a guest.
| Tags: podcast, PDF, AI, script-generation, data-extraction, JupyterLab | Task Categories: rag,multimodal |
Last modified: 2025-08-31
Open_Contextual_RAG.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide to implementing Contextual Retrieval-Augmented Generation (RAG) using open-source models. It details the process of chunking documents, generating contextual snippets, and utilizing both keyword and semantic embeddings for effective information retrieval.
| Tags: rag, contextual-retrieval, embedding, bm25, information-retrieval, open-source | Task Categories: rag,other |
Last modified: 2025-08-31
Multiturn_Conversation_Finetuning.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to fine-tune a language model for improved multi-turn conversational capabilities using the CoQA dataset. It includes steps for data preparation, model training, and evaluation metrics.
| Tags: fine-tuning, CoQA, conversation, evaluation, transformers | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
Multimodal_Search_and_Conditional_Image_Generation.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to implement text-to-image and image-to-image search using multimodal embedding models, along with conditional image generation using diffusion models. It provides practical examples and code snippets for retrieving semantically relevant images and generating new images based on them.
| Tags: multimodal, image-generation, text-to-image, image-retrieval, conditional-generation | Task Categories: multimodal,other |
Last modified: 2025-08-31
MultiModal_RAG_with_Nvidia_Investor_Slide_Deck.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to utilize a multimodal retrieval-augmented generation (RAG) approach to interact with Nvidia’s investor slide deck, enabling users to query and retrieve information effectively from the document. It leverages the ColQwen2 model for indexing and the Llama 3.2 model for generating responses based on the retrieved content.
| Tags: rag, multimodal, Nvidia, document-querying, AI-cookbook, ColQwen2, Llama-3 | Task Categories: rag,multimodal |
Last modified: 2025-08-31
LongContext_Finetuning_RepetitionTask.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates the process of fine-tuning a language model on a long-context repetition task, highlighting the challenges faced by LLMs with longer inputs. It provides a step-by-step guide to setting up the task, evaluating model performance, and improving results through fine-tuning.
| Tags: fine-tuning, long-context, LLM, evaluation, repetition-task, datasets | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
LoRA_Finetuning&Inference.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to perform fine-tuning and inference using Low-Rank Adaptations (LoRA) with the Together AI API. It provides step-by-step instructions for uploading datasets, training models, and generating responses using various LoRA fine-tunes.
| Tags: LoRA, fine-tuning, AI, Together AI, model inference, text generation | Task Categories: fine-tuning |
Last modified: 2025-08-31
Knowledge_Graphs_with_Structured_Outputs.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to generate and visualize knowledge graphs using Large Language Models (LLMs) and structured JSON outputs. It leverages Together AI’s JSON mode to create knowledge graph components and utilizes GraphViz for visualization.
| Tags: knowledge-graph, LLM, JSON, GraphViz, data-visualization, API | Task Categories: other |
Last modified: 2025-08-31
Getting_started_with_Llama4.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide for developers to utilize Meta’s Llama 4 models via the Together AI API, covering various capabilities including chat completions, repository summarization, and image understanding.
| Tags: Llama4, Together AI, image understanding, repository summarization, multimodal | Task Categories: multimodal,summarization,other |
Last modified: 2025-08-31
Flux_LoRA_Inference.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to generate images using the FLUX.1 model with LoRA fine-tunes, focusing on the use of trigger words and the mixing of multiple LoRA models. It provides practical examples and links to various LoRA styles for image generation.
| Tags: image-generation, LoRA, FLUX.1, multimodal, AI-cookbook, Python | Task Categories: multimodal |
Last modified: 2025-08-31
Finetuning_Guide.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide for fine-tuning large language models using the Together AI platform, covering data preparation, job monitoring, and evaluation of model performance. It aims to help users adapt pre-trained models to specific tasks and datasets effectively.
| Tags: fine-tuning, LLMs, model evaluation, data preparation, Together AI | Task Categories: fine-tuning,evaluation |
Last modified: 2025-08-31
DPO_Finetuning.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to perform preference fine-tuning using Direct Preference Optimization (DPO) on the HelpSteer2 dataset, enabling models to generate more helpful responses based on human preferences. It provides a step-by-step guide for setting up the environment, processing datasets, and training models using the Together AI platform.
| Tags: fine-tuning, DPO, preference optimization, AI training, Together AI, HelpSteer2, language models | Task Categories: fine-tuning |
Last modified: 2025-08-31
Continual_Finetuning.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates the process of Continual Fine-tuning (CFT) on function calling datasets, showcasing how to incrementally improve a model’s capabilities. It includes steps for data preparation, model training, and evaluation using the Together API.
| Tags: fine-tuning, function-calling, data-preparation, model-training, together-api | Task Categories: fine-tuning |
Last modified: 2025-08-31
Prompt_Evals.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to compare different prompts and model settings for summarization tasks using the Together AI Evaluations API. It focuses on optimizing prompt effectiveness and evaluating summary quality against established criteria.
| Tags: prompt-engineering, summarization, evaluation, AI, datasets, model-comparison | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
Compare_Evals.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide to comparing the performance of two language models on summarization tasks using the Together AI Evaluations API. It demonstrates how to load a dataset, configure models, and evaluate their outputs based on various quality criteria.
| Tags: summarization, model-comparison, evaluation, datasets, AI | Task Categories: evaluation,summarization |
Last modified: 2025-08-31
Classification_Evals.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to evaluate the safety of language models using the HarmBench dataset, comparing two models’ responses to potentially harmful prompts. It utilizes a classification approach to determine whether the outputs are harmful or not.
| Tags: HarmBench, safety evaluation, language models, classification, AI ethics, harmful content detection | Task Categories: evaluation,classification |
Last modified: 2025-08-31
Embedding_Visualization.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to generate embeddings for a movie dataset using the Together AI API and visualize the embeddings with UMAP. It aims to explore the clustering of movie genres in the vector space representation.
| Tags: embeddings, UMAP, movie-dataset, visualization, data-analysis, together | Task Categories: other |
Last modified: 2025-08-31
Batch_Inference_Evals.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to use Together AI’s Batch Inference API to evaluate large language models on factual question answering using the SimpleQA benchmark. It includes steps for formatting requests, generating answers, and implementing automated grading workflows.
| Tags: batch-inference, evaluation, factual-qa, automated-grading, DeepSeek-V3 | Task Categories: evaluation |
Last modified: 2025-08-31
Together_Open_Deep_Research_CookBook.ipynb from together-ai-cookbook
Summary: This cookbook provides a structured approach to conducting research using large language models and web search techniques, enabling users to generate comprehensive, evidence-based reports. It emphasizes modularity and adaptability for various research needs.
| Tags: research, evidence-based, LLM, web search, report generation, modular design | Task Categories: rag,agents,summarization |
Last modified: 2025-08-31
Serial_Chain_Agent_Workflow.ipynb from together-ai-cookbook
Summary: This cookbook provides a structured workflow for creating an audio podcast from a PDF document using a series of language model calls. It demonstrates how to extract relevant information, generate outlines, and create scripts in a serial chain format.
| Tags: podcast, LLM, data-extraction, workflow, serial-chain, text-to-speech | Task Categories: agents,rag |
Last modified: 2025-08-31
PydanticAI_Agents.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create intelligent agents using PydanticAI to search for flights, extract flight information, validate results, and handle seat selection through natural language processing.
| Tags: flight-booking, agents, data-extraction, pydantic, natural-language-processing, API-integration | Task Categories: agents |
Last modified: 2025-08-31
Parallel_Subtask_Agent_Workflow.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create an agent workflow that decomposes complex tasks into subtasks, executed in parallel using different language models. It showcases the orchestration of LLMs to efficiently tackle various aspects of a coding task.
| Tags: orchestrator, subtask, parallel-execution, LLM, task-decomposition, asyncio | Task Categories: agents |
Last modified: 2025-08-31
Parallel_Agent_Workflow.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create a parallel agent workflow using multiple language models to collaboratively solve tasks and synthesize responses. It highlights the benefits of leveraging various models’ strengths through an aggregator model that refines the output.
| Tags: parallel processing, LLM aggregation, agent workflow, synthesis, collaborative AI | Task Categories: agents |
Last modified: 2025-08-31
Looping_Agent_Workflow.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates a looping agent workflow that iteratively generates and evaluates solutions to programming tasks using LLMs. It employs a Generator LLM to propose solutions and an Evaluator LLM to assess and provide feedback, facilitating continuous improvement until a satisfactory solution is achieved.
| Tags: LLM, agent-workflow, code-evaluation, iterative-improvement, pydantic | Task Categories: agents,evaluation |
Last modified: 2025-08-31
LangGraph_Planning_Agent.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create an intelligent planning agent using LangGraph and Together AI, capable of breaking down complex queries into manageable steps and adapting its plan based on new information.
| Tags: planning, agents, langchain, llama, AI, workflow | Task Categories: agents |
Last modified: 2025-08-31
Agentic_RAG_LangGraph.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to build an advanced Retrieval-Augmented Generation (RAG) system using LangGraph, enabling intelligent searching and reasoning over a collection of ML blog posts. It focuses on creating an agent that can evaluate and synthesize information from multiple sources to answer questions effectively.
| Tags: rag, agents, langchain, document-retrieval, machine-learning | Task Categories: rag,agents,evaluation |
Last modified: 2025-08-31
Agents_KlavisAI.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create an AI agent that integrates Together AI’s language models with Klavis MCP servers, allowing for interaction with external services and APIs. It includes examples of processing requests for video analysis and sending emails using the integrated services.
| Tags: AI integration, Together AI, Klavis AI, video analysis, email automation, agents | Task Categories: agents,summarization |
Last modified: 2025-08-31
Together_Open_DataScience_Agent.ipynb from together-ai-cookbook
Summary: This cookbook provides a comprehensive guide for building a Data Science Agent using the ReAct framework, enabling iterative reasoning and code execution for data analysis tasks. It showcases how to create an open-source agent capable of handling complex data science workflows autonomously.
| Tags: data-science, agents, python-execution, iterative-reasoning, data-analysis, visualization | Task Categories: agents |
Last modified: 2025-08-31
DSPy_Agents.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create and optimize DSPy agents using different LLMs to search for information across multiple steps. It showcases the performance improvements achieved by leveraging a smaller model for initial development and a larger model for optimization.
| Tags: DSPy, LLM, information-retrieval, optimization, fact-checking, multi-hop-claims | Task Categories: agents,rag,evaluation |
Last modified: 2025-08-31
Conditional_Router_Agent_Workflow.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to implement a conditional router agent workflow that dynamically selects the appropriate language model based on the task requirements, optimizing for various specialties such as coding, planning, and storytelling.
| Tags: LLM, router, workflow, task-selection, pydantic, API | Task Categories: agents |
Last modified: 2025-08-31
Agents_Composio.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to integrate Together AI’s language models with Composio’s tools to automate email communication. It covers setting up the required packages, configuring the email tool, and customizing email behavior through preprocessing.
| Tags: email automation, AI agents, Gmail integration, Composio, Together AI, preprocessing, API integration | Task Categories: agents |
Last modified: 2025-08-31
Agents_Arcade.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to integrate Together AI’s language models with Arcade’s tools to create an AI agent capable of sending emails. It covers the setup, configuration, and execution of email communication using these tools.
| Tags: email automation, AI agents, Gmail integration, Together AI, Arcade.dev, OAuth authentication, Python | Task Categories: agents |
Last modified: 2025-08-31
Agents_Agno.ipynb from together-ai-cookbook
Summary: This cookbook demonstrates how to create AI agents using the Agno framework in conjunction with Together AI’s language models, enabling capabilities such as web search, knowledge base access, and multi-agent collaboration.
| Tags: AI agents, knowledge base, web search, financial data, multi-agent systems | Task Categories: agents,rag |
Last modified: 2025-08-31
colabtune.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to fine-tune a large language model using Google Colab, specifically focusing on the LLaMA 2 model. It provides step-by-step instructions for setting up the environment and executing the fine-tuning process.
| Tags: fine-tuning, LLaMA, Colab, transformers, AI cookbook, model training | Task Categories: fine-tuning,summarization |
Last modified: 2025-08-31
Llama_3_1_Synthetic_Data.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide to generating structured synthetic geography quiz questions using the Llama 3.1 model via an API. It includes code examples for setting up the environment, generating questions, and saving them in a dataset format.
| Tags: geography, quiz, synthetic-data, llama, pydantic, API | Task Categories: other |
Last modified: 2025-08-31
structured_response_llama_3_1.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a comprehensive guide on utilizing the Llama 3.1 models for generating structured responses using the Fireworks AI API. It covers various applications including data extraction, task automation, and precision control through defined output schemas.
| Tags: structured-responses, data-extraction, task-automation, API-integration, grammar, json-schema | Task Categories: other |
Last modified: 2025-08-31
[[external]Healthcare_Generation_with_Reasoning_Mode_DeepSeek(v3&_R1).ipynb](https://github.com/fw-ai/cookbook/blob/main/learn/structured_response/[external]_Healthcare_Generation_with_Reasoning_Mode_DeepSeek(v3_&_R1).ipynb) from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to use structured responses with DeepSeek Models on Fireworks AI to generate reliable healthcare data, focusing on automation and integration into electronic health record systems.
| Tags: healthcare, structured-data, API, pydantic, automation, DeepSeek, Fireworks AI | Task Categories: other |
Last modified: 2025-08-31
[[external]ComputerSpec_Generation_with_Reasoning_Mode_DeepSeek(v3&_R1).ipynb](https://github.com/fw-ai/cookbook/blob/main/learn/structured_response/[external]_ComputerSpec_Generation_with_Reasoning_Mode_DeepSeek(v3_&_R1).ipynb) from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to generate structured computer system specifications using Fireworks AI’s DeepSeek models, focusing on predictability and automation in hardware configurations.
| Tags: computer specifications, Fireworks AI, DeepSeek, structured responses, API integration, pydantic | Task Categories: other |
Last modified: 2025-08-31
mcp_server_with_store_false_argument.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide on how to interact with the Fireworks API using the OpenAI client, demonstrating how to make API calls and handle responses effectively. It includes examples of querying for information and managing response data.
| Tags: API, OpenAI, Fireworks, Python, data-retrieval, streaming | Task Categories: other |
Last modified: 2025-08-31
fireworks_streaming_example.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides examples of how to interact with the Fireworks API using OpenAI’s client library, demonstrating how to generate text responses based on user prompts.
| Tags: API, OpenAI, text-generation, streaming, Python, client-library | Task Categories: other |
Last modified: 2025-08-31
fireworks_previous_response_cookbook.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to utilize the Fireworks OpenAI-compatible Response API, focusing on maintaining conversation continuity through the use of previous response IDs. It provides practical examples to illustrate how to efficiently build multi-turn workflows and chain complex reasoning across API calls.
| Tags: OpenAI, API, conversation continuity, multi-turn workflows, response ID, Fireworks, programming | Task Categories: agents,other |
Last modified: 2025-08-31
fireworks_mcp_with_streaming.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide for using the Fireworks API to generate responses and interact with models in a streaming manner. It demonstrates how to set up the client, make queries, and handle responses effectively.
| Tags: Fireworks API, streaming, Python, API integration, response generation | Task Categories: rag,other |
Last modified: 2025-08-31
fireworks_mcp_examples.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides examples of using the Fireworks OpenAI-compatible API with Model Context Protocol (MCP) support, focusing on the integration with the reward-kit repository for various AI tasks.
| Tags: OpenAI, API, MCP, reward-kit, code-analysis, installation, documentation | Task Categories: rag,evaluation |
Last modified: 2025-08-31
rag-paper-titles.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to implement a retrieval-augmented generation (RAG) system using Fireworks Fast Inference LLMs to suggest accessible titles for machine learning papers. It combines large language models with external knowledge to enhance the reliability and usability of generated content.
| Tags: rag, machine learning, title generation, fireworks, text processing, data retrieval, language models | Task Categories: rag,other |
Last modified: 2025-08-31
RAG-with-Fireworks.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates the creation of a Retrieval-Augmented Generation (RAG) system using ChromaDB for vector storage and Fireworks models for language generation. It guides users through data preparation, embedding generation, and the integration of retrieved information to enhance model responses.
| Tags: rag, data-preparation, embedding, fireworks, chromaDB, language-generation | Task Categories: rag,other |
Last modified: 2025-08-31
Multi_LoRA_Demo.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a comprehensive guide for fine-tuning AI models using Fireworks’ Multi-LoRA technique, specifically tailored for product-specific inquiries across various domains. It outlines the steps for dataset preparation, fine-tuning job creation, and model deployment to enhance the AI’s ability to deliver precise responses to user queries.
| Tags: fine-tuning, AI, Fireworks, Multi-LoRA, datasets, model-deployment, product-specific | Task Categories: fine-tuning |
Last modified: 2025-08-31
search_and_generate_toolhouse.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to enhance large language models (LLMs) deployed on Fireworks.AI with tool-based extensions, allowing for real-time data extraction and image generation. It provides a technical guide for integrating external functionalities into LLM workflows without manual coding.
| Tags: toolhouse, image-generation, data-extraction, LLM, Fireworks.AI, real-time-data, function-calling | Task Categories: rag,agents,multimodal |
Last modified: 2025-08-31
fireworks_langgraph_tool_usage.ipynb from fireworks-ai-cookbook
Summary: This AI cookbook demonstrates the integration of the Fireworks function-calling model with the LangGraph framework to create an agent capable of handling user queries and executing specialized tasks. It showcases how to route requests to different models and tools based on user intent.
| Tags: function-calling, LangGraph, AI agents, tool integration, Fireworks, chatbot | Task Categories: agents |
Last modified: 2025-08-31
fireworks_langchain_tool_usage.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to utilize the Fireworks Function Calling model in conjunction with LangChain to create an agent capable of handling user queries and performing mathematical calculations. It showcases the integration of various tools and models to enhance the capabilities of AI agents.
| Tags: function-calling, langchain, AI agents, math evaluation, custom tools | Task Categories: agents |
Last modified: 2025-08-31
fw_autogen_stock_chart.ipynb from fireworks-ai-cookbook
Summary: This AI cookbook demonstrates how to create an agent-based system for generating stock price charts using the AutoGen framework and Fireworks API. It showcases the integration of function calling to facilitate the retrieval and visualization of stock data.
| Tags: stock-prices, data-visualization, function-calling, AI-agents, financial-analysis, AutoGen, Fireworks | Task Categories: agents |
Last modified: 2025-08-31
fireworks_functions_information_extraction.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to utilize the Fireworks Function Calling model to extract structured information from unstructured data sources, such as text or URLs. It showcases the integration of various tools and functions to facilitate information retrieval and processing.
| Tags: information-extraction, function-calling, data-cleaning, API-integration, text-processing, structured-data | Task Categories: rag,other |
Last modified: 2025-08-31
fireworks_function_calling_demo.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to use the Fireworks Function Calling API to retrieve financial data for a specified company and year using a function call within a chat interface. It provides a complete example of setting up the environment, making API calls, and processing the responses.
| Tags: function-calling, financial-data, API-integration, chatbot, OpenAI | Task Categories: agents |
Last modified: 2025-08-31
fireworks_firefunction_openai_qa.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to utilize Fireworks functions to generate structured responses from a language model, specifically for answering questions about the 2022 State of the Union speech with citations.
| Tags: function-calling, structured-responses, State of the Union, openai, data-extraction, API-integration | Task Categories: rag,agents |
Last modified: 2025-08-31
knowledge_distillation.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a comprehensive guide on knowledge distillation using Fireworks AI, focusing on transferring knowledge from larger teacher models to smaller student models while maintaining performance. It outlines a systematic two-stage process involving Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) to enhance model accuracy and response structure.
| Tags: knowledge distillation, fine-tuning, AI models, GSM8K, Fireworks AI, machine learning, training data generation | Task Categories: fine-tuning,other |
Last modified: 2025-08-31
batch_api.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide for using the Batch API to asynchronously process audio files for transcription. It includes examples of submitting multiple audio files, tracking their processing status, and retrieving results in a structured format.
| Tags: batch processing, audio transcription, API integration, asynchronous tasks, CSV tracking | Task Categories: multimodal,other |
Last modified: 2025-08-31
audio_streaming_speech_to_text.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide to streaming audio data to the Fireworks Speech-to-Text API and receiving real-time transcriptions. It includes code examples for audio processing and websocket communication.
| Tags: speech-to-text, audio-streaming, websocket, real-time-transcription, torch, torchaudio, API | Task Categories: multimodal |
Last modified: 2025-08-31
audio_prerecorded_speech_to_text.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide to transcribing prerecorded audio using the Fireworks Prerecorded Speech-to-Text API. It includes installation instructions, API key setup, and example code for making API requests to transcribe audio files.
| Tags: speech-to-text, audio transcription, API integration, Fireworks, Python | Task Categories: other |
Last modified: 2025-08-31
Use_Portkey_with_Fireworks.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a comprehensive guide to integrating Fireworks models using the Portkey AI Gateway, showcasing features like load balancing and fallback strategies. It includes code examples for initialization and usage of the Portkey SDK.
| Tags: AI integration, Fireworks, Portkey, load balancing, fallback, API usage, Python SDK | Task Categories: other |
Last modified: 2025-08-31
mongodb_triggers.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide on integrating Fireworks with MongoDB to enable real-time embedding of datasets as they are inserted. It includes code examples for generating embeddings and querying a MongoDB collection using vector search.
| Tags: rag, mongodb, real-time, embedding, vector search, fireworks, api integration | Task Categories: rag |
Last modified: 2025-08-31
mongodb_koda_retriever.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a comprehensive guide to integrating Koda Retriever with MongoDB and Fireworks for enhanced retrieval-augmented generation (RAG) capabilities. It outlines the steps for data import, embedding, and querying using a hybrid retrieval approach.
| Tags: rag, mongodb, fireworks, data-embedding, koda-retriever, llama-index, query-engine | Task Categories: rag |
Last modified: 2025-08-31
mongodb_agent.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to create a MongoDB agent using LangChain and Fireworks for retrieving movie recommendations based on user queries and embeddings. It integrates MongoDB with an AI agent framework to enhance data retrieval and interaction.
| Tags: mongodb, langchain, rag, data-extraction, ai-agent, recommendation-system, fireworks | Task Categories: rag,agents |
Last modified: 2025-08-31
mongo_resize_embeddings.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a guide to creating a movie recommendation system using Fireworks for embedding generation and MongoDB for data storage and retrieval. It demonstrates how to process movie data, generate embeddings, and perform vector searches to recommend movies based on user queries.
| Tags: movie-recommendation, embedding, mongodb, fireworks, data-processing, vector-search | Task Categories: rag |
Last modified: 2025-08-31
mongo_basic.ipynb from fireworks-ai-cookbook
Summary: This cookbook provides a step-by-step guide to building a movie recommendation system using Fireworks API for embedding generation, MongoDB for data storage, and the Nomic-AI embedding model for understanding movie data. It includes code examples for generating embeddings and querying a MongoDB database to retrieve relevant movie recommendations based on user input.
| Tags: movie-recommendation, embedding, mongodb, fireworks, nomic-ai, data-retrieval, rag | Task Categories: rag |
Last modified: 2025-08-31
Use_Klavis_with_Fireworks.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to integrate Fireworks AI’s language model with Klavis MCP servers to create an AI agent capable of processing user requests, such as summarizing YouTube videos and sending emails. It provides step-by-step instructions for setting up the necessary API keys and creating server instances.
| Tags: AI integration, Fireworks AI, Klavis, YouTube summarization, email automation, API usage | Task Categories: agents,summarization |
Last modified: 2025-08-31
Agents_Arcade.ipynb from fireworks-ai-cookbook
Summary: This cookbook demonstrates how to integrate Fireworks AI’s language models with Arcade’s tools to create an AI agent capable of sending and managing emails. It covers setup, authentication, and the creation of an email-sending agent using natural language processing.
| Tags: email automation, AI agents, Fireworks AI, Arcade, Gmail integration, natural language processing | Task Categories: agents |
Last modified: 2025-08-31