{"data":{"slug":"lancedb-vectordb-recipes","name":"vectordb-recipes","tagline":"Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs","github_url":"https://github.com/lancedb/vectordb-recipes","owner":"lancedb","repo":"vectordb-recipes","owner_avatar_url":"https://avatars.githubusercontent.com/u/108903835?v=4","primary_language":"Jupyter Notebook","stars":973,"forks":171,"topics":["agents","ai","deep-learning","embeddings","fine-tuning","gpt","gpt-4-vision","lancedb","langchain","llama-index","llms","machine-learning","multimodal","multimodal-ai","openai","rag","vector-database"],"archived":false,"github_pushed_at":"2026-04-24T11:29:16+00:00","maintenance_label":"Slowing","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/lancedb-vectordb-recipes","markdown_url":"https://www.graphcanon.com/tools/lancedb-vectordb-recipes.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lancedb-vectordb-recipes","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lancedb-vectordb-recipes","description":"Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs","homepage_url":null,"license":"Apache-2.0","open_issues":4,"watchers":10,"ai_summary":"A repository providing resources including recipes, examples, and tutorials focused on utilizing vector search and large language models (LLMs) in various applications such as AI agents, RAG systems, and multimodal AI.","readme_excerpt":"# VectorDB-recipes\n<br />\nDive into building GenAI applications!\nThis repository contains examples, applications, starter code, & tutorials to help you kickstart your GenAI projects.\n\n- These are built using LanceDB, a free, open-source, serverless vectorDB that **requires no setup**. \n- It **integrates into Python data ecosystem** so you can simply start using these in your existing data pipelines in pandas, arrow, pydantic etc.\n- LanceDB has **native Typescript SDK** using which you can **run vector search** in serverless functions!\n\n<img src=\"https://github.com/lancedb/vectordb-recipes/assets/5846846/d284accb-24b9-4404-8605-56483160e579\" height=\"85%\" width=\"85%\" />\n\n<br />\nJoin our community for support - <a href=\"https://discord.gg/zMM32dvNtd\">Discord</a> •\n<a href=\"https://twitter.com/lancedb\">Twitter</a>\n\n---\n\nThis repository is divided into 2 sections:\n- [Examples](#examples) - Get right into the code with minimal introduction, aimed at getting you from an idea to PoC within minutes!\n- [Applications](#projects--applications) - Ready to use Python and web apps using applied LLMs, VectorDB and GenAI tools\n\n\nThe following examples are organized into different tables to make similar types of examples easily accessible.\n\n### Sections\n\n- [Build from Scratch](#build-from-scratch) - Step-by-step guides to create AI applications from scratch.\n- [Multimodal](#multimodal) - Build apps that process and search across both text and images.\n- [RAG](#rag) - Combine document retrieval with LLM-powered responses.\n- [Vector Search](#vector-search) - Learn to efficiently find relevant documents using vector-based search.\n- [Chatbot](#chatbot) - Create AI chatbots that fetch information and generate intelligent replies.\n- [Evaluation](#evaluation) - Measure the quality and accuracy of AI-generated answers.\n- [AI Agents](#ai-agents) - Build LLM-driven applications where multiple agents collaborate and interact.\n- [Recommender Systems](#recommender-systems) - Develop AI-powered recommendation systems for personalized suggestions.\n- [Concepts](#concepts) - Tutorials and explanations of key techniques used in AI applications.\n\n\n### 🌟 New 🌟 \nStay up to date with the latest projects, tools, and improvements added to the repository.\n- **V-JEPA Video Search** - <a href=\"https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/v-jepa-video-search/intra-video.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>\n\n### Build from Scratch\n\nStart with the basics! These examples guide you through creating AI applications from the ground up using LanceDB for efficient document retrieval and search.\n\n| Build from Scratch &nbsp; &nbsp;| Interactive Notebook & Scripts &nbsp; | \n|-------- | -------------: |\n|||\n| [Build RAG from Scratch](./tutorials/RAG-from-Scratch) |   |  |\n| [Local RAG from Scratch with Llama3](./tutorials/Local-RAG-from-Scratch) |   |  |\n| [Multi-Head RAG from Scratch](./tutorials/Multi-Head-RAG-from-Scratch/) |    |  |\n| [Fintech AI Agent from Scratch](./examples/fintech-ai-agent) |<a href=\"https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/fintech-ai-agent/fintech-ai-agent.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>       | |\n||||\n\n### MultiModal\n\nSearch across different types of data (text, images, and more). Build powerful search applications that work with diverse inputs.\n\n| Multimodal &nbsp; &nbsp;| Interactive Notebook & Scripts &nbsp; | Blog |\n| --------- | -------------------------- | ----------- |\n||||\n| [V-JEPA Video Search](./examples/v-jepa-video-search/) | <a href=\"https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/examples/v-jepa-video-search/intra-video.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a> | |\n| [Multimodal CLIP: DiffusionDB](./examples/multimodal_clip_diffusiondb/) | <a hre","github_created_at":"2023-06-25T06:10:35+00:00","created_at":"2026-07-07T17:44:47.794189+00:00","updated_at":"2026-08-21T18:02:06.384916+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai","name":"ai"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"embeddings","name":"embeddings"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"gpt","name":"gpt"},{"slug":"llms","name":"llms"},{"slug":"multimodal-ai","name":"multimodal-ai"}],"trust":{"provenance":{"is_fork":false,"github_id":658219396,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-21T18:02:05.574Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":119,"last_release_at":null,"stars_delta_30d":4,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:26:42.065Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-21T18:02:06.063Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-21T18:02:06.063Z"},"languages":{"value":["jupyter notebook","javascript"],"source":"github.language+package.json","observed_at":"2026-08-21T18:02:06.063Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-21T18:02:06.063Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- When you need a comprehensive set of examples, starter code and tutorials specifically optimized for LanceDB, an open-source vector database that integrates seamlessly into the Python data ecosystem","- For projects requiring no infrastructure setup, as it leverages serverless capabilities of LanceDB which eliminates the overhead of maintaining databases","- If you are interested in diving deep into multimodal AI applications where both text and images are processed simultaneously"],"when_not_to_use":["- When seeking support for a specific competitor's vector database (like Pinecone or Weaviate), as Vectordb-recipes focuses solely on LanceDB’s ecosystem","- If you have strict requirements for custom database tuning that only vendor-specific proprietary databases can offer, as Vectordb-recipes’ focus is on leveraging the out-of-the-box advantages of an","critical_facts_for_deployment_or_use_case_specifics: ["],"source":"enrich:decision_facts","observed_at":"2026-07-09T09:10:34.968Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Vectordb-recipes offers resources and tutorials for building GenAI applications using LanceDB. It is particularly designed to help users get started quickly with minimal setup required."}]}}