Back to directory

VectorDB-recipes

A collection of runnable examples, applications and tutorials for building multimodal AI, retrieval-augmented generation and agent applications with LanceDB, a serverless open-source vector database.

VectorDB-recipes

VectorDB-recipes is a repository of examples, starter code and tutorials for building generative AI applications with LanceDB, a free, open-source, serverless vector database that needs no separate setup and integrates directly into the Python data ecosystem such as pandas, Arrow and Pydantic. LanceDB also has a native TypeScript SDK for running vector search from serverless functions.

The repository is split into Examples, minimal code aimed at getting from an idea to a proof of concept quickly, and Applications, ready-to-use Python and web apps built with applied LLMs, vector search and other generative AI tools. Its sections cover building from scratch, multimodal search across text and images, RAG, vector search, chatbots, evaluation of AI-generated answers, multi-agent applications, and recommender systems.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.