Enables retrieval-augmented generation by allowing LLMs to search documents in a local folder using vector similarity, supporting multiple file formats.
Local offline semantic search over documents (txt, md, pdf, docx, pptx, csv). Indexes folders into a LanceDB vector database with multilingual embeddings and supports hybrid vector + keyword search via Reciprocal Rank Fusion. No API keys, no cloud, no Docker required.
Enables AI agents to run semantic search over a local folder of text files, returning the best-matching passages ranked by cosine similarity, each with its source filename and score. Runs locally with no API keys, external services, or vector database.
Enables assistants such as Claude Desktop to call document search over a folder of markdown as a tool, returning grounded answers with citations or measured refusals when the evidence is insufficient.