#162 · Primary category： Knowledge Base & RAG
llm-search
Querying local documents, powered by LLM
Project last updated：01/17/26
GitHub Stars
661
Forks
71
Contributors
6
License
MIT
Why we included this project
llm-search is a RAG pipeline you configure with a YAML file, aimed at people who want to ask questions over their own document collection without shipping everything to a hosted service. It parses markdown, PDF, and docx files, stores dense and sparse (SPLADE) embeddings in ChromaDB, and layers hybrid search, re-ranking, HyDE, and multi-query retrieval on top of plain vector lookup. A web frontend and a FastAPI-based MCP server let you query the same index from Cursor, Windsurf, or VS Code Copilot, and incremental indexing means new files get added without re-indexing the whole store. It works with local models or anything OpenAI-compatible, and deep links jump straight to the source page or PDF section. For a private document assistant that stays on your own hardware, this is a solid starting point.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience