snexus/llm-search
Querying local documents, powered by LLM
Implements hybrid search combining dense embeddings (ChromaDB) with sparse SPLADE embeddings, plus advanced RAG techniques like HyDE, multi-querying, and re-ranking with cross-encoders. Supports multiple embedding providers (OpenAI, HuggingFace, Sentence-Transformers) and LLMs via LiteLLM/Ollama, with incremental indexing across multiple document formats (MD, PDF, DOCX). Exposes both FastAPI and MCP server interfaces for integration with IDEs like VSCode, Cursor, and Windsurf.
647 stars.
Stars
647
Forks
71
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/snexus/llm-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
undreamai/LLMUnity
Create characters in Unity with LLMs!
Mintplex-Labs/anythingllm-docs
Documentation of AnythingLLM by Mintplex Labs Inc.
mamei16/LLM_Web_search
An extension for oobabooga/text-generation-webui that enables the LLM to search the web
bloodworks-io/phlox
Open source, local first AI medical scribe for desktop and web.
Ask-Sage/AskSage-Open-Source-Community
🚀 Welcome to AskSage Open Source Repo, a community aimed at providing code 🧑💻, documentation📝,...