snexus/llm-search

Querying local documents, powered by LLM

47
/ 100
Emerging

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.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

647

Forks

71

Language

Jupyter Notebook

License

MIT

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.