chernistry/sentio

Boilerplate RAG System with LangGraph Architecture

26
/ 100
Experimental

Implements a multi-stage retrieval pipeline with dense (Qdrant) + optional sparse (BM25) search, configurable fusion strategies (RRF, weighted, comb-sum), and optional reranking via external APIs. Features LLM-driven answer verification that audits citations and can auto-revise failed responses, with all prompts externalized in markdown for runtime customization. Exposes a REST API returning answers with citations [n], source documents, and detailed verification metadata (verdict, citation correctness, revision notes).

No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Python

License

—

Category

lightweight-rag-systems

Last pushed

Nov 21, 2025

Commits (30d)

0

GitHub
Lightweight Rag Systems · 4 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/chernistry/sentio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

rasinmuhammed/rag-tui

⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch...

52

kbeaugrand/KernelMemory.StructRAG

Microsoft's Kernel Memory StructRAG implementation

44

metawake/ragtune

EXPLAIN ANALYZE for RAG retrieval — inspect, debug, benchmark, and tune your retrieval layer

31

Explore RAG Tools

All categories Trending RAG directory Insights