sarabesh/HybridRAG

A hybrid retrieval system for RAG that combines vector search and graph search, integrating unstructured and structured data. It retrieves context using embeddings and a knowledge graph, then passes it to an LLM for generating accurate responses.

29
/ 100
Experimental

This project helps you build more accurate and comprehensive AI chatbots or question-answering systems. It takes your unstructured documents and structured data (like a knowledge graph) as input, intelligently combines information from both, and then uses a large language model to generate precise answers. Data scientists and AI solution architects would use this to power their RAG applications.

No commits in the last 6 months.

Use this if you need to build a robust RAG system that leverages both the semantic understanding of unstructured text and the factual precision of structured knowledge graphs.

Not ideal if your application solely relies on unstructured text for retrieval or if you don't have structured data in a knowledge graph.

AI-chatbot knowledge-retrieval question-answering enterprise-search data-science
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Jupyter Notebook

License

Last pushed

Apr 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/sarabesh/HybridRAG"

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