FareedKhan-dev/rag-with-raptor

A Step-by-Step Implementation of RAPTOR based RAG implementation

41
/ 100
Emerging

This project helps developers build more effective Retrieval Augmented Generation (RAG) systems by creating a smarter, hierarchical index of their documents. It takes raw source documents, processes them into detailed chunks, then clusters and summarizes these chunks recursively to build a 'knowledge tree' of concepts. The output is a highly optimized vector store that improves the accuracy and relevance of AI-generated answers for a wide range of queries.

No commits in the last 6 months.

Use this if you are a developer struggling with your RAG system providing irrelevant or low-quality answers from complex, extensive documentation.

Not ideal if you need a simple RAG setup for small, straightforward datasets where basic retrieval is sufficient.

LLM application development Information retrieval Knowledge base Natural language processing Vector databases
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

38

Forks

11

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/FareedKhan-dev/rag-with-raptor"

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