VectorInstitute/kg-rag

This project implements a comprehensive framework for Knowledge Graph Retrieval Augmented Generation (KG-RAG). It focuses on financial data from SEC 10-Q filings and explores how knowledge graphs can improve information retrieval and question answering compared to baseline approaches.

50
/ 100
Established

This project helps financial analysts and researchers extract precise answers from complex financial documents like SEC 10-Q filings. You feed it a collection of these filings and ask questions in natural language, receiving accurate, context-rich answers. It's designed for anyone needing to quickly find specific financial information without manually sifting through dense reports.

Use this if you need to rapidly and accurately answer specific questions using data from a large collection of financial regulatory documents, improving on standard search methods.

Not ideal if your primary need is general document summarization or if your data is not structured financial text.

financial-analysis SEC-filings market-intelligence investor-relations due-diligence
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

26

Forks

11

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/VectorInstitute/kg-rag"

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