AmirhosseinHonardoust/Graph-RAG-Engine
An explainable AI system that combines Graph Intelligence, Vector Search, and Retrieval-Augmented Generation (RAG) to deliver grounded answers and transparent reasoning paths. Includes a FastAPI backend, Streamlit UI, FAISS vector index, and an in-memory knowledge graph for hybrid retrieval and recommendations.
This project helps anyone who needs to quickly find answers and understand relationships within a large collection of documents. You input your existing documents, and it creates an interactive system where you can ask questions, get direct answers with citations, and receive recommendations for related information. This is ideal for researchers, analysts, or knowledge managers who deal with extensive internal documentation or specialized reports.
Use this if you need an AI system that can answer questions and suggest related documents from your data, while also showing you a clear reasoning path for its answers.
Not ideal if you only need simple keyword search or don't require an explanation of why certain information was retrieved.
Stars
26
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/AmirhosseinHonardoust/Graph-RAG-Engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents