Ahmad-Wali-i170106/kgrag-poc
A Graph RAG implementation using Neo4j and LangChain
This tool helps subject matter experts and researchers transform raw, unstructured information from text files, PDFs, and webpages into an organized knowledge graph. It takes these documents as input and builds a structured network of interconnected facts and concepts in a Neo4j database. Anyone needing to find specific information or relationships within a large collection of domain-specific documents would benefit.
No commits in the last 6 months.
Use this if you have many documents and need to easily extract and query factual relationships and entities, even with complex or ambiguous questions.
Not ideal if you only need simple keyword searches or if your documents are already highly structured and easily searchable.
Stars
8
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Ahmad-Wali-i170106/kgrag-poc"
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