Loading repository data…
safishamsi / repository
Knowledge Graph-RAG system using Neo4j, LangChain, LangGraph, Claude-3.5-Sonnet. Hybrid retrieval: SBERT embeddings + graph traversal + BM25. 61K papers, 190K authors from Scopus. 50% NDCG improvement, 57% bias reduction. Includes notebooks, evaluation scripts, benchmark queries. Python/Jupyter.
Academic search system combining knowledge graphs with retrieval-augmented generation to eliminate citation bias and hallucinations in research discovery.
Knowledge-Graph-Based-Hybrid-RAG-System/ ├── Neo4jKG/ ├── RAG/ ├── embeddings/ ├── scopusscraping/ ├── Dissertation/ ├── Data/ ├── LLMpoweredRAG.py ├── demowithinspector.pdf ├── queries.txt ├── uobkg.png ├── LICENSE └── README.md
git clone https://github.com/safishamsi/Knowledge-Graph-Based-Hybrid-RAG-System.git
cd Knowledge-Graph-Based-Hybrid-RAG-System
# Install dependencies
pip install neo4j sentence-transformers faiss-cpu langchain langchain-anthropic langgraph
# Set environment variables
export ANTHROPIC_API_KEY="your-api-key"
from LLMpoweredRAG import AcademicSearchSystem
# Initialize the system
search = AcademicSearchSystem()
# Search for papers
results = search.query("machine learning in healthcare")
# Find collaborators
collaborators = search.find_collaborators("deep learning")
# Get research trends
trends = search.analyze_trends("transformer architectures", years=5)
Research Context
Master's thesis project, University of Birmingham (2025)
Supervised by Prof. Dr. Paolo Missier
License
MIT License - see LICENSE file
Contact
For questions or collaboration: safishamsi98@gmail.com
Selected from shared topics, language and repository description—not editorial ratings.
semantica-agi /
Semantica • Build AI systems that can explain, trace, and justify every decision. Knowledge graphs, context graphs, reasoning engines, provenance, and governance for production AI.
AmirhosseinHonardoust /
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.
jmponcebe /
GraphRAG system for querying drug interactions and adverse events using FDA data. Combines Neo4j knowledge graph + ChromaDB vector search + Gemini LLM, served via FastAPI and Streamlit.
nynuz /
An end-to-end GraphRAG pipeline that combines Qdrant hybrid vector search with Neo4j Knowledge Graph traversal to build a retrieval system that goes beyond simple embedding similarity.
Premkumar9799817360 /
About An intelligent Financial Analysis system that combines Knowledge Graphs with Large Language Models using GraphRAG (Graph Retrieval-Augmented Generation) to answer complex financial queries with explainable reasoning.
BdTaha /
Privacy-first RAG platform combining semantic vector search, knowledge graph traversal, and a Q-Learning routing agent for intelligent, grounded question answering over domain-specific documents, built with FastAPI, React, and Neo4j.