GraphRAG-SDK and kg-rag
About GraphRAG-SDK
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
Combines knowledge graphs, ontology extraction, and LLM inference via LiteLLM to enable GraphRAG workflows—automatically structuring unstructured data into queryable graphs stored in FalkorDB. Supports multi-vendor LLM deployment (OpenAI, Google, Azure, Ollama) and provides both ontology auto-detection from sources and chat-based query interfaces for knowledge graph traversal and augmented generation.
About kg-rag
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.
Implements multiple retrieval strategies including entity-based embedding matching with beam search, Cypher queries against Neo4j, and hierarchical community detection (GraphRAG-style), enabling direct comparison of knowledge graph approaches versus traditional vector similarity and chain-of-thought baselines. Built as a modular Python package with Chroma vector stores, OpenAI LLM integration, and comprehensive evaluation pipelines including hyperparameter search across methods.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work