graph-rag-agent
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.
Discover GraphRAG Agent performance tuning options. Optimize throughput, latency, and resources via env vars for concurrency, batching, GDS settings, and caching.
How the Incremental Update Mechanism for Knowledge Graphs Works in graph-rag-agentLearn how the incremental update mechanism for knowledge graphs in graph-rag-agent efficiently detects and applies changes to your Neo4j graph without full rebuilds.
How to Configure the GraphRAG Agent System: Complete Setup GuideConfigure the GraphRAG Agent system easily. Follow this setup guide to clone the repo, install dependencies, set up Neo4j and LLM credentials, and run the application.
How to Start the Streamlit Frontend UI for Graph-RAG AgentStart the Streamlit frontend UI for your Graph-RAG Agent by running streamlit run frontend/app.py from the repository root. Access the web interface at http://localhost:8501.
How to Start the FastAPI Backend Service for the Graph-RAG AgentStart your FastAPI backend service for the Graph-RAG Agent by running uvicorn server main app --reload. Get your project running quickly and efficiently.
GraphRAG Agent Deployment: Complete Steps to Deploy the Services Locally or with DockerDeploy the GraphRAG Agent locally or with Docker. Follow our complete guide to clone the repo install dependencies configure environment variables and launch backend and frontend services.
How Caching is Implemented in GraphRAG Agent for Performance OptimizationDiscover how GraphRAG Agent optimizes performance with a dual-layer caching strategy, reducing LLM calls and transformer downloads for faster results.
The Role of Community Detection in GraphRAG Agent: Architecture and ImplementationDiscover how community detection in GraphRAG Agent clusters knowledge graphs for faster retrieval and richer context. Learn about its architecture and implementation.
How Deep Research Search Mode Functions in GraphRAG AgentUnderstand how the deep research search mode in GraphRAG Agent works. Explore its iterative think-search-reason loop for complex query answers using vector retrieval and Neo4j graph traversal.
What Is Hybrid Search in GraphRAG Agent: A Complete Technical GuideExplore hybrid search in GraphRAG Agent, a powerful retrieval strategy combining Cypher and vector similarity for detailed entity retrieval and broad contextual understanding. Learn how it works.
How Local Search Works in the GraphRAG Agent: Neo4j Vector Search and LLM IntegrationDiscover how local search in the GraphRAG Agent leverages Neo4j vector search and LLM integration with LangChain to retrieve and synthesize context from knowledge graphs for precise answers.
GraphRAG Agent Search Strategies: 8 Methods for Knowledge Graph RetrievalExplore 8 GraphRAG Agent search strategies including Local, Global, Hybrid, and Deep Research for efficient knowledge graph retrieval. Optimize your agent's knowledge access.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →