flexible-graphrag
Active·★ 194·Apache-2.0·Updated 2026-10-21
Flexible GraphRAG is an open-source platform that integrates document processing, automated knowledge graph construction, and hybrid search (full-text, vector, graph) with AI query and chat capabilities. It supports 13 data sources, multiple vector and graph databases, and offers automatic incremental updates to keep data synchronized in real-time.
#GraphRAG#Knowledge Graph#Hybrid Search#LLM#Document Processing#FastAPI#Docker#Data Ingestion
01
Features
01Configurable Hybrid Search (vector, full-text, graph)
02Automated Knowledge Graph Construction for GraphRAG
03Multi-Source Document Ingestion from 13 different data sources
04Automatic Incremental Updates for real-time data synchronization
05Flexible and modular Docker deployment with multiple UI clients (Angular, React, Vue)
02
Compatibility
Python
Runtime
Verified via docs
Docker
Deployment
Verified via docs
FastAPI
Backend Framework
Verified via docs
LlamaIndex
RAG Framework
Verified via docs
Angular, React, Vue
UI Frameworks
Verified via docs
Vector Databases (e.g., Qdrant, Milvus, PostgreSQL, Neo4j, Elasticsearch)
Vector Databases
Verified via docs
03
Quick start
1
$ cd flexible-graphrag
2
$ cp env-sample.txt .env
3
$ cd ..
4
$ cd docker
5
$ cp docker-env-sample.txt docker.env
6
$ docker-compose -f docker-compose.yaml -p flexible-graphrag up -d
04
Use cases
↳Advanced Information Retrieval and Q&A over diverse document sets
↳Automated Knowledge Management and Graph-powered insights from unstructured data
↳Real-time Synchronization of Knowledge Bases with frequently updating data sources
↳Building Conversational AI and Chatbots that can interact with enterprise content
↳Unified Document Processing and Search across cloud storage and enterprise repositories
05
Alternatives
wa_llm★ 170
A WhatsApp bot that can participate in group conversations, powered by AI. The bot monitors group messages and responds when mentioned.
sparql-llm★ 130
🦜✨ Chat system, MCP server, and reusable components to improve LLMs capabilities when generating SPARQL queries
mykg★ 77
Knowledge graph extractor: Markdown (or any format) → knowledge graph with RDFS/OWL ontology
Vault-for-LLM★ 50
🧠 Local-first knowledge system for LLM agents — sqlite-vec + ONNX embeddings, no cloud/Docker/PyTorch dependency
Comments
Log in to leave a comment
No comments yet. Be the first!