NEW! Flexible GraphRAG supports automatic incremental updates (Optional) from most data sources, keeping your Vector, Search and Graph databases synchronized in real-time or near real-time.

New! - KG Spaces Integration of Flexible GraphRAG in Alfresco ACA Client

Flexible GraphRAG

Flexible GraphRAG is an open source platform supporting document processing (Docling or LlamaParse), knowledge graph auto-building, schemas, LlamaIndex LLMs, RAG and GraphRAG setup, hybrid search (fulltext, vector, graph), AI query, and AI chat capabilities. The backend uses Python, LlamaIndex, and FastAPI. Has Angular, React, and Vue TypeScript frontends. A MCP Server is also available. Currently supports 13 data sources, 10 vector databases, OpenSearch / Elasticsearch search, 8 graph databases, and Alfresco. These servers and their dashboards can be configured in a provided docker compose.

Features

• Hybrid Search: A configurable hybrid search system that combines vector search, full-text search, and graph GraphRAG
• Knowledge Graph GraphRAG: Extracts entities and relationships from documents to auto create graphs in graph databases for GraphRAG. Configuration for schemas to use or use as a starting point for LLM to expand on is supported.
• Configurable Architecture: LlamaIndex provides abstractions for allowing multiple vector databases, graph databases, search engines, and LLM providers to be supported