Flexible GraphRAG v0.6.3 released: It may be easier to setup now with the built docker images for the backend, react, vue, and angular frontends that can now be pulled from the Integrated Semantics docker.com hub: https://hub.docker.com/u/integratedsemantics
Configure a docker/docker.env (copy from docker/docker-env-sample.txt and change to scenario B full stack) for say neo4j/qdrant/elastic that overrides flexible-graphrag/.env (set openai key in .env) Enable app-stack.yaml and proxy.yaml lines in docker/docker-compose.yaml Use proxied addresses for the frontends ( localhost:8070/ui/react/ or /ui/vue/ or ui/angular/)
Flexible GraphRAG is an Apache 2.0 open source AI context platform supporting a document processing pipeline (Docling or LlamaParse), knowledge graph auto-building, ontologies, schemas, many LLM providers, GraphRAG and RAG, hybrid semantic search (fulltext, vector, property graph, RDF/SPARQL), AI query, and AI chat. The backend is Python. Angular, React, and Vue TypeScript frontends and an MCP server are included. The stack supports 13 data sources (9 with incremental auto-sync), 15 property graph databases, 4 RDF triple stores , 10 vector databases, OpenSearch / Elasticsearch / BM25 search, and Alfresco.
Flexible GraphRAG is an Apache 2.0 open source AI context platform supporting a document processing pipeline (Docling or LlamaParse), knowledge graph auto-building, ontologies, schemas, many LLM providers, GraphRAG and RAG, hybrid semantic search (fulltext, vector, property graph, RDF/SPARQL), AI query, and AI chat. The backend is Python. Angular, React, and Vue TypeScript frontends and an MCP server are included. The stack supports 13 data sources (9 with incremental auto-sync), 15 property graph databases, 4 RDF triple stores , 10 vector databases, OpenSearch / Elasticsearch / BM25 search, and Alfresco.
Goals for added Flexibility with Frameworks and Pipelines: 1. More Databases 2.a. Framework Independence (with adapter layer) 2.b. support both LangChain and LlamaIndex python application / agent developers (will need python apis not just current REST and MCP). 3. Flexible pipelines: custom python for stages and pipelines 4. Support OpenRAG or OpenRAG like with customizable visual Langflow flows for the pipeline and retrieval flows. 5. Support the CocoIndex rust pipeline and incremental engine as option to current flexible graphrag incremental update system (python/postgres). Also Flexible GraphRAG data sources and property graph, rdf, vector, search dbs could be used with CocoIndex as custom connectors (in addition native and other custom CocoIndex connectors). Flexible GraphRAG’s React, Vue, and Angular frontends would provide UI.
What's new: • Full LlamaIndex, LangChain or mixed pipeline: chunker, KG extractor, graph/vector/search backends, retrieval fusion — each independently configurable • 15 property graph DBs (8 LI stores + 8 LangChain matching versions + 6 LC-only + 1 new LI) All 15 can be used in a LlamaIndex or LangChain focused pipeline • 4 RDF stores — now includes Amazon Neptune RDF • 10 LangChain vector backends + 3 LangChain search backends duplicate LlamaIndex support • LangChain EnsembleRetriever (RRF) + text-to Cypher / GQL / SurrealQL / AQL / SPARQL graph QA • Docling OCR support (RapidOCR, EasyOCR, Tesseract, and more) • Incremental add/delete/modify across all graph, vector, search, and RDF backends (for both LlamaIndex and LangChain backend stores) • Integration testing: run_matrix and run_overnight can test all databases, LI / LC pipeline stages, all LLM providers, and all embedding providers
Flexible GraphRAG now has a zensical documentation web sitehttps://stevereiner.github.io/flexible-graphrag/ Flexible GraphRAG can create a Knowledge Context from a combination of Alfresco (Hyland) , SharePoint , Box , S3, GCS, Azure Blob sources. Incremental update auto syncs multiple databases (search, property graph, rdf graph, and vector) used for hybrid search / ai query /ai chat , and agents.
In 0.5.1, Flexible GraphRAG added LadybugDB support. Version 0.5.0 added RDF-based ontologies for both property graph dbs and RDF graph dbs (Graphwise, Ontotext GraphDB, Fuseki, Oxigraph), plus document ingestion with KG extraction, auto incremental change detection, and a search UI (hybrid search, AI query, AI chat) for RDF graph dbs in addition to previous property graph / vector / search db support.
Next version will expand flexible LangChain / LlamaIndex support: using everything in LlamaIndex, or LlamaIndex plus 6 additional LangChain new property graph databases, or everything in LangChain (graph, vector, search, llm).
Flexible GraphRAG v0.5.1 now supports LadybugDB and hybrid_system was modularized. In v0.5.0 , support for RDF-based ontologies for both property graph databases and RDF graph databases (Graphwise Ontotext GraphDB, Fuseki, and Oxigraph) was added. Also, document ingestion with KG extraction, auto incremental data source change detection, and search UI (hybrid search, AI query, and AI chat) are all supported with both database types. For RDF search, install with the additional LangChain option. Next version will be able to use everything in LlamaIndex, or LlamaIndex with 6 additional LangChain property graph databases, or everything in LangChain (graph,vector,search). Note: until GitHub support fixes an automated flag on my account, you need to login to GitHub to see my repos: flexible-graphrag: https://github.com/stevereiner/flexible-graphrag llama-index-ladybug: https://github.com/stevereiner/llama-index-ladybug
