Category: Azure Blob Storage

Big News: Flexible GraphRAG now supports Incremental Update Auto Sync from Data Sources

Flexible GraphRAG on GitHub

X.com Steve Reiner @stevereiner  LinkedIn Steve Reiner LinkedIn Posts

Repost of my LinkedIn post from February 6, 2026 (original LinkedIn post)

Flexible GraphRAG incremental update auto sync: Postgres document state, Sources and Processing tabs, and the Neo4j knowledge graph

Big News: Flexible GraphRAG now supports Incremental Update Auto Sync from Data Sources
Huge New Feature: Flexible GraphRAG check-in: Added Incremental Update Auto Sync from 9 data sources to all supported vector, search, and graph databases. Added Postgres state management.
🌟 Github: https://github.com/stevereiner/flexible-graphrag

• All auto syncing data sources working: S3 (SQS events), Hyland Alfresco (ActiveMQ events), Azure Blob, GCS (Pub/Sub), Google Drive, Box, OneDrive, SharePoint, Filesystem (watchdog).

• All 10 vector databases working with this (Qdrant, LanceDB, Elastic, OpenSearch Project, Chroma, Milvus, created by Zilliz, Weaviate, Pinecone, PostgreSQL pgvector, Neo4j)

• All 3 full text search engines working with this (Elasticsearch, OpenSearch, built-in LlamaIndex BM25)

• Graph databases working with this: Neo4j, FalkorDB, ArcadeDB (fix to delete coming), MemGraph. More testing needed with Kuzu, NebulaGraph, Amazon Neptunes.

Flexible GraphRAG or Flexible RAG, an Apache 2.0 open source Python platform, uses LlamaIndex , supports 8 graph databases, 10 vector databases, 3 search engines, and 13 data sources (9 auto-sync) Also supports knowledge graph auto-building, schemas, 9 LlamaIndex LLMs, Docling or LlamaParse doc processing, GraphRAG mode, RAG only mode, Hybrid search, AI query, AI chat. Has React, Vue, and Angular TypeScript frontends, a FastAPI backend, and a REST API. Also has a FastMCP MCP server. Has a convenient docker compose that can include any of the databases (Vector, Graph, Search, Alfresco) and Dashboards / Consoles.
Blog: https://integratedsemantics.org/
X.com: https://x.com/stevereiner

Flexible GraphRAG and RAG: LlamaParse from LlamaIndex and Docling now both working for doc processing with Box, Google Drive, GCS, Azure Blob, S3

Flexible GraphRAG on GitHub

X.com Steve Reiner @stevereiner  LinkedIn Steve Reiner LinkedIn Posts

Repost of my LinkedIn post from November 10, 2025 (original LinkedIn post)

Flexible GraphRAG React UI Sources tab with the data source dropdown: File Upload, Alfresco, CMIS, Web Page, Wikipedia, YouTube, Google Drive, OneDrive, S3, Azure Blob, GCS, Box, SharePoint
Sources tab: choose from the data sources (web, cloud storage, enterprise)
Flexible GraphRAG Processing tab: two documents ingested into the vector index, knowledge graph and Elasticsearch
Processing tab: documents ingested into the vector index, knowledge graph, and Elasticsearch
Flexible GraphRAG AI chat answering questions about Hyland content management platforms, next to the auto-built knowledge graph in Neo4j Browser
AI chat answering from the auto-built knowledge graph, shown in Neo4j Browser

Flexible GraphRAG and RAG checkin: LlamaParse from LlamaIndex
and Docling now both working for doc processing with Box, Google Drive, GCS, Azure Blob, S3, File Upload, Hyland Alfresco, and CMIS data sources.
Please 🌟 Star the GitHub repo
https://github.com/stevereiner/flexible-graphrag

1. LlamaParse added as an additional configurable doc processing choice beyond Docling (default).
2. Newly working Box, Google Drive, GCS, Azure Blob Storage data sources work with both Docling and LlamaParse.
3. Previous data sources that worked with Docling now also working with LlamaParse: File Upload, Hyland Alfresco, CMIS, S3
4. Currently working to get SharePoint and OneDrive for Business to test.
5. The web data sources (Web Pages, Wikipedia, YouTube) don’t use document processing

Flexible GraphRAG or Flexible RAG, an Apache 2.0 open source python platform, uses LlamaIndex, supports 8 graph databases, 10 vector databases, 3 search engines, and 13 data sources, Also supports knowledge graph auto-building, schemas, LlamaIndex LLMs, Docling and LlamaParse doc processing, GraphRAG mode, RAG only mode, Hybrid search, and AI query / chat. Has React, Vue, and Angular frontends, and a FastAPI backend. React, Vue, Angular, Backend work on Windows, Mac, Linux (standalone or in docker). Also has a FastMCP MCP server. Has a convenient docker compose that can include any of the databases (Vector, Graph, Search, Alfresco) and Dashboards / Consoles.