X.com Steve Reiner @stevereiner LinkedIn Steve Reiner LinkedIn Posts
Repost of my LinkedIn post from November 10, 2025 (original LinkedIn post)
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.