Flexible GraphRAG v0.10.0: a new Graph tab in Flexible GraphRAG and KG Spaces

Flexible GraphRAG v0.10.0 was released on November 10, 2026. The main addition is a Graph tab that shows the knowledge graph behind your documents: the entities and relationships extracted from them. It’s in the Flexible GraphRAG React, Vue and Angular apps and in KG Spaces for Alfresco and Nuxeo.

Left: KG Spaces for Nuxeo, Graph tab for the “acme” folder (68 nodes, 159 relationships, in Neo4j). Right: KG Spaces for Alfresco ACA with a document selected and its context menu: Add to KG Spaces, Ask KG Spaces about this document, and View KG Spaces graph of this document.

The Graph tab

The Graph tab shows the entities and relationships extracted from:

  • an ingest: Show graph on Processing tab jobs and rows
  • Hybrid Search results
  • AI Query sources and AI Chat sources
  • a selected document or folder in KG Spaces

Each entity type gets its own colour. The side panel lists entity types and relationship types with counts, and you can switch each one on or off. Chunk nodes are optional. Click a node or relationship to see its details, double-click a node to expand its neighbours, and export the graph. Only documents the user may read are shown.

The graph comes from ingest: a document has one once it has been ingested with Graph checked. A document that hasn’t been ingested yet, or was ingested for search and vector only (Graph unchecked), has no graph to show. Whether RDF was checked doesn’t matter.

Where it is

  • The Flexible GraphRAG apps: React, Vue and Angular
  • KG Spaces for Alfresco ACA (Angular): select a document or folder and choose View KG Spaces graph of this document from the context menu. The three KG Spaces actions (Add to KG Spaces, Ask KG Spaces about this document, View KG Spaces graph) are also on the graph icon in the ACA toolbar.
  • KG Spaces for Nuxeo (Angular), which works with Nuxeo Web UI. The Nuxeo Web UI customization has the same three actions on its KG Spaces toolbar button:

The KG Spaces toolbar button in Nuxeo Web UI: Add to KG Spaces, Ask KG Spaces about this document, and View KG Spaces graph of this document.

The graph view is a shared Cytoscape.js component, published on npm as @flexible-graphrag/graph-view.

All 15 property graphs

The Graph tab works with all 15 property graph databases Flexible GraphRAG supports:

Neo4j, ArcadeDB, FalkorDB, LadybugDB, Memgraph, NebulaGraph, Amazon Neptune, Neptune Analytics, Google Cloud Spanner, ArangoDB, Apache AGE, Cosmos Gremlin, HugeGraph, SurrealDB and TigerGraph.

It reads the property graph; RDF stores aren’t shown in the Graph tab.

Also in v0.10.0

  • Google Cloud Spanner Graph with LangChain (GRAPH_BACKEND=langchain), where it was LlamaIndex only before.
  • Ollama models stay on the GPU. LlamaIndex was sending each model’s maximum context with every request (up to 128k), which made Ollama reserve far more memory than needed and spill models onto the CPU, so calls took minutes. The new OLLAMA_CONTEXT_WINDOW setting (default 8192) is now sent by both the LlamaIndex and LangChain Ollama clients. After the first query, ollama ps should show the model at 100% GPU. See Ollama configuration.
  • Better search results: weak matches are dropped and scores rescaled (SEARCH_MIN_RELATIVE_SCORE, VECTOR_MIN_RELATIVE_SIMILARITY), plus a SEARCH_ANALYZER setting for Elasticsearch / OpenSearch.
  • Graph fixes: a document’s graph now includes relationships shared with other documents, and deleting or re-syncing a document keeps the entities and relationships other documents still use, in both property graphs and RDF stores.

v0.9.1 (November 3, 2026)

  • OpenArch in the Flexible GraphRAG Docker Compose stack (docker/includes/openarch.yaml), not just in the KG Spaces deployment.
  • Faster KG extraction by raising KG_EXTRACTION_WORKERS: the default of 4 suits local LLMs like Ollama; use 8-16 with cloud LLMs like OpenAI.
  • Security fixes (see SECURITY.md): REST and MCP filesystem ingest only reads paths under uploads/, SOURCE_PATHS or the new INGEST_ALLOWED_PATHS; query injection fixed in the Memgraph, Apache AGE, ArcadeDB, Ladybug, Gremlin / Cosmos DB and NebulaGraph adapters and the RDF converter; and graph Q&A now runs only read queries, so a question can’t get the LLM to change or delete graph data.
  • Preparatory work for Python 3.15 and free-threaded 3.15t.

About Flexible GraphRAG and KG Spaces

Flexible GraphRAG is an Apache 2.0 open source AI context platform: document processing (Docling, LlamaParse or LiteParse), knowledge graph auto-building, ontologies, GraphRAG and RAG, hybrid search (fulltext, vector, property graph, RDF/SPARQL), AI query and AI chat. It supports 14 data sources (10 with incremental auto-sync), 15 property graphs, 4 RDF stores, 10 vector stores and OpenSearch / Elasticsearch / BM25 search. The backend is Python with both LlamaIndex and LangChain; the frontends are React, Vue and Angular, and there’s an MCP server. All databases and dashboards can be run with the provided Docker Compose setup.

KG Spaces brings Flexible GraphRAG into content management apps: KG Spaces for Alfresco ACA is an Apache 2.0 Alfresco Content App extension, and KG Spaces for Nuxeo is a Nuxeo Web UI add-on plus an Angular app sharing the Web UI session. Both are built on the shared @flexible-graphrag/angular-ui library and work with the user’s own repository permissions.

Links

Video: KG Spaces for Alfresco (ACA) and KG Spaces for Nuxeo, based on Flexible GraphRAG v0.9.0

Flexible GraphRAG on GitHub

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

Repost of my LinkedIn post from October 28, 2026 (original LinkedIn post)

YouTube video of KG Spaces for Alfresco (ACA) and KG Spaces for Nuxeo, both based on Flexible GraphRAG v0.9.0, which now supports Hyland OpenArch (all are Apache 2.0 open source). KG Spaces Deployment uses docker compose to deploy the whole stack (KG Spaces apps, Flexible GraphRAG, OpenArch and Alfresco and/or Nuxeo)
Recorded in HD: to read the UI, set the YouTube player’s quality to 1024p HD with the ⚙ Settings → Quality menu.
https://youtu.be/1DV1_QwGz74

Flexible GraphRAG v0.9.0 and KG Spaces v0.9.0 released, with support for Hyland OpenArch

Flexible GraphRAG on GitHub

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

Repost of my LinkedIn post from October 27, 2026 (original LinkedIn post)

Flexible GraphRAG v0.9.0 and KG Spaces v0.9.0 are released, with support for Hyland OpenArch.

Hyland OpenArch federates unstructured, AI-ready data from all sources across an organization and makes it available to AI services and agents while always respecting permissions. GitHub: https://github.com/Hyland/OpenArch

In OpenArch mode, OpenArch is the search, vector, and document state store. Flexible GraphRAG sends it parsed text from its doc processors (Docling, LlamaParse, LiteParse) plus embedding chunks, and keeps building knowledge graphs into any of 15 property graph databases and/or 4 RDF stores. Search and AI query fuse graph and RDF results with OpenArch search and vector results.

All 14 data sources work with OpenArch, 10 with incremental auto-sync:
Auto-sync: Alfresco, Nuxeo, SharePoint, OneDrive, Box, Google Drive, Amazon S3, Google Cloud Storage, Azure Blob Storage, Filesystem
Without: CMIS, Web Pages, Wikipedia, YouTube

Builds on the 0.8.x permission work: per-source sign-in/sign-out, results filtered to what each user can see (UI and MCP), and filter pills to pick which sources feed hybrid search and AI chat. v0.9.0 adds separate Graph and RDF columns to the Processing table for per-file/folder options.

The projects

🔹 Flexible GraphRAG: Python backend, doc processing, KG building, ontologies, RAG/GraphRAG, Angular/React/Vue UIs, MCP server
GitHub: https://github.com/stevereiner/flexible-graphrag

🔹 python-openarch-api: Python client for OpenArch’s REST API
GitHub: https://github.com/stevereiner/python-openarch-api

🔹 KG Spaces for Alfresco ACA: “Add to KG Spaces” (ingest, or manage search+vector, graph, RDF, auto-sync) and “Ask KG Spaces about this folder or document”
GitHub: https://github.com/stevereiner/kg-spaces-aca

🔹 KG Spaces for Nuxeo (new): runs in its own tab; the Add/Ask menus in Nuxeo Web UI switch to it, and view links switch back
GitHub: https://github.com/stevereiner/kg-spaces-nuxeo

🔹 KG Spaces Deployment: one Docker Compose with Alfresco, Nuxeo, Hyland OpenArch, Flexible GraphRAG and both KG Spaces UIs; pick your graph DB and/or RDF store
GitHub: https://github.com/stevereiner/kg-spaces-deployment

📸 The image: KG Spaces landing page, Nuxeo Web UI with Add to KG Spaces, KG Spaces for Nuxeo AI query, and KG Spaces for ACA AI chat, with search filter pills from ingesting all 14 sources.

Graph databases as the node store for content repositories: three new open source projects

Flexible GraphRAG on GitHub

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

Repost of my LinkedIn post from October 16, 2026 (original LinkedIn post)

Graph databases as the node store for content repositories: three new open source projects:
Now available: three Apache 2.0 Java projects that keep a content repositories’ whole tree (documents, folders, metadata, versions, permissions) in Neo4j or ArcadeDB instead of MongoDB or SQL. The platform and its APIs are unchanged, and every write still goes through the repository.

🔹 nuxeo-graph-storage: Nuxeo LTS 2025 with its document and folder nodes in Neo4j or ArcadeDB. Both run Nuxeo‘s own core repository tests, and the Nuxeo Web UI works with either. https://github.com/stevereiner/nuxeo-graph-storage

🔹 oak-graph-store: Apache Jackrabbit Oak DocumentStores for Neo4j and ArcadeDB, replacing the MongoDB and RDB stores. Apache Sling and Composum Tools run with the whole repository in the graph.
oak-graph-store: https://github.com/stevereiner/oak-graph-store

🔹 openarch-graph-storage: Hyland OpenArch federates AI-ready data from sources across the organization and makes it available to AI services and agents while respecting permissions. OpenArch kept Nuxeo‘s pluggable node storage, so this stores its nodes in Neo4j or ArcadeDB.
openarch-graph-storage: https://github.com/stevereiner/openarch-graph-storage
Hyland OpenArch: https://github.com/Hyland/OpenArch

Why a graph?
• Better modeling: business entities (products, contracts, suppliers) and their relations as typed nodes and edges, not only files.
• Impact and dependency questions, many hops deep, become direct traversals.
• Context graph support: the content tree and the knowledge graphs built from it in one database, entities linked to their source documents.
• AI agents get context and provenance from the graph; the repository still enforces what they may see and do.

What's next
Starting: Flexible GraphRAG and KG Spaces ACA with OpenArch, regular or with openarch-graph-storage. Either way, Flexible GraphRAG can build the knowledge graph in a property graph database (any of 15), an RDF store (any of 4), or both; with graph storage, most likely the same Neo4j or ArcadeDB as the content, plus optional RDF. Flexible GraphRAG‘s Turtle Ontologies work with both property graphs and RDF stores.
Flexible GraphRAG: https://github.com/stevereiner/flexible-graphrag
KG Spaces ACA: https://github.com/stevereiner/kg-spaces-aca

All three node storage projects are prototypes. Feedback welcome.

Flexible GraphRAG v0.8.4 and KG Spaces v0.8.4 for the Alfresco Content App (ACA)

Flexible GraphRAG on GitHub

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

Repost of my LinkedIn post from October 12, 2026 (original LinkedIn post)

Flexible GraphRAG v0.8.4 and KG Spaces (v0.8.4) for Alfresco Content App (ACA)

📸 KG Spaces Processing Tab Each row now has Search+Vector, Graphs and Auto Sync checkbox columns instead of single settings.
• You can use these when ingesting, and later to manage settings: turn vector + search indexing on or off, auto-built graphs (property and/or RDF) on or off, and auto sync on or off, per document, per folder, or for all.
• On documents or folders that are already processed, unchecking Search+Vector and/or Graphs removes them (checking adds them) when you click Start Processing.
• New Run in background checkbox
• New user Jobs tab: shows the users document ingests, index / graph adds and removals, and when an auto sync occurs.

🔗 Answers you can trace: Hybrid search results (vector, search, graph, and RDF) and AI query / AI chat answers now name the source documents they came from, as links:
• Alfresco documents open in the ACA viewer over their folder (or in Share)
• Nuxeo documents open in the Nuxeo Web UI
• Web pages and Wikipedia open at their URL
• YouTube opens at the time of the transcript segment

🤖 Source links from the MCP server too The Flexible GraphRAG MCP server returns the same style source links: Alfresco documents to view in ACA, Nuxeo in its Web UI, and links for web page, Wikipedia and YouTube sources. Use search_documents tool for hybrid search and query_documents tool for AI query.

🔐 Permission-aware answers: Hybrid search, AI query and AI chat return results only from documents the signed-in Alfresco user may read.

💬 New in KG Spaces
• Ask KG Spaces about this document / folder menu, then keep asking with this context in AI chat
• Closing ACAs viewer from source links returns you to your hybrid search results, AI query, or AI chat

Also: ArcadeDB moves to 26.10.1.

Flexible GraphRAG GitHub: https://github.com/stevereiner/flexible-graphrag
KG Spaces for ACA GitHub: https://github.com/stevereiner/kg-spaces-aca