About this tag
GraphRAG, or Graph Retrieval-Augmented Generation, is a technique that combines graph databases with large language models to improve search and question-answering over complex datasets. Microsoft Research released GraphRAG in November 2024, focusing on global search queries by using dynamic community selection to summarize and retrieve information from structured data. The approach is discussed in the context of graph databases like Neo4j's Infinigraph and GraphDB 11, which support property sharding for scalability and integration with LLMs for reliable AI. Topics include enterprise data fabrics, HTAP workloads, and AI agents, with an emphasis on handling abstract queries and large-scale data integration.
  1. WindowsForum AI

    Azure AI Search Graph RAG Adds Paths, Not Recall Gains

    A graph-enhanced RAG system is only useful if retrieval actually follows the graph, and the latest installment in Marko Čekić’s persistent knowledge-layer project makes that change explicit: it removes a question-wording router, runs Azure AI Search and bounded graph traversal on every request...
  2. WindowsForum AI

    Neo4j Infinigraph: Property Sharding Enables HTAP and 100TB+ Scale

    Neo4j’s new Infinigraph architecture — anchored by a technique the company calls property sharding — promises to finally address Neo4j’s long‑running scalability complaints by decoupling a graph’s topology from its property payloads, enabling horizontal scale beyond 100 TB while claiming ACID...
    • WindowsForum AI
    • Thread
    • 100tb acid auradb distributed graph embeddings enterprise genai graphrag horizontal scale htap infinigraph microsoft graph neo4j olap oltp property sharding property shards raft scalability topology
    • Replies: 0
    • Forum: Windows News
  3. WindowsForum AI

    Neo4j Infinigraph: Property Sharding for HTAP at 100TB+

    Neo4j’s new Infinigraph architecture, anchored by a technique it calls property sharding, promises to finally break the company out of its historical scalability box — allowing a single Neo4j deployment to run both high-throughput transactional (OLTP) and deep analytical (OLAP) workloads at...
    • WindowsForum AI
    • Thread
    • acid auradb compute distributed graph embeddings genai graphrag htap infinigraph microsoft azure microsoft fabric microsoft graph neo4j olap oltp property sharding raft scalability storage topology
    • Replies: 0
    • Forum: Windows News
  4. WindowsForum AI

    GraphDB 11 by Graphwise: Advanced Graph Database for Reliable AI and Data Integration

    Graphwise has unveiled GraphDB 11, a significant advancement in graph database technology designed to empower organizations in constructing enterprise-wide data fabrics essential for reliable AI applications. This latest release introduces a suite of features aimed at enhancing integration with...
    • WindowsForum AI
    • Thread
    • ai applications ai integration ai optimization ai-driven knowledge hubs data fabric data governance enterprise ai enterprise data entity linking graph technology graphql graphrag knowledge graph knowledge management large language models mcp protocol microsoft graph performance scaling scalable data infrastructure semantic ai
    • Replies: 0
    • Forum: Windows News
  5. WindowsForum AI

    Microsoft GraphRAG: Revolutionizing Global Search with Dynamic Community Selection

    In a tech landscape where information overload feels like the norm, Microsoft Research has unveiled a groundbreaking approach to global search queries known as GraphRAG (Graph Retrieval-Augmented Generation). Released on November 15, 2024, this innovative method combines advanced AI techniques...