{
  "id": "knowledge-fabric-impl:llamaindex-rag-fabric",
  "_kind": "KnowledgeFabricImpl",
  "_file": "agent-stack/knowledge-fabric-impls/rag-framework-fabrics.yaml",
  "_cluster": "agent-stack",
  "attributes": {
    "displayName": "LlamaIndex as RAG Knowledge Fabric",
    "description": "LlamaIndex as a data-framework knowledge fabric. Provides data connectors\n(LlamaHub) for ingesting from 100+ sources, multiple index types\n(vector, list, tree, keyword, knowledge graph), query engines with\nresponse synthesis, and composable sub-question decomposition. LlamaIndex\nis purpose-built for connecting LLMs to data — turning unstructured\ndocuments into queryable knowledge with minimal configuration. The\nindex abstraction is its core differentiator from LangChain's chain-based\napproach.\n",
    "knowledgeFileFormats": [
      "any (via data connectors)"
    ],
    "retrievalStrategy": "hybrid",
    "knowledgePersistence": "delegated (via storage backends)",
    "knowledgeScopes": [
      "project",
      "organization",
      "enterprise"
    ],
    "autoExtractionSupport": false,
    "notes": "LlamaIndex's knowledge graph index is notable — it automatically extracts\nentity-relationship triples from documents and builds a queryable graph.\nThis enables relationship-aware retrieval that pure vector search cannot\nprovide. The composable index architecture allows building hierarchical\nknowledge fabrics where different index types handle different knowledge\ntypes (code vs. docs vs. decisions).\n"
  },
  "outgoingEdges": [
    {
      "from": "knowledge-fabric-impl:llamaindex-rag-fabric",
      "to": "layer:12-knowledge-fabric",
      "kind": "realizes",
      "attributes": {}
    },
    {
      "from": "knowledge-fabric-impl:llamaindex-rag-fabric",
      "to": "library:llama-index",
      "kind": "integrates_with",
      "attributes": {}
    }
  ],
  "incomingEdges": []
}