{
  "@context": "https://schema.org",
  "@type": "SoftwareApplication",
  "@id": "https://www.insightits.com/products/prismrag.html",
  "slug": "prismrag",
  "canonicalName": "PrismRAG",
  "name": "PrismRAG — Taxonomy-Controlled Graph RAG Library",
  "canonicalUrl": "https://www.insightits.com/products/prismrag.html",
  "knowledgeUrl": "https://www.insightits.com/catalog/prismrag.json",
  "markdownUrl": "https://www.insightits.com/catalog/prismrag.md",
  "family": "aiRetrieval",
  "infraFamily": "AI Retrieval",
  "recordType": "product",
  "status": "published",
  "parentProduct": null,
  "whatItIs": "Taxonomy-controlled Graph RAG library (PyPI: prismrag-patch). Client-defined word-to-category mapping, dual vectors, Louvain communities, BFS graph search, and auditable retrieval for pgvector, ChromaDB, Pinecone, and Weaviate.",
  "problem": "Flat top-k retrieval bleeds categories. Teams that own category rules need deterministic projection and graph search — not Microsoft GraphRAG-style document co-occurrence as the only control.",
  "isNot": [
    "Hosted SaaS (retired — use the Apache-2.0 library or self-host)",
    "A neutral cross-vendor accuracy or speed claim",
    "VectorPrism (intent-gated 1024d retrieval) or VectorBridge (migration)"
  ],
  "alternatives": [
    {
      "name": "Microsoft GraphRAG",
      "relationship": "Published comparison page: PrismRAG is a library with user-defined taxonomy; Microsoft GraphRAG is a document co-occurrence graph approach. No comparative accuracy claim.",
      "url": "https://www.insightits.com/compare/prismrag-vs-microsoft-graphrag.html"
    }
  ],
  "features": [
    {
      "name": "Tier-1 Rules Mapping",
      "description": "Auditable word→category assignment; 768-d semantic → 256-d personal projection. Same rules → same vectors every run."
    },
    {
      "name": "Graph RAG Search",
      "description": "Community seeding → BFS on your word graph → semantic re-rank. Direct fallback when the graph path runs dry."
    },
    {
      "name": "Louvain Communities",
      "description": "Automatic topic clusters with optional LLM labels. Bridge vectors link communities for cross-domain queries."
    }
  ],
  "architecture": "Tier-1 rules mapping (word→category) → 768-d semantic to 256-d personal projection → Louvain communities → BFS on the word graph with semantic re-rank → direct fallback when the graph path runs dry. MemoryStore for tests; PostgresStore for production.",
  "useCases": [
    "Healthcare, pharmacy, and finance taxonomies you own",
    "ChorusGraph RetrievalBackend over a customer database",
    "Teams that need the same mapping to produce the same vectors every run"
  ],
  "benchmarks": {
    "published": true,
    "summary": "The public evaluation is a repository test harness, not a neutral cross-vendor benchmark. No comparative accuracy or speed claim is made. Teams should evaluate retrieval quality on their own taxonomy, documents, embedding model, and false-positive budget.",
    "disclosures": [
      "The public evaluation is a repository test harness, not a neutral cross-vendor benchmark. No comparative accuracy or speed claim is made. Teams should evaluate retrieval quality on their own taxonomy, documents, embedding model, and false-positive budget."
    ],
    "urls": [
      "https://github.com/insightitsGit/prismrag/blob/main/tests/test_lib_step06_evaluation.py",
      "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/test_integration.py"
    ],
    "integrationCheck": {
      "testCount": 13,
      "source": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/test_integration.py",
      "runner": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/run_verification.py",
      "scope": "Package import, no-license operation, ingest, dual vectors, communities, search, category filtering, top-k, per-search latency under three seconds, append, quality reporting, and bridge creation when multiple communities exist.",
      "disclosure": "These are product-authored integration checks using the demo mapping. Runtime varies by environment; no fixed full-pipeline time is claimed."
    }
  },
  "github": "https://github.com/insightitsGit/prismrag",
  "pypi": "https://pypi.org/project/prismrag-patch/0.2.1/",
  "documentation": [
    {
      "title": "Taxonomy Graph RAG guide",
      "url": "https://www.insightits.com/guides/taxonomy-graph-rag.html"
    },
    {
      "title": "PrismRAG vs Microsoft GraphRAG",
      "url": "https://www.insightits.com/compare/prismrag-vs-microsoft-graphrag.html"
    },
    {
      "title": "Graph RAG tools",
      "url": "https://www.insightits.com/compare/graph-rag-tools.html"
    },
    {
      "title": "INFO.md",
      "url": "https://github.com/insightitsGit/prismrag/blob/main/INFO.md"
    },
    {
      "title": "Evaluation harness",
      "url": "https://github.com/insightitsGit/prismrag/blob/main/tests/test_lib_step06_evaluation.py"
    },
    {
      "title": "howItWorks",
      "url": "https://www.insightits.com/products/prismrag.html#what-is-prismrag"
    },
    {
      "title": "vsMicrosoft",
      "url": "https://www.insightits.com/products/prismrag.html#why-prismrag"
    },
    {
      "title": "pricing",
      "url": "https://www.insightits.com/products/choruscontrol.html#pricing"
    },
    {
      "title": "register",
      "url": "https://pypi.org/project/prismrag-patch/"
    },
    {
      "title": "libDocs",
      "url": "https://github.com/insightitsGit/prismrag/tree/main/docs"
    },
    {
      "title": "interactiveDemo",
      "url": "https://github.com/insightitsGit/prismrag/tree/main/examples/demo_app"
    },
    {
      "title": "demoAppReadme",
      "url": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/README.md"
    }
  ],
  "install": "pip install \"prismrag-patch[graph]\" (Apache-2.0, v0.2.1). No license key. Interactive demo: examples/demo_app.",
  "version": "0.2.1",
  "relatedProducts": [
    "chorusgraph",
    "python-libs",
    "vectorprism"
  ],
  "publisher": {
    "@type": "Organization",
    "name": "Insight IT Solutions",
    "legalName": "Insight IT Solutions LLC",
    "url": "https://www.insightits.com"
  }
}