{
  "uid": "cogitave.learn.query-the-estate-with-cogitave-query",
  "kind": "module",
  "href": "/modules/query-the-estate-with-cogitave-query/",
  "title": "Query the estate with Cogitave Query",
  "summary": "Learn how Cogitave Query resolves a request against the canonical graph - lexical BM25 and dense HNSW vectors fused by Reciprocal Rank Fusion, a graph-aware rerank and ranking signals, and the bounded, read-only query_graph profile agents call directly.",
  "type": null,
  "products": [
    "cogitave-core"
  ],
  "roles": [
    "developer"
  ],
  "levels": [
    "intermediate"
  ],
  "subjects": [
    "software-engineering"
  ],
  "headings": [],
  "source": "By the end of this module, you'll be able to:\n- Explain why Cogitave Query fuses lexical, dense, and graph signals instead of relying on any one retriever alone.\n- Trace a query through the pipeline: BM25 recall, HNSW dense recall, Reciprocal Rank Fusion, and graph-aware rerank.\n- State why Reciprocal Rank Fusion was chosen over a weighted linear combination of retriever scores.\n- Read the bounded `query_graph` contract well enough to explain what makes it safe for an agent to call directly.\n",
  "units": [
    "cogitave.learn.query-the-estate-with-cogitave-query.introduction",
    "cogitave.learn.query-the-estate-with-cogitave-query.cogitave-query",
    "cogitave.learn.query-the-estate-with-cogitave-query.hybrid-retrieval",
    "cogitave.learn.query-the-estate-with-cogitave-query.knowledge-check",
    "cogitave.learn.query-the-estate-with-cogitave-query.summary"
  ],
  "durationInMinutes": 25,
  "badge": "cogitave.learn.query-the-estate-with-cogitave-query.badge",
  "partOf": "cogitave.learn.paths.build-on-core"
}