CogitaveLearn

Query the estate with Cogitave Query

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.

Units5
Duration25 min
Levelintermediate

By the end of this module, you'll be able to:

  • Explain why Cogitave Query fuses lexical, dense, and graph signals instead of relying on any one retriever alone.
  • Trace a query through the pipeline: BM25 recall, HNSW dense recall, Reciprocal Rank Fusion, and graph-aware rerank.
  • State why Reciprocal Rank Fusion was chosen over a weighted linear combination of retriever scores.
  • Read the bounded query_graph contract well enough to explain what makes it safe for an agent to call directly.

Units

  1. 01Introduction4 min
  2. 02How Cogitave Query resolves a request7 min
  3. 03Why hybrid retrieval, and what the graph adds7 min
  4. 04Knowledge check4 min
  5. 05Summary3 min