Skip to main content

Hybrid Retrieval

Clinical Corvus uses hybrid retrieval to support evidence-backed answers: it combines keyword matching (fast, exact) with semantic retrieval (concept-aware) to improve recall and precision on real clinical queries.

The End-to-End Flow​

  1. Ingestion: documents (guidelines, PDFs, curated references) are parsed and converted into structured text.
  2. Chunking & metadata: content is split into coherent sections with basic tags (e.g., guideline vs narrative).
  3. Indexing: content is stored in:
    • a keyword index for exact matching,
    • a vector index for semantic similarity.
  4. Hybrid search: both retrieval modes are run and merged into a single ranked list.
  5. Context packaging: the top evidence is formatted into a traceable context pack.
  6. Cited synthesis: the answer is generated with citations tied to the retrieved snippets.

Why Hybrid Beats “Vector Only”​

  • Keyword search is often better for exact terms (drug names, lab thresholds, acronyms).
  • Semantic search is often better for conceptual questions (syndromes, management strategies).
  • Clinical questions frequently require both.

Conceptual Diagram​