ask_book
Search book content to find relevant passages with citations using natural language questions. Scope searches with concept IDs for precise results and log retrieval steps for consultation tracking.
Instructions
DEEP CONTEXT — RAG search against book sections. Embeds a natural language question and returns the most relevant book passages with full text, chapter, page numbers, and section title. ALWAYS scope with concept_ids from get_subgraph for precision. Returns suggested_questions derived deterministically from graph edges. Pass consultation_id to log retrieval steps.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Natural language question to search for in the book | |
| concept_ids | No | Optional: scope search to sections linked to these concept IDs | |
| max_passages | No | Maximum number of passages to return (default: 3) | |
| consultation_id | No | Optional consultation ID from match_concepts to log this step |