Semantic Search
Searches a knowledge base and returns ranked chunks.
The knowledge base is identified by knowledge_base_id in the body rather than in the path. Results are ranked purely on similarity.
Only material whose ingestion has reached ‘completed’ is searchable. If a recently uploaded document does not appear, check its status before assuming a ranking problem, and use the document chunks endpoint to see what was actually indexed.
Body
Request body for semantic search.
The text to search for.
The knowledge base to search. Note that this travels in the body, not the path.
Maximum number of chunks to return, ranked by similarity.
1 <= x <= 100Optional metadata filter, passed straight through to the vector backend. Omit it entirely unless you are genuinely filtering: whatever you send becomes a real metadata condition, so leaving an interactive-playground placeholder such as {"additionalProp1": {}} in place will make the search error or silently return nothing. Knowledge-base scoping is applied automatically either way and cannot be bypassed through this field. Only the $eq operator is portable across the supported backends. For example, to match only chunks tagged with a given department, send {"department": {"$eq": "billing"}}.

