Senso
Sign inSign up

What are the four query modes?

A query returns a different shape depending on the mode you ask for:

  • content: matching document ids and titles, no text. Locate documents, then read them.
  • context: matching chunks, no generated answer. For when your agent writes the answer itself.
  • answer: matching chunks plus a grounded answer. The default, and right for most questions.
  • full: an answer grounded on whole documents rather than matched chunks. Best for "summarize the whole policy", and the slowest.
ModeEndpointWhat comes back
contentPOST /org/search/contentIds and titles. No text. Locate, then read.
contextPOST /org/search/contextMatching chunks. Feed your own model.
answerPOST /org/searchChunks plus a grounded answer and its sources.
fullPOST /org/search/fullAnswer grounded on whole documents. Slowest.
bash
curl -X POST https://apiv2.senso.ai/api/v1/org/search \
  -H "X-API-Key: $SENSO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "what is our refund window", "max_results": 5}'

Call it

POST/org/search/contentOpen in API reference →Matching source ids only.
POST/org/search/contextOpen in API reference →Raw chunks, no generated answer.
POST/org/searchOpen in API reference →Chunks plus a grounded answer.
POST/org/search/fullOpen in API reference →Grounded answer over whole documents.
MCP Server →