Objects

AnswerResponse

The assistant's answer (POST /v1/ask, POST /v1/chat without streaming, and the done event of the stream). There are several forms: a regular answer; “no documents” (empty: no_hits, without provenance); a refusal on a restricted topic (empty: restricted with restricted); and a guardrail refusal (empty: guardrail with guardrail, where the text is the organization's standard refusal message). A cached answer has cached: true and cache_hit (an exact repeat or an answer to a similar question). An answer based only on verified cards (VERIFIED_ONLY) has verified_only: true.

Fields

answerstringrequired
question_idintegerrequired
querystring
collectionstringrequired
sourcesarray of Sourcerequired
table_queriesarray of TableQueryrequired
datasetsarray of Datasetrequired
chartsarray of ChartSpecrequired
warningsarray of AnswerWarningrequired
timingsTimingsrequired
provenancearray of NumberProvenance
emptystring
Allowed values: no_hitsrestrictedguardrailno_data_for_period
basisAnswerBasis
verificationAnswerVerification
alt_periodsarray of AnswerAltPeriod
items ≤ 6
drilldownarray of AnswerDrilldown
items ≤ 20
restrictedRestrictedInfo
guardrailGuardrailVerdict
verified_onlyboolean
cachedboolean
cache_hitAnswerCacheHit
out_of_scopeAnswerOutOfScope
attachmentsarray of Attachment
export_errorstring
toolsstring | null
Why tools were used for this answer: request (asked for explicitly); compare, compute, action (based on the question); needs_calc (a calculation over tables is needed); summary (an overview of a collection or documents); mcp (the organization has connected external MCP servers).
Allowed values: requestcomparecomputeactionneeds_calcsummarymcpnull
tool_callsarray of ToolCallInfo
calculationsarray of Calculation
pending_actionsarray of PendingAction
entitiesarray of AnswerEntityrequired
followupsarray of Followuprequired
conversation_idstring
Only for POST /v1/chat with a conversation.
answer_idstring
ID of the answer object.

Used by

Part of

ChatDone