Typed answers and metadata returned from one classification request.
Read every answer from answers, or use nouls, choices, scores, and
boxes for views filtered by answer type. Each map preserves the question
IDs supplied in ClassifierRequest.questions. The views are non-enumerable
so they are not duplicated into traces or JSON.stringify output.
Q is the questions map that was asked. When it is known, answers and views
are typed per question ID, and a Choice answer's choice is one of its
labels.
interface ClassifierResponseAll answers keyed by their original question IDs.
Localization answers keyed by their original question IDs.
Categorical answers keyed by their original question IDs.
Model that answered the request.
Binary answers keyed by their original question IDs.
Provider request ID, useful when diagnosing a request with provider support.
Ordinal answers keyed by their original question IDs.
Token usage reported for the request, if any. A missing count is treated
as 0, and total_tokens defaults to their sum.