OptionalcontextControls the context snippets used to generate an answer.
OptionalfilterFilter the files used for retrieval by metadata, such as { category: 'returns' }.
OptionalincludeRequest highlighted passages from the source files that support the answer.
OptionaljsonRequest a JSON answer with Assistant.chat; unavailable for streaming.
The MessagesModel to send to the Assistant. Can be a list of strings or a list of objects. If sent as a list of
objects, must have exactly two keys: role and content. The role key can only be one of user or assistant.
OptionalmodelThe large language model to use for answer generation
OptionaltemperatureControls response variability where supported by the model. Lower values favor more consistent answers.
Messages and response settings for Assistant.chat and Assistant.chatStream.
Example