"tool_choice" = "any"
)
mode or mixed mode ("auto" = "any"
). The format is fully compatible with OpenAI streaming.
stream=true
when
calling the chat completions api. This returns an object that streams
the response as data-only server-sent events.
To extract chunks,
use the delta field instead of the message field.
Specifically, the streaming mode of tool use will guarantee to have the function name return as a
single chunk then streaming the arguments. (See the code example)