It looks like you’ve removed it all All the tutorials reference it, the Python function calling documentation example references something like it but it’s not there in API reference so it’s all very confusing for someone new.
The submit tool outputs to run section says " When a run has the status: "requires_action" and required_action.type is submit_tool_outputs , this endpoint can be used to submit the outputs from the tool calls once they’re all completed. All outputs must be submitted in a single request." but there’s no tool_calls field in the run object section. Same with chat completions API.
No, I mean like described here:
htt|||ps://platform.openai.com/docs/guides/function-calling
(remove |||, I cannot include links)
“For example, the model may call functions to get the weather in 3 different locations at the same time, which will result in a message with 3 function calls in the tool_calls array, each with an id . To respond to these function calls, add 3 new messages to the conversation, each containing the result of one function call, with a tool_call_id referencing the id from tool_calls .”
Or in these articles from other people:
htt|||ps://serpapi.com/blog/connect-openai-with-external-apis-with-function-calling/
htt|||ps://medium.com/@sivaneni1992/openai-apis-and-tools-calling-384e96d2867f
Oh, nevermind, my bad. I’ve finally found it in chat completion object under choices → message → tool_calls. You can’t find it by Ctrl-F since it’s hidden. Same thing with the run object: required_action → submit_tool_outputs → tool_calls.
All the tutorials reference it, the Python function calling documentation example references something like it but it’s not there in API reference so it’s all very confusing for someone new.