[WARN] Model request timed out (timeout 767.68ms)
We are seeing all our calls from this morning, for each turn are getting '[WARN] Model request timed out' .
This is happening after each function call, including 'light' function calls which return very little data/text back to the model'
I've tried using gpt-4o and gpt-4-turbo and gpt-3.5-turbo, with and without our own OpenAI key.
Is there a way to increase the model timeout?
This is happening after each function call, including 'light' function calls which return very little data/text back to the model'
I've tried using gpt-4o and gpt-4-turbo and gpt-3.5-turbo, with and without our own OpenAI key.
Is there a way to increase the model timeout?
