ChatCompletionMessag is returning content=None when finish_reason='stop'

API
1

I am using 1106 gpt-35-turbo.
It is returning usage=CompletionUsage(completion_tokens=205, prompt_tokens=2261, total_tokens=2466) but the content is None

1 Like
2

could you check content_filter_result?

Seems like other folks have a similar issue too

3

For me this is the response : [Choice(finish_reason=‘stop’, index=0, message=ChatCompletionMessage(content=None, role=‘assistant’, function_call=None, tool_calls=None), content_filter_results={})], created=1704130, model=‘gpt-35-turbo’, object=‘chat.completion’, system_fingerprint=None, usage=CompletionUsage(completion_tokens=218, prompt_tokens=1715, total_tokens=1933), prompt_filter_results=[{‘prompt_index’: 0, ‘content_filter_results’: {‘hate’: {‘filtered’: False, ‘severity’: ‘safe’}, ‘self_harm’: {‘filtered’: False, ‘severity’: ‘safe’}, ‘sexual’: {‘filtered’: False, ‘severity’: ‘safe’}, ‘violence’: {‘filtered’: False, ‘severity’: ‘safe’}}}])

4

Is the issue still persisting?

If so, could be a prompt issue that’s triggering a possible bug