Gpt-4o vision extremaly long response time

API Bugs
,
1

Hi,

I’m using GPT-4.0 to extract text from images. For the past two hours, after calling the OpenAI API, I either don’t get any response or receive a weird one after few minutes. It was working perfectly all day today.

Does anyone else have the same problem?

2

Welcome to the community!

There seemed to be a server issue yesterday (Extremely long request times- Completions API gpt-4o) but it sounds like you might be experiencing something different.

Can you give us an example of one of these weird responses?

1 Like
3

sure, for example:
“Instructor Raw Response: ChatCompletion(id=‘chatcmpl-AbO2gNQsA78RN2RaoPGZ97t2fzzii’, choices=[Choice(finish_reason=‘length’, index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role=‘assistant’, audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id=‘call_KklWmLsraL2ITbw6KeqWxdn9’, function=Function(arguments='{"textFromImage":"ISTQB Certified QA Engineer\\nCracow, Poland \u2022 \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa \u25aa ', name=‘TextFromImage’), type=‘function’)]))], created=1733473918, model=‘gpt-4o-2024-08-06’, object=‘chat.completion’, service_tier=None, system_fingerprint=‘fp_831e067d82’, usage=CompletionUsage(completion_tokens=16383, prompt_tokens=1359, total_tokens=17742, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=None), prompt_tokens_details=None, prompt_token_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0)))”

i made text from image shorter to pass it to forum