Hi team,
I am building an app that uses o1-preview. I have a fairly long prompt containing instructions which the model follows pretty well during tests in the Playgorund and ChatGPT. However I am getting awful results via API for the exact same prompt. I am not sending any parameters with the API call except the model name and user message as provided by the code generator in the Playground, see below:
prompt = os.getenv("PROMPT") response = await self.client.chat.completions.create( model="o1-preview-2024-09-12", messages=[ { "role": "user", "content": [ { "type": "text", "text": prompt } ] } ] )
Is there any reason why the results from the API would differ from the Playground and ChatGPT?