[Bug]: prompts.complete not working as mentioned in the docs about portkey-python-sdk

[dosubot]

🤖

Hey @ayush-portkey! 😊

I'm Dosu, a friendly bot here to lend a hand with bugs, answer inquiries, and guide you on your journey to becoming a contributor! While you're waiting for a human maintainer, I'm here to help. 🦾

Based on the information you've provided, there could be several reasons why the prompts.complete function is not generating completions as expected. Here are a few possibilities:

1. The prompt parameter is None or an empty string. The prompt is the input text that you want the AI to complete. If it's not provided or empty, the AI might not know what to generate.

2. The max_tokens parameter is set to a very low value. This parameter controls the maximum length of the generated text. If it's too low, the AI might not generate any text.

3. The temperature parameter is set to a very low value. This parameter controls the randomness of the generated text. If it's too low, the AI might always generate the same text.

4. The top_k and top_p parameters are set to very low values. These parameters control the diversity of the generated text. If they're too low, the AI might not generate diverse text.

5. There might be an issue with the connection to the Portkey API. Check if the API is up and running and if your API key is valid.

Here's the relevant code:

def create(
        self,
        *,
        prompt: Optional[str] = None,
        stream: bool = False,
        temperature: Optional[float] = None,
        max_tokens: Optional[int] = None,
        top_k: Optional[int] = None,
        top_p: Optional[float] = None,
        **kwargs,
    ) -> Union[TextCompletion, Stream[TextCompletionChunk]]:
        body = dict(
            prompt=prompt,
            temperature=temperature,
            max_tokens=max_tokens,
            top_k=top_k,
            top_p=top_p,
            stream=stream,
            **kwargs,
        )
        return self._post(
            PortkeyApiPaths.TEXT_COMPLETE_API,
            body=body,
            params=None,
            cast_to=TextCompletion,
            stream_cls=Stream[TextCompletionChunk],
            stream=stream,
            headers={},
        )

You can find this code in the portkey_ai/api_resources/apis/complete.py file.

If you're still experiencing issues, could you please provide more details? Specifically, it would be helpful to know the exact error message or behavior you're experiencing when trying to use the prompts.complete function. Also, please let us know the exact parameters you're passing to the function. This will help us better understand the issue and provide a more accurate solution.

Sources

• portkey_ai/api_resources/apis/complete.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.