Macbook m1 can not run program?

DavidKotykOfficial commented 5 days ago

whenever my computer tries to run o1 engineer i keep getting

Error while communicating with OpenAI: Completions.create() got an unexpected keyword argument 'max_completion_tokens' ERROR:root:Error while communicating with OpenAI: Completions.create() got an unexpected keyword argument 'max_completion_tokens' Failed to generate a planning response. Please try again. ERROR:root:AI failed to generate a planning response.

I have an m1 macbook.

whrit commented 5 days ago

Also have the same issue and on an M3 MBP- Thinking this might be OAI tier related and having access to the o1 API. Believe I'm a Tier 3 account, so in theory should have access to o1 and o1 Mini... I'll run a test on my Windows machine to see if it's the same there.

whrit commented 5 days ago

Also have the same issue and on an M3 MBP- Thinking this might be OAI tier related and having access to the o1 API. Believe I'm a Tier 3 account, so in theory should have access to o1 and o1 Mini... I'll run a test on my Windows machine to see if it's the same there.

Yeah confirming this is an API Tier issue. Running on Windows gave me the error that I don't have access to the model. Quite strange given I should be Tier 3 and have access to o1..

Doriandarko commented 5 days ago

You need to update your OpenAI python package

Pietro Schirano Founder | EverArt http://everart.ai

On Wed, Oct 2, 2024 at 12:41 DavidKotykOfficial @.***> wrote:

whenever my computer tries to run o1 engineer i keep getting

Error while communicating with OpenAI: Completions.create() got an unexpected keyword argument 'max_completion_tokens' ERROR:root:Error while communicating with OpenAI: Completions.create() got an unexpected keyword argument 'max_completion_tokens' Failed to generate a planning response. Please try again. ERROR:root:AI failed to generate a planning response.

I have an m1 macbook.

— Reply to this email directly, view it on GitHub https://github.com/Doriandarko/o1-engineer/issues/12, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAJQPTGFEDJSNFMCRYTSS4TZZQO3TAVCNFSM6AAAAABPIB2Z3GVHI2DSMVQWIX3LMV43ASLTON2WKOZSGU3DEMJVG44DKOA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

DavidKotykOfficial commented 4 days ago

update your OpenAI python package

Worked, Thank you!!!

kalebzaki4 commented 3 days ago

It looks like you're encountering an error related to the Completions.create() function in OpenAI's API while trying to run the o1 engineer program on your M1 MacBook. The specific issue is that the function is being called with an unexpected keyword argument max_completion_tokens, which is likely not valid or supported.

Here are a few steps to troubleshoot and resolve the issue:

1. Check OpenAI API Version:

The max_completion_tokens argument might be outdated or not supported in the version of the OpenAI API you are using. Make sure that you are using the latest version of the OpenAI Python package. You can update it by running:
```
 pip install --upgrade openai
```
After updating, review the official OpenAI API documentation to ensure you’re using the correct parameters for your API calls.

2. Correct API Call:

The correct argument might be max_tokens instead of max_completion_tokens. You could try replacing max_completion_tokens with max_tokens in the code where the API call is made. For example:
```
 response = openai.Completion.create(
     engine="text-davinci-003",
     prompt="Your prompt here",
     max_tokens=100  # Replace with the desired value
 )
```

3. Compatibility with M1 MacBook:

The issue does not seem to be specific to your M1 MacBook, but it’s always a good idea to check that all dependencies are properly installed and compatible with your architecture. If you're using virtual environments (e.g., venv or conda), make sure they are correctly set up for the M1 chip.

4. Review Logs and Documentation:

Check if there’s an issue tracker or documentation specific to the o1 engineer project that references this issue. It’s possible others have faced the same problem, and there may already be a fix or patch.

If none of these steps resolve the issue, you might want to report this to the project maintainers, including details about your setup (Python version, OpenAI library version, etc.) to help them investigate further.

Doriandarko / o1-engineer