Azure Deployment Name Bug about gpt-engineer HOT 20 CLOSED

Hey.

As discussed in the meeting today. My proposal would be to to sync the Azur part with same approach we use open models and Open router. For example (from here):

export OPENAI_API_BASE="https://openrouter.ai/api/v1"
export OPENAI_API_KEY="sk-key-from-open-router"
export MODEL_NAME="meta-llama/llama-3-8b-instruct:extended"

gpte <project_dir> $MODEL_NAME --lite --temperature 0.1

Instead of using custom --azure flag.

@captivus what do you think? I don't know their hosting specs so I'm not sure if it's doable.

from gpt-engineer.

Hey @JiaCYu, we have our community meeting today, and I'll make sure we discuss this topic with the team and get back to you!

from gpt-engineer.

@viborc I have a meeting conflict with today's dev meeting, but I can speak more about this if the issue isn't resolved during the meeting today.

from gpt-engineer.

Looking at this further, I think the bug may be ours and due to the way that we implement the model version in an opinionated way:

Let's discuss in our dev meeting.

from gpt-engineer.

I just reread the instructions and I realized that the Azure Deployment Name should be the model name as well. Which kind of sucks because there are a bunch of projects dependent on that deployment name and a lot refactoring would have to be done.

from gpt-engineer.

If I understand the issue you're reporting correctly, this is due to the parameters that OpenAI expects for Azure deployments of its model and is not a GPTE-specific issue.

from gpt-engineer.

Sounds good @captivus! I might assign you to this one if we don't figure it out during the meeting!

from gpt-engineer.

We decided to use your very generous offer to help us with this @captivus and @zigabrencic mentioned that he'll add some comments here, too!

from gpt-engineer.

More thoughts here. @JiaCYu can you please set the OPENAI_API_VERSION environment variable with your deployment's version and try again? The internals I've linked to above show how we handle environment variable when it is not set, and is consistent with the error messages you've provided. Without knowing more about your specific deployment, it's difficult to advise specifically what this value should be.

This documentation may be helpful. This issue resolution may also prove helpful.

Please try and feedback!

from gpt-engineer.

@captivus Sorry for the late reply.

I set OPEN_API_VERSION in the environmental variable in powershell, and I still get the same error as I do from the original post:

The deployment I have is named gpt-4-[redacted, but there are 4 letters here] and the deployment of the actual model is just gpt-4-turbo ver. 0125-preview:

from gpt-engineer.

Can you please try referencing one of the available deployments in your environment, as shown in the output you provided? The error suggests that you are trying to use a model that is unavailable.

Also, kindly share text outputs in addition to screenshots if additional debugging is needed.

We will upgrade the default version to use the latest supported model in Azure, which is 2024-05-01-preview per the docs.

from gpt-engineer.

So, the "Unknown model" that the error message contains is my deployment name that I mentioned here:

The deployment I have is named gpt-4-[redacted, but there are 4 letters here]

The thing is, my deployment name is different than the actual model name itself.

Also, kindly share text outputs in addition to screenshots if additional debugging is needed.

Here is the command I use with gpt-engineer:

The first red box is my azure endpoint and the last red box is the last 4 letters of my deployment name on azure.

I think it may be taking my deployment name and entering it as the model name at some point. I don't think there is a way to enter the model name separately.

from gpt-engineer.

Passing azure model deployment name in --model tag solved the issue.
Here is the command:
gpt-engineer --azure <AZURE_OPENAI_API> --model <DEPLOYMENT_NAME> ./projects/snake

from gpt-engineer.

Passing azure model deployment name in --model tag solved the issue. Here is the command: gpt-engineer --azure <AZURE_OPENAI_API> --model <DEPLOYMENT_NAME> ./projects/snake

from gpt-engineer.

Passing azure model deployment name in --model tag solved the issue.

Here is the command:

gpt-engineer --azure <AZURE_OPENAI_API> --model <DEPLOYMENT_NAME> ./projects/snake

This is the expected behavior @JiaCYu. I see your response indicating that this hasn't worked for you. Assuming you're escaping characters in the name of your model, as needed from the shell, I'm at a loss as to how to further debug the issue.

from gpt-engineer.

Can you please try referencing one of the available deployments in your environment, as shown in the output you provided? The error suggests that you are trying to use a model that is unavailable.

Also, kindly share text outputs in addition to screenshots if additional debugging is needed.

We will upgrade the default version to use the latest supported model in Azure, which is 2024-05-01-preview per the docs.

I've just merged the upgrade to the default version that I suggested we'd incorporate. Does that change anything for you?

from gpt-engineer.

It seems I am blocked due to the situation I'm in and am no longer allowed to test it :(
Thank you @captivus for keeping up with this and helping me out.

from gpt-engineer.

Hey @JiaCYu what do you mean you are blocked due to the situation?

from gpt-engineer.

Hey @JiaCYu what do you mean you are blocked due to the situation?

It's a personal reason due to to the situation I'm in, not anything of gpt-engineer's team's fault. I'm not allowed to use pypi or npm anymore :'(

from gpt-engineer.

Got it! Good luck with everything, then @JiaCYu. I hope we'll see you contributing to gpt-engineer again in the future!

from gpt-engineer.