Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added Azure OpenAI Service Model, error when selecting base model "gpt-4-turbo-2024-04-09" #4057

Open
4 tasks done
Caixiaopig opened this issue May 2, 2024 · 6 comments
Open
4 tasks done
Labels
🐞 bug Something isn't working

Comments

@Caixiaopig
Copy link

Caixiaopig commented May 2, 2024

Self Checks

  • This is only for bug report, if you would like to ask a quesion, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • Pleas do not modify this template :) and fill in all the required fields.

Dify version

0.6.6

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

  1. Enter Settings -> Model Provider
  2. Click Add Azure OpenAI Service Model
  3. Fill in the required fields in the form, and select gpt-4-turbo-2024-04-09 as the Base Model
  4. Alert error: Base Model Name gpt-4-turbo-2024-04-09 is invalid
  5. Bug change the Base Model Name to gpt-4-0125-preview and can successfully add it

WX20240502-233838@2x

✔️ Expected Behavior

Base Model Name selected gpt-4-0125-preview was successfully added

❌ Actual Behavior

Change the Base Model Name to gpt-4-0125-preview and can successfully add it

Copy link

dosubot bot commented May 2, 2024

Hey @Caixiaopig, great to see you diving into the depths of Dify again! 😊 I remember our last adventure through code together. Let me take a closer look at what's going on with the Azure OpenAI Service Model and the elusive gpt-4-turbo-2024-04-09. I'll circle back shortly with some insights or a solution!

@dosubot dosubot bot added the 🐞 bug Something isn't working label May 2, 2024
@nsvrana
Copy link

nsvrana commented May 2, 2024

Same issue for me when using gpt-4-turbo-2024-04-09 on Azure OpenAI.

image

Copy link

dosubot bot commented May 2, 2024

The issue with adding the Azure OpenAI Service Model using the base model name "gpt-4-turbo-2024-04-09" in Dify might be related to a few key factors. It's possible that this specific model name does not match the expected format or is not recognized by Dify's current version (0.6.6) due to one of the following reasons:

  1. Validation Against a Predefined List: Dify checks the base model name against a predefined list of valid model names. If "gpt-4-turbo-2024-04-09" is not on this list, the system will flag it as invalid.

  2. API Version Compatibility: The error could be related to the API version specified in your configuration. If "gpt-4-turbo-2024-04-09" requires a different API version than what's configured, this could lead to compatibility issues.

  3. Model Availability: The model "gpt-4-turbo-2024-04-09" might not be available in the Azure OpenAI Service at the time of your configuration, or there could be restrictions based on your Azure subscription or service region.

  4. Configuration Error: A misconfiguration or typo in the setup specific to "gpt-4-turbo-2024-04-09" could also be the cause, unlike with "gpt-4-0125-preview", which you mentioned works correctly.

To move forward, ensure that the model name is correct and supported by Dify, check for any typos in your configuration, and verify that you're using the correct API version. If the issue persists, providing more details about the error message or logs could help in diagnosing the problem more accurately.

Details

Sources


About Dosu
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.

To continue the conversation, mention @dosu.

@shelltea
Copy link

shelltea commented May 6, 2024

I encountered the same issue, and it was resolved by setting the base model to gpt-4. However, this setup results in the inability to use the vision feature. I hope it can be fixed as soon as possible.
image

@nsvrana
Copy link

nsvrana commented May 6, 2024

Use GPT-4-Vision and you will be able to use all of the functionality until this is fixed.

@shelltea
Copy link

In version 0.6.7, this issue has been fixed and can now be closed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🐞 bug Something isn't working
Projects
None yet
Development

No branches or pull requests

3 participants