got-4o-mini not available in a list of OpenAI models - docker compose installation

[amatiytsiv]

Self Checks

• [X] This is only for bug report, if you would like to ask a question, please head to Discussions.
• [X] I have searched for existing issues search for existing issues, including closed ones.
• [X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [X] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• [X] Please do not modify this template :) and fill in all the required fields.

Dify version

0.6.14

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Clean VM alpine linux clean install of dify 0.6.14 using docker compose using OpenAI API key. - hit show models

✔️ Expected Behavior

All models are displayed

❌ Actual Behavior

All models except got-4o-mini are displayed

[amatiytsiv]

[dosubot[bot]]

Hello, @amatiytsiv! I'm here to help you with any bugs, questions, or contributions you might have. I'm Dosu, a bot designed to assist while you wait for a human maintainer.

The issue you're encountering with the "gpt-4o-mini" model not being displayed is likely due to the model name being incorrect or not supported in the current version of Dify. Ensure you are using one of the valid model names supported by Dify. Here is a list of valid model names:

- openai/gpt-4o
- openai/gpt-4
- openai/gpt-4-32k
- openai/gpt-3.5-turbo
- anthropic/claude-3.5-sonnet
- anthropic/claude-3-haiku
- anthropic/claude-3-opus
- anthropic/claude-3-sonnet
- google/gemini-pro-1.5
- google/gemini-flash-1.5
- google/gemini-pro
- cohere/command-r-plus
- cohere/command-r
- meta-llama/llama-3-70b-instruct
- meta-llama/llama-3-8b-instruct
- mistralai/mixtral-8x22b-instruct
- mistralai/mixtral-8x7b-instruct
- mistralai/mistral-7b-instruct
- qwen/qwen-2-72b-instruct
- deepseek/deepseek-chat
- deepseek/deepseek-coder

Make sure to use one of these valid model names instead of gpt-4o-mini when configuring your model settings ^[1].

Additionally, the support for the "gpt-4o-mini" model has been added and will be available in the latest version. You can refer to the pull request #6442 for more details ^[2].

To continue talking to Dosu, mention @dosu.

[amatiytsiv]

@dosu in clean install based on previous commits it expected to be in the list once you added api key, no custom adding of some models has to be executed. so that's a bug on clean setup

[dosubot[bot]]

The "gpt-4o-mini" model is not listed among the available models after a clean install of Dify version 0.6.14 because it is not mentioned as one of the supported models in the provided documentation. The supported models include OpenAI, Azure OpenAI, Anthropic, and open-source LLMs hosted on platforms like Hugging Face, Replicate, and xinference, but there is no mention of a "gpt-4o-mini" model ^[1][2].

If the "gpt-4o-mini" model was expected to be included based on previous commits, it might be a regression or an oversight in the current release. You can refer to the pull request #6442 for more details on the support for this model.

To continue talking to Dosu, mention @dosu.

[crazywoola]

It's already added in this PR, https://github.com/langgenius/dify/pull/6442 it's available in Cloud version, and it will be released in v0.6.15.