[Bug] MODEL_LIST不知道为啥无效了，部署完成后默认不显示任何模型，设置里模型列表也是官方的而不是我自己自定义的

[CCMAYNOTXX]

📦 部署环境

Docker

📌 软件版本

v1.51.8

💻 系统环境

Other

🌐 浏览器

Edge

🐛 问题描述

系统版本：CENT OS 8.2

MODEL_LIST参数不知道为啥无效果了，按照图片的参数部署后，默认只有openai的默认模型，模型设置里也没有我自己自定义的模型列表，只有默认获取的模型列表，回滚到1.50.5版本后模型列表正常，但是也需要手动在模型设置里添加模型，回滚到更早的版本后，自定义好model list后就不用再去应用设置里选择对应的API提供商开启指定模型，而是直接在对话窗口左下角切换里就有

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[lobehubbot]

👀 @CCMAYNOTXX

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

📦 Deployment environment

Docker

📌 Software version

v1.51.8

💻 System environment

Other

🌐 Browser

EDGE

🐛 Question description

System version: CENT OS 8.2

I don't know why the MODEL_LIST parameter has no effect. After deploying according to the parameters of the picture, there is only the default model of openai by default. There is no customized model list in the model settings. There is only the model list obtained by default, and it is rolled back to 1.50.5 The model list after the version is normal, but you also need to manually add the model in the model settings. After rolling back to an earlier version, you no longer have to go to the application settings to select the corresponding API provider to enable the specified model. It is directly switched in the lower left corner of the dialogue window

📷 Reproduction steps

No response

🚦 Expected results

No response

📝 Supplementary information

No response

[dosubot]

I found a similar closed issue that might be relevant to your problem. The issue titled "[Bug] 1.44.2版本环境变量OPENAI_MODEL_LIST语法失效" was resolved by a pull request that fixed the *_MODEL_LIST environment variable in a new provider ^[1]. This might indicate that there were changes in how the MODEL_LIST parameter is handled in recent versions.

In version 1.51.8, there was a refactor of the model fetch method, which could potentially affect the functionality of the MODEL_LIST parameter ^[2]. This refactoring might be related to the issue you're experiencing with the model list not displaying your custom models.

To configure the MODEL_LIST parameter in the Docker environment, you should use the OPENAI_MODEL_LIST environment variable. This allows you to add, hide, or customize the display name of models using a specific syntax. For example:

OPENAI_MODEL_LIST=+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo

If you want to disable all models first and then enable specific ones, you can use:

OPENAI_MODEL_LIST=-all,+gpt-3.5-turbo

This configuration should help you manage which models are displayed in the user interface ^[3].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[arvinxx]

似乎也是和 #5804 有关

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

It seems to be related to #5804

[lobehubbot]

✅ @CCMAYNOTXX

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。

[lobehubbot]

🎉 This issue has been resolved in version 1.51.13 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀