lobehub / lobe-chat

🤯 Lobe Chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT chat application.

Home Page:https://chat-preview.lobehub.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Bug] 自定义模型的表单问题

BrandonStudio opened this issue · comments

💻 系统环境

Windows

📦 部署环境

Vercel / Zeabur / Sealos

🌐 浏览器

Edge

🐛 问题描述

在添加多个自定义模型时,输入第一个自定义模型的信息是正常的。
当添加第二个自定义模型的时候,设置页面显示的仍然是第一个自定义模型的信息。

如:已添加一个 model_a,其显示名称设置为 Model A,最大token数设为32K
此时添加一个 model_b,点进设置页面,显示的仍然是 model_aModel A 和 32K 的配置,而不是 model_b
将表单改为 model_bModel B 和 128 K,再点击 model_a 的设置,显示的是 model_bModel B 和 128 K,而不是 model_aModel A 和 32K。

🚦 期望结果

设置自定义模型的表单不应保留上一个模型的信息,而应该是本模型的信息

📷 复现步骤

No response

📝 补充信息

在 Azure OpenAI 上测的,不知道其它模型有没有这个问题

👀 @BrandonStudio

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。

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


💻 System environment

Windows

📦 Deployment environment

Vercel / Zeabur / Sealos

🌐 Browser

Edge

🐛 Problem description

When adding multiple custom models, it is normal to enter the information for the first custom model.
When adding a second custom model, the settings page still displays the information of the first custom model.

For example: a model_a has been added, its display name is set to Model A, and the maximum number of tokens is set to 32K
At this time, add a model_b and click into the settings page. The configurations of model_a, Model A and 32K are still displayed instead of model_b.
Change the form to model_b, Model B and 128 K, and then click the settings of model_a. What is displayed is model_b, Model B and 128 K instead of model_a, Model A and 32K.

🚦 Expected results

The form for setting up a custom model should not retain the information of the previous model, but the information of this model.

📷 Steps to reproduce

No response

📝 Supplementary information

Tested on Azure OpenAI, I don’t know if other models have this problem

理论上已经在 #2318 被修复。
拉取到本地调试运行是正常的,暂不清楚 release 为何没有实装。

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


Theoretically has been fixed in #2318.
It is normal to pull it to local debugging and running. It is not clear why release is not installed.

@BrandonStudio

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。