You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Bot detected the issue body's language is not English, translate it automatically.
Title: [Bug] The model that generates the summary will use the chat model's api key instead of its own key
📦 Deployment method
Vercel
📌 Software version
v2.15.8
💻 System environment
Windows
📌 System version
22H2
🌐 Browser
Chrome
📌 Browser version
131.0.6778.109
🐛 Problem description
I have tried static deployment and Vercel deployment, and both have this problem:
When the service provider of the chat model is different from the service provider of the summary model, the endpoint of the request to generate the summary is correct, but the api key and the format of the provided key are those of the chat model, not the summary model in the settings. The key and corresponding format set by the service provider.
📷 Steps to reproduce
The service provider that sets up the summary model is different from the chat model, initiates chat, and captures requests to the summary model.
🚦 Expected results
Requests to a summary model should use its corresponding provider's API key.
📦 部署方式
Vercel
📌 软件版本
v2.15.8
💻 系统环境
Windows
📌 系统版本
22H2
🌐 浏览器
Chrome
📌 浏览器版本
131.0.6778.109
🐛 问题描述
我尝试过静态部署和Vercel部署,均存在这个问题:
当聊天模型的服务商与摘要模型的服务商不同时,生成摘要的请求的
endpoint
正确,但是api key和提供key的格式却用的是聊天模型的,而不是在设置中为摘要模型的服务商设置的key和对应格式。📷 复现步骤
设置摘要模型的服务商与聊天模型不同,发起聊天,抓取向摘要模型的请求。
🚦 期望结果
向摘要模型的请求应当使用它对应的提供商的api key。
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: