-
-
Notifications
You must be signed in to change notification settings - Fork 12.5k
有关流式输出 #7379
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
Comments
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. |
Hello @deeeiznc! I'm here to help you with any bugs or questions you might have as you wait for a human maintainer. Feel free to ask me anything! To address the issues you're experiencing with Lobe Chat, here are some suggestions:
These suggestions aim to improve the flexibility and reliability of Lobe Chat when dealing with different AI models and configurations. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
同求,gemini的模型使用流式输出很容易出现中断的情况。 |
Together, gemini's model uses streaming output and is prone to interruption. |
📦 部署环境
Docker
📦 部署模式
服务端模式(lobe-chat-database 镜像)
📌 软件版本
v1.79.7
💻 系统环境
macOS
🌐 浏览器
Chrome
🐛 问题描述
问题
若 uni-api 中的 Google 系列模型思考时间过长,会导致如图错误,比如我使用 uni-api 中的 gemini-2.5-pro-exp-03-25 模型,发送了 Prompt(具体见复现步骤),
查看 uni-api 日志发现 uni-api 运行正常, 且发现 lobechat 提交的请求是非流式的,故我用 curl 非流式请求 uni-api 同一个问题,结果正常输出,是 lobechat 的问题。
相关的问题
希望能实现第三方 Custom AI Provider 中每个模型的具体配置与官方模型的配置同步:对于第三方 Custom AI Provider 中的很多模型(比如 Google 系列),功能(Support)不能与官方同步,而联网功能自己是无法开启的(没有这个选项框),如下图所示
📷 复现步骤
我发送的 Prompt with gemini-2.5-pro-exp-03-25
🚦 期望结果
对于问题
对于相关的问题
希望能实现第三方 Custom AI Provider 中每个模型的具体配置与官方模型的配置同步
📝 补充信息
No response
The text was updated successfully, but these errors were encountered: