Skip to content
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

[Bug] Gemini vision model cannot start chat with text message #4102

Open
1 of 3 tasks
ghost opened this issue Feb 22, 2024 · 10 comments
Open
1 of 3 tasks

[Bug] Gemini vision model cannot start chat with text message #4102

ghost opened this issue Feb 22, 2024 · 10 comments
Labels
bug Something isn't working

Comments

@ghost
Copy link

ghost commented Feb 22, 2024

Bug Description

{
"error": true,
"message": "Request failed"
}

Steps to Reproduce

  1. 手动同步最新版;2、打开网页;3、新建聊天发送;4、返回请求失败

Expected Behavior

请求成功

Screenshots

image

Deployment Method

  • Docker
  • Vercel
  • Server

Desktop OS

windows 10

Desktop Browser

Chrome

Desktop Browser Version

121.0.6167.185

Smartphone Device

No response

Smartphone OS

No response

Smartphone Browser

No response

Smartphone Browser Version

No response

Additional Logs

No response

@ghost ghost added the bug Something isn't working label Feb 22, 2024
@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


Title: The latest version request Gemini failed to return [Bug]

@dyq94310
Copy link

Todya I have same bug when use Gemini

{
  "error": true,
  "message": "Add an image to use models/gemini-pro-vision, or switch your model to a text model."
}

image

@ghost
Copy link
Author

ghost commented Feb 22, 2024

I instant rollback can fix it.

@xieyos
Copy link

xieyos commented Feb 22, 2024

gemini-pro-vision模型必须以图片开始对话,简单说就是第一次对话必须上传一张图片

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


The gemini-pro-vision model must start the conversation with a picture. Simply put, the first conversation must upload a picture.

@H0llyW00dzZ
Copy link
Contributor

Todya I have same bug when use Gemini

{
  "error": true,
  "message": "Add an image to use models/gemini-pro-vision, or switch your model to a text model."
}

image

The Gemini-Pro-Vision is not yet available or stable for multi-modal tasks, unlike the GPT-4-Vision-Preview, which can directly send messages without attaching an image. However, the GPT-4-Vision-Preview has its own issues, as indicated in issue #4088.

@dyq94310
Copy link

Todya I have same bug when use Gemini

{
  "error": true,
  "message": "Add an image to use models/gemini-pro-vision, or switch your model to a text model."
}

image

My problem was automatically fixed today,maybe request #4162 fix this problem.

@Yeadon888
Copy link

我也是这个问题,是不是中国的服务器无法访问gemini

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


I have the same problem. Is it because Chinese servers cannot access gemini?

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


Hello! The email has been received, thank you for your hard work!

@fred-bf fred-bf changed the title 最新版请求Gemini返回失败 [Bug] [Bug] Gemini vision model cannot start chat with text message Mar 1, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

5 participants