-
-
Notifications
You must be signed in to change notification settings - Fork 11.4k
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] Claude图片上传后提问报错 #3853
Comments
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. |
Hello @yuwuxing! I'm here to help you with bug fixes, answer questions, and assist with contributions. Let's tackle this issue together! I found a similar unsolved discussion regarding the Gemini model not receiving images [1]. To resolve the error messages when uploading an image and using Claude Sonnet 3.5 or Google Gemini models in a Docker-deployed environment on Ubuntu with Chrome, ensure that the necessary environment variables for these models are correctly set in your Dockerfile. Here is the relevant section of the Dockerfile where you can set these variables: # Model Variables
ENV \
# Google
GOOGLE_API_KEY="" GOOGLE_PROXY_URL="" \
# Anthropic
ANTHROPIC_API_KEY="" ANTHROPIC_PROXY_URL="" Replace the empty strings with your actual API keys and proxy URLs if needed. For example: # Model Variables
ENV \
# Google
GOOGLE_API_KEY="your_google_api_key" GOOGLE_PROXY_URL="your_google_proxy_url" \
# Anthropic
ANTHROPIC_API_KEY="your_anthropic_api_key" ANTHROPIC_PROXY_URL="your_anthropic_proxy_url" Additionally, ensure that the # Add sharp dependencies
&& mkdir -p /sharp \
&& pnpm add sharp --prefix /sharp For the specific error messages you encountered:
If you have set these variables correctly and still encounter issues, check the logs for more specific error messages that could provide further insights into what might be going wrong. It's also important to note that based on recent evaluations, the Google Gemini models, particularly Gemini 1.5 Pro and Gemini 1.5 Flash, have shown poor performance in tool calling capabilities. For instance, Gemini 1.5 Pro has issues with recognizing plugin names correctly and throws errors for complex instructions. Gemini 1.5 Flash does not output tool calling data at all, making it essentially unusable for such tasks [2][3]. |
Google Gemini 在 #3370 修复 |
Fixed by Google Gemini in #3370 |
已在 #3870 修复 |
This issue is closed, If you have any questions, you can comment and reply. |
Fixed in #3870 |
📦 部署环境
Docker
📌 软件版本
v1.15.26
💻 系统环境
Ubuntu
🌐 浏览器
Chrome
🐛 问题描述
使用Claude sonnet 3.5模型和google Gemini 模型提问,上传一张图片,显示上传成功,但是返回报错信息:
Claude 报错
Gemini Flash 1.5 报错
{
"error": {
"message": "currently we don't support image url: https://s3-lobechat.xxxxx.com/lobechat/files/479410/99270fd2-1643-41eb-93ca-684d1d6934ed.jpg"
},
"provider": "google"
}
控制台查询图片路径正常上传,图片可以访问
换了本地部署的minio和R2都是同样报错
📷 复现步骤
🚦 期望结果
能够正常对话
📝 补充信息
GPT相关模型可以回答成功
The text was updated successfully, but these errors were encountered: