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

Vectorizer task trace log: pemja.core.PythonException #341

Open
1 of 2 tasks
nilin1998 opened this issue Feb 11, 2025 · 1 comment
Open
1 of 2 tasks

Vectorizer task trace log: pemja.core.PythonException #341

nilin1998 opened this issue Feb 11, 2025 · 1 comment

Comments

@nilin1998
Copy link

Search before asking

  • I had searched in the issues and found no similar issues.

Operating system information

Linux

What happened

我使用docker部署kag后,上传文档进行测试,遇到的错误如以下截图所所示:
Image
我的向量化配置如下:

Image
我已经在本地通过curl测试了向量化的配置,是成功的,但是在页面上该配置就会出错

How to reproduce

我的向量化采用了阿里云的embedding模型,baseurl为https://dashscope.aliyuncs.com/compatible-mode/v1,v1-v3版本的嵌入模型都尝试过,报相同的错

Are you willing to submit PR?

  • Yes I am willing to submit a PR!
@caszkgui
Copy link
Collaborator

Search before asking

  • I had searched in the issues and found no similar issues.

Operating system information

Linux

What happened

我使用docker部署kag后,上传文档进行测试,遇到的错误如以下截图所所示: Image 我的向量化配置如下:

Image 我已经在本地通过curl测试了向量化的配置,是成功的,但是在页面上该配置就会出错

How to reproduce

我的向量化采用了阿里云的embedding模型,baseurl为https://dashscope.aliyuncs.com/compatible-mode/v1,v1-v3版本的嵌入模型都尝试过,报相同的错

Are you willing to submit PR?

  • Yes I am willing to submit a PR!

It looks like the context window of embedding model service you have chosen is too short, could you try using bge-m3?

Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants