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] 轻量化部署-使用线上Embedding模型报错 #3100

Closed
yellowaug opened this issue Feb 28, 2024 · 7 comments
Closed

[BUG] 轻量化部署-使用线上Embedding模型报错 #3100

yellowaug opened this issue Feb 28, 2024 · 7 comments
Assignees
Labels
bug Something isn't working

Comments

@yellowaug
Copy link

**问题描述
根据文档描述
Untitled
我将configs/model_config.py的"EMBEDDING_MODEL"字段的值设置成“zhipu-api”,
Untitled1
然后运行知识库的初始化命令,报错如下
Untitled2

@yellowaug yellowaug added the bug Something isn't working label Feb 28, 2024
Copy link

dosubot bot commented Feb 28, 2024

🤖

你好,@yellowaug!很高兴再次看到你的问题,希望这次我们也能一起顺利解决。

根据您提供的信息,我发现了一些可能的解决方案。这个TypeError错误可能是由于在configs/model_config.py中的"zhipu-api"初始化或配置出现问题。错误提示在代码中的某个地方,尝试在一个None对象上进行操作,而这个对象应该是一个具有conjugate方法的类或类型的实例。这可能是因为初始化命令期望得到某种应该由配置设置的对象或值,但没有得到,可能是因为"zhipu-api"配置没有正确创建或返回预期的对象。

要解决此问题,您需要确保:

  1. configs/model_config.py中的"zhipu-api"配置已正确设置所有必需的参数。
  2. 初始化命令正确处理"zhipu-api"配置,正确实例化并设置其需要的任何对象或组件。
  3. 使用由命令初始化的配置或对象的任何代码都检查None值,并适当处理它们,以避免在NoneType对象上尝试操作。

没有具体的初始化命令代码以及它如何与配置交互,很难确定确切的原因。但是,审查初始化过程并确保正确使用和处理配置应有助于识别和解决问题。

另外,我在Langchain-Chatchat的问题库中找到了一些类似的已解决问题,可能对您有所帮助:

  1. [BUG] 简洁阐述问题 / 运行python init_database.py --recreate-vs错误
  2. [BUG] 简洁阐述问题 / Concise description of the issue
  3. [BUG] 无法使用zhipu的在线embedding

希望这些信息能帮助您解决问题。如果您有任何其他问题或需要进一步的澄清,请随时告诉我。

Sources

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

@zRzRzRzRzRzRzR
Copy link
Collaborator

zhipu的应该是没支持,其他轻量化服务不是我写的,我不太清楚

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR self-assigned this Feb 28, 2024
@yellowaug
Copy link
Author

哈哈作者真是勤劳话说问下你们的0.3什么时候更新

@zRzRzRzRzRzRzR
Copy link
Collaborator

这个得看一下时间了,chatchat是我们的业余项目,我们在不同的公司,这个只能有时间做

@yellowaug
Copy link
Author

业余项目你们能做成这样,很强了。祝你们项目成功

@LaoK263
Copy link

LaoK263 commented Mar 18, 2024

zhipu的应该是没支持,其他轻量化服务不是我写的,我不太清楚
看代码智谱的embedding还没有支持,但是wiki却说是支持的,建议更新wiki文档,我在这个事情上花了3天时间,才搞清楚。
下图代码在/server/model_workers/zhipu.py中,我理解这是初始化智谱模型的代码:
image

@TonyHmx
Copy link

TonyHmx commented Jun 28, 2024

请问下使用了lite方案,LLM和embedding模型都选择的qwen-turbo,启动和LLM问答正常,但是使用知识库问答,在使用了text-embedding-v1模型一直匹配不到知识库内容,这是为啥呢
problem

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

4 participants