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] [Module Name] Bug title 输入文本中有信息,但是大模型没有抽取到信息。这是什么原因导致的呢? #329

Open
2 tasks done
zhulin-acad opened this issue Jan 31, 2025 · 2 comments

Comments

@zhulin-acad
Copy link

Search before asking

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

Operating system information

Linux

What happened

输入文本中有信息,但是大模型没有抽取到信息。这是什么原因导致的呢?

How to reproduce

各位大佬好,我在知识构建的过程中遇见了下面的问题:
问题1:在运行构建知识图谱的脚本之后,大模型并没有抽出我定义的节点的相关内容。
例:我在schema中定义了下面的节点:
TeachingSpirit(教风): EntityType
desc: 学校的教风情况
properties:
teachDescription(描述): Text
desc: 对教风的整体描述
constraint: NotNull
relations:
belongsTo(隶属学校): School

在我的输入文件中有下面的信息:
成都信息工程大学教风为”爱生、敬业、求实、创新”。
爱生意为教师对“爱心”的具体实现,要求教师在传授知识中塑造着和谐人格,在追求真理中充满热情和激情。敬业是教师“责任”的体现。要求教师遵从事业的召唤,热爱自己的事业。求实即求真务实,要求教师以实为本,在诚实、朴实、务实和求实中将爱心附诸实施,把敬业落实到行动上。创新是教育事业兴旺发达的不竭动力,也是教师“行动”的精髓。其要求教师用创新的理念和创新思维训练头脑。
学风

但是最后抽取完成之后我定义的节点里面显示no record,并且是每一个我定义的节点都是no record。

请问应该怎么样才能让模型抽取出正确的信息?

Are you willing to submit PR?

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

justplus commented Feb 5, 2025

可能是大模型的能力不足 看下日志?

@zhuzhongshu123
Copy link
Collaborator

Hello, you can set the log level to DEBUG in the kag_config.yaml file to check if the inputs and outputs of the LLM in the extraction process, such as NER and triplet extraction, are as expected.

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

3 participants