[Issue]: 输出结果是否可以定制化

[jiangyong07]

Do you need to file an issue?

• [ ] I have searched the existing issues and this bug is not already filed.
• [ ] My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• [ ] I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the issue

用了几次，感觉graphrag功能非常强大。但处理长文本的时候，时间花费很多，而我需要的资料相对具体。比如，我只需要某个人的相关信息：像是籍贯、生卒年、亲属关系、社会关系等。是否可以通过改写Prompt来实现定制化的输出？这样也可以节省很多时间和算力。如果可以，程序中的4个prompt该如何改写呢？

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version:
• Operating System:
• Python Version:
• Related Issues:

[YepJin]

I am also looking for a solution, but you can try this one. https://www.microsoft.com/en-us/research/blog/graphrag-auto-tuning-provides-rapid-adaptation-to-new-domains/

[jgbradley1]

The various prompts include few-shot examples of entities and relationships to look for.

After generating the prompts for the first time, you can edit the examples inside the prompts to contain only few-shot examples of the specific entity types and relationships that you’re interested in. You do not need to modify the rest of the prompt.

The syntax to provide the labeled few-shot examples can be tricky to utilize correctly, which is why I advise auto-generating the prompts first so you have some examples to refer to

[github-actions[bot]]

This issue has been marked stale due to inactivity after repo maintainer or community member responses that request more information or suggest a solution. It will be closed after five additional days.

[github-actions[bot]]

This issue has been closed after being marked as stale for five days. Please reopen if needed.