Feature: remove documents of which score is below 0.01 from knowledge retrieval

[jasonkang14]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

When performing knowledge searches, there are instances where documents with scores below 0.01 are retrieved, as their scores are non-zero but extremely low (e.g., 0.00051512). I would like to propose a feature that checks the scores of retrieved documents and excludes those where the rounded value of the score is 0.00.

Would your team be open to a pull request for this enhancement?

2. Additional context or comments

No response

3. Can you help us with this feature?

• I am interested in contributing to this feature.