modelscope / modelscope/sirchmunk
SIRCHMUNK_SEARCH_PATHS里有多个文件且有相同关键字如“上班”，找不准对应文件
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 146
- Avg merge
- 3h 31m
- Merged PRs (30d)
- 6
Description
当前SIRCHMUNK_SEARCH_PATHS放了一份考勤管理要求文档，一份新员工入职文档。
当询问“申请停车位需要满足什么条件？”期望找到新员工入职文档，会因为考勤管理要求文档更多出现了“申请”而引起找到了错误的考勤管理要求文档。而不能回答正确的问题。
具体例子如下：
14. 申请停车位需要满足什么条件？ - 车位申请 [A]
回答内容:
搜索结果简报
用户问题
申请停车位需要满足什么条件？
搜索结果分析
提供的文档为**《xxx考勤管理》**，内容涵盖：
- 考勤管理目的与适用范围
- 打卡规定（含免打卡弹性工作制）
- 加班管理
- 考勤月结管理
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the parking-space query with the two documents configured in SIRCHMUNK_SEARCH_PATHS, then trace the search and ranking entry point that selects the attendance document. Done means queries with overlapping terms select the document matching the requested topic and produce the expected onboarding-document answer; add or update a regression test if the project has a relevant search test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- search
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100