modelscope / modelscope/sirchmunk
如何处理历史错误命中的缓存向量和本次查询的相似度过高导致的查询错误？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 146
- Avg merge
- 3h 31m
- Merged PRs (30d)
- 6
Description
您好：
如果有些知识相近或 LLM 对于垂直领域知识的不清晰，导致的第一次知识检索错误，然后当前查询向量和历史知识簇的查询嵌入向量匹配度过高，导致的错误命中如何处理?
是全部的 cache clear 还是有逐条清理的机制。如果是生产环境，可能全部清理的风险比较大。
延伸出来下一个问题，基于当前查询流程，如果是知识更新后，实际上可能出现匹配度更高的知识文档，但是当前由于缓存只能命中历史的cache，这个是否如何处理？
是否可以更新知识的时候，同步刷新相关缓存？
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
No files, tests, or entry points are named. Start by tracing the current query-cache lookup, vector-similarity matching, and knowledge-update flow, then determine how an incorrect cache entry can be removed and how updates should invalidate related entries. Done means the project has an agreed, safe invalidation strategy for both individual errors and updated knowledge.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100