VECTOR_SEARCH_TOP_K匹配知识条数受限

[SKKKKYLAR]

问题描述 / Problem Description
匹配知识条数最多只能20，为啥不能修改的更高呢？
匹配的条数限制了我最后正确答案的输出，如果我的正确匹配答案有27个，就没办法找全
即使是使用了history，由于每次都是按照分数排列再取前VECTOR_SEARCH_TOP_K条信息，我就一直没办法找全
有什么办法修改VECTOR_SEARCH_TOP_K的限制吗？
或者其他的方法来解决

[dosubot]

@SKKKKYLAR Hello there! 👋 I'm here to help you with any bugs, questions, or contributions you have. I'm Dosu, a bot designed to assist you while you're waiting for a human maintainer.

To modify the VECTOR_SEARCH_TOP_K limit to allow more than 20 matches, you can adjust the top_k parameter in the SearchKbDocsParam class. This parameter is set by default to VECTOR_SEARCH_TOP_K, but you can specify a different value when creating an instance of SearchKbDocsParam. Here's an example:

from open_chatcaht.types.knowledge_base.doc.search_kb_docs_param import SearchKbDocsParam

search_params = SearchKbDocsParam(
    query="your search query",
    knowledge_base_name="your knowledge base name",
    top_k=30  # Set this to the desired number of matches
)

This will allow you to retrieve more than 20 matches by setting top_k to a higher value ^[1].

Additionally, there is a similar open issue discussing this limitation, where a suggested solution involves modifying the top_k in the ensemble.py and vectorstore.py files within the retrievers directory of your project. If this doesn't work, you might need to modify it in your project's virtual environment ^[2].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}