We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
有人知道结果排序不准确怎么处理吗,有些问答匹配结果甚至跑到第七八条了,我看源码里rerank相关代码都注释掉了。 用的xinference:v1.1.0+chatchat0.3.1.3,Qwen2.5-14B-Instruct,bge-large-zh-v1.5,bge-reranker-larger。 score从0.1到2.0都试了个遍。
The text was updated successfully, but these errors were encountered:
在 Langchain-Chatchat 0.3.1.3 版本中,确实存在 rerank 相关代码被注释掉的问题,这会影响结果的排序准确性。要解决这个问题,你需要手动修改源码,取消注释 reranker 的实现部分。具体来说,你需要在 chatchat/server/chat/kb_chat.py 文件中找到相关的注释代码,并将其取消注释。此外,确保相关的设置和模型路径已正确配置[1][2]。
chatchat/server/chat/kb_chat.py
如果 rerank 功能被禁用,系统会依赖初始检索和排序机制,这通常由搜索引擎的实现来决定,例如 Bing、DuckDuckGo 或 Metaphor 的搜索功能[3]。你可以尝试调整这些搜索引擎的参数,或者启用 rerank 功能以改善结果的排序。
To continue talking to Dosu, mention @dosu.
Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other
Sorry, something went wrong.
No branches or pull requests
有人知道结果排序不准确怎么处理吗,有些问答匹配结果甚至跑到第七八条了,我看源码里rerank相关代码都注释掉了。
用的xinference:v1.1.0+chatchat0.3.1.3,Qwen2.5-14B-Instruct,bge-large-zh-v1.5,bge-reranker-larger。
score从0.1到2.0都试了个遍。
The text was updated successfully, but these errors were encountered: