# 使用语义搜索查找相关主题

**URL:** <https://meta.discourse.org/t/use-semantic-search-for-related-topics/330259>\
**Category:** Product Support\
**Tags:** ai\
**Created:** [2024 年10 月 10 日 14:40 UTC](https://meta.discourse.org/t/use-semantic-search-for-related-topics/330259 "2024-10-10T14:40:53Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

作者： ![fbpbdmin](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/fbpbdmin/32/300893_2.png) [@fbpbdmin](https://meta.discourse.org/u/fbpbdmin)\
发布日期： [2024 年10 月 10 日 14:40 UTC](https://meta.discourse.org/t/use-semantic-search-for-related-topics/330259/1 "2024-10-10T14:40:54Z")

</div>

关于 AI 启用的相关主题列表的问题

在 Discourse AI 插件中，有一个设置  
`Use Semantic Search for related topics.`（对相关主题使用语义搜索。）

启用此设置后，在每个主题的底部，都会有一个相关主题列表。  
关于此功能的一个问题是，当有人打开一个主题进行查看时，系统是否每次都会向 AI API 发送请求以获取相关主题列表？  
如果它是这样工作的，那么发送到 AI 服务器的流量似乎会很大……

谢谢……

看到了 Falco 在这里的帖子，似乎确实如此……？

> [@Differences in search latency between AI semantic and keyword search](https://meta.discourse.org/t/differences-in-search-latency-between-ai-semantic-and-keyword-search/294571/2?u=fbpbdmin):
>
> Can you expand on what you mean by latency here? For Related Topics, since every embeddings is pre-calculated there is not extra runtime cost. Much to the contrary, finding related topics SQL query is faster than our old suggested topics query, and we cache related topics for even faster performance. As for AI Search, our current HyDE[[1]](#footnote-1451250-1) approach to it incurs in serious latency, which is why it happens async and the user is presented first with the standard search and the option to augment it…

---

_[View the full topic](https://meta.discourse.org/t/use-semantic-search-for-related-topics/330259)._