# 构建技术支持聊天机器人

**URL:** <https://meta.discourse.org/t/building-a-technical-support-chatbot/319825>\
**Category:** Extras\
**Tags:** chat, ai\
**Created:** [2024年八月2日 13:34 UTC](https://meta.discourse.org/t/building-a-technical-support-chatbot/319825 "2024-08-02T13:34:30Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![sam](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/sam/32/102149_2.png) [@sam](https://meta.discourse.org/u/sam)\
**Post date:** [2024年十月4日 04:59 UTC](https://meta.discourse.org/t/building-a-technical-support-chatbot/319825/2 "2024-10-04T04:59:26Z")

</div>

> [@37Rb](#):
>
> 强制 LLM 调用函数。

供参考，这将根据以下内容在 Discourse AI 中实现：

> <https://github.com/discourse/discourse-ai/pull/818>
>
> Sometimes we need to force LLMs to use tools, for example in RAG
> like use cases… we may want to force an unconditional search.
> 
> The new framework allows you backend to force tool usage.
> 
> This implements both front and and back end support.
> 
> Initial support is only written for OpenAI models, however follow up commits will backfill support to other providers.

我同意，这对于 RAG 来说是一项非常重要的功能，LLM 很懒惰，经常拒绝搜索。

---

_[View the full topic](https://meta.discourse.org/t/building-a-technical-support-chatbot/319825)._