> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/advanced-basic/chat.md).

# 对话进阶

【对话】适合边交流边整理思路。除了单模型问答，还可以并排比较多个模型、从任意消息创建分支、管理长对话上下文，并把回复中的文件、图片、代码和引用作为产物继续使用。

{% hint style="info" %}
如果任务需要连续读写本地文件、调用多种工具或长时间运行，改用【工作】中的 Agent。对话更适合讨论、比较和定稿，Agent 更适合执行。
{% endhint %}

<figure><img src="/files/V0njWDz16qReQZ5g3T8V" alt="对话进阶中从完整问题到比较、分支和产物的选择流程图"><figcaption><p>问题和输出要求先写完整；只有需要交叉验证时再增加模型比较或消息分支。</p></figcaption></figure>

## 按目标选择能力

| 目标            | 推荐做法                  |
| ------------- | --------------------- |
| 比较不同模型的观点     | 在输入区选择多个模型后发送同一个问题    |
| 保留原讨论并探索另一条思路 | 从关键消息创建分支             |
| 继续很长的讨论       | 查看上下文用量，必要时总结后新开话题    |
| 让下一条问题稍后发送    | 使用消息队列，不必打断当前回复       |
| 继续处理回复中的文件或代码 | 打开产物预览，再下载、复制或在新任务中继续 |

<figure><img src="/files/nAVKvMi2ID3xbSjnfz4h" alt="对话中的模型选择器和多个模型入口"><figcaption><p>模型选择器可以为同一个问题选择一个或多个模型。</p></figcaption></figure>

## 推荐顺序

{% stepper %}
{% step %}

### 1. 先把问题写完整

说明目标、材料、限制和希望的输出方式。多个模型只会放大原问题的差异，不会自动补齐缺少的信息。
{% endstep %}

{% step %}

### 2. 再决定是否需要比较

需要不同视角时再选多个模型。日常问答保持单模型，界面更清楚，用量也更容易控制。
{% endstep %}

{% step %}

### 3. 把有效结论沉淀下来

可复用的资料存入笔记或知识库；需要继续执行的工作交给 Agent，并附上已经确认的结论。
{% endstep %}
{% endstepper %}

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>多模型对比与消息分支</strong></td><td>比较答案，同时保留探索路径</td><td><a href="/pages/UmfIJ6NWV6kBSaNE1NX0">/pages/UmfIJ6NWV6kBSaNE1NX0</a></td></tr><tr><td><strong>长对话、上下文与排队消息</strong></td><td>让长对话保持清楚、可控</td><td><a href="/pages/4qWjHE1et7sZdiqWFWiL">/pages/4qWjHE1et7sZdiqWFWiL</a></td></tr><tr><td><strong>产物、引用与导出</strong></td><td>检查并带走真正有用的结果</td><td><a href="/pages/7YG2cHLDq0gomzfEZdVZ">/pages/7YG2cHLDq0gomzfEZdVZ</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cherryai.com.cn/advanced-basic/chat.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.