> For the complete documentation index, see [llms.txt](https://docs.omnichat.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.omnichat.ai/features/tong-xun-qu-dao/di-san-fang-ying-yong/chuan-jie-raccoon-ai.md).

# 串接 Raccoon AI

{% hint style="info" %}
此功能為加購項目，若頁面上顯示「需加購」，歡迎聯繫您的團隊顧問或線上來訊詢問我們唷！
{% endhint %}

<figure><img src="/files/8673kQ9fZ70My8Aqt6Sh" alt=""><figcaption></figcaption></figure>

## 前置作業

請先向 Raccoon AI 索取「App Token」與「Header Auth」資訊。

## 步驟一

在 Omnichat 後台左側選單中找到串接頁面：通訊渠道 > 第三方應用 > Al Agent > Raccoon AI，並點擊「串接」按鈕。

<figure><img src="/files/QuuPXsC8eRggtOg1ZauS" alt=""><figcaption></figcaption></figure>

## 步驟二

確認串接後支援內容後，點擊「開始」按鈕。

<figure><img src="/files/IaaU4iEm9mvsURNyPZr1" alt=""><figcaption></figcaption></figure>

## 步驟三

輸入從 Raccoon AI 索取到的「App Token」，輸入後並點擊「送出」按鈕。\
若沒有 App Token 資訊，需請 Raccoon AI 協助提供。

<figure><img src="/files/vuBl2WQ4foW2qfWd4XZx" alt=""><figcaption></figcaption></figure>

## 串接成功！

若有顯示綠色打勾符號，則表示有串接成功囉！

<figure><img src="/files/Vp0OTtGr75tNc8gDFCsy" alt=""><figcaption></figcaption></figure>

## 其他動作說明

點擊右側「...」按鈕，即可進行更多設定。

* 編輯串接資料：可重新更新 app token。
* 前往 Agent Studio：點擊後前往到 Omni AI 的 Agent Studio 頁面 → 可繼續編輯 Agent 設定，詳細操作步驟教學請參考 [Raccoon AI Agent 說明頁面](/features/omni-ai-jia-gou-gong-neng/raccoon-ai-agent.md)。
* 前往聊天機器人：點擊後前往 聊天機器人 頁面 → 可繼續新增 AI Agent 卡片。
* 解除串接：移除 Agent Studio 內 Raccoon AI 相關的 Agent 設定。

<div><figure><img src="/files/UsQVKAKV7kmpnIgntoKu" alt=""><figcaption></figcaption></figure> <figure><img src="/files/4z9HGd6aoDaNE6WjPRDx" alt=""><figcaption></figcaption></figure></div>


---

# 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.omnichat.ai/features/tong-xun-qu-dao/di-san-fang-ying-yong/chuan-jie-raccoon-ai.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.