> ## Documentation Index
> Fetch the complete documentation index at: https://docs.t3planet.de/en/latest/llms.txt
> Use this file to discover all available pages before exploring further.

# Data Source

> Add the content AI Search may use: TYPO3 pages, sitemap, web pages, PDFs, Q&A pairs and text. Includes source groups and header/footer indexing.

A **data source** is content that AI Search may use to answer questions, for example your website pages, PDF files or your own questions and answers.

[T3AS Data Source Demo](https://app.supademo.com/embed/cmrajdte10somqmhxdf258tv8?utm_source=link)

**Add a data source**

1. Go to **AI Universe → AI Chatbot/Search → Data Source**.
2. Click **+ Add Source**.
3. Choose a **Source Type** (see the list below).
4. Fill in the fields for this type.
5. Enter a **Name**, for example `Main Website`.
6. Under **Used by**, choose **Both (Chatbot & Search)**, **Chatbot** or **Search**.
7. Choose how often the content is read again under **Sync Interval**: **Hourly**, **Daily** or **Weekly**.
8. Turn on **Enabled**.
9. Click **Save**.

![Data Source tab with the source list and the buttons Manage source groups, Sync All and Add Source](https://mintcdn.com/t3planet/om7TXKpIsaY4DDlr/en/latest/ExtNsT3AS/Configuration/images/data-source-list.webp?fit=max\&auto=format\&n=om7TXKpIsaY4DDlr\&q=85\&s=5a44edcf995c41633bfc7471fe311508)

**Source types**

* **TYPO3 Pages** – pages of this website. Enter the page IDs, choose how many sub-page levels to include (**Recursive**) and keep **Index mode** on **Frontend (rendered page HTML)** (the page as visitors see it).
* **Sitemap XML** – all pages listed in your sitemap, for example `https://example.com/sitemap.xml`.
* **Web Pages** – a website address. Add `/*` at the end to include only one part, for example `https://example.com/blog/*`. Turn on **Single URL** to read only this one page.
* **PDF Documents** – pick a folder with **Browse**, or upload a file with **Upload PDF** (up to 25 MB).
* **Q\&A Pairs** – type a **Question** and an **Answer**. Click **Add Q\&A pair** for more.
* **Text** – paste any text you want the AI to know.
* **Indexed Search**, **ke\_search** and **Solr** – only shown when that extension is installed.

> [!TIP]
>
> After saving, AI Search creates the background task for training by itself. You don't need to set anything up in the Scheduler.

> [!NOTE]
>
> Each website has one training task. It runs at the **Sync Interval** of the data source you saved last.

**Edit or delete a source**

Use the buttons next to each source in the list to edit or delete it.

> [!WARNING]
>
> Deleting a data source also deletes everything the AI learned from it.

**Read the content again (Sync)**

* Click **Sync Now** to read one source again, or **Sync All** for all sources.
* The new content is used after the next training run (see [Scheduler](/en/latest/en/latest/ExtNsT3AS/Configuration/TrainingCenter/Index.md#scheduler)).

## Source groups

A **source group** is a label you give to data sources, for example "Products" or "HR". On each page you can choose which groups the AI may use. This way, product pages only answer with product content.

**Create a source group**

1. Go to **Data Source**.
2. Open **Source Groups**.
3. Add, edit or delete a group.

![Manage source groups dialog](https://mintcdn.com/t3planet/pLoxFXT75jnKPjim/en/latest/ExtNsT3AS/Configuration/images/manage-source-groups1.webp?fit=max\&auto=format\&n=pLoxFXT75jnKPjim\&q=85\&s=4ad968f66db8c8a9b318f999ba5a011b)

> [!NOTE]
>
> The group **Global** always exists and cannot be changed or deleted.

**Add a data source to a group**

1. Edit the data source.
2. Choose the groups under **Source groups**.
3. Click **Save**.

**Choose the groups for a page**

1. Open the page in the page module.
2. Click **Edit page properties**.
3. Open the tab **AI Chatbot / Search** (called **AI Search** if only AI Search is installed).
4. Choose the groups under **Source groups**. **Global** means all sources.
5. Click **Save**.

![Page properties, tab AI Chatbot / Search with the Source groups field](https://mintcdn.com/t3planet/UT2hGUOzD8duhzaD/en/latest/ExtNsT3AS/Configuration/images/page-properties-source-groups.webp?fit=max\&auto=format\&n=UT2hGUOzD8duhzaD\&q=85\&s=2161d4edaa2fed065ba2ea8039f574e5)

Sub-pages use the same groups. Source groups only decide which content is used for answers. They don't change the training.

## Header and footer of your website

For **Sitemap XML** and **Web Pages** sources you can turn on **Index Site Header** and **Index Site Footer**. Then the text in your website header and footer (for example your address or main menu) is learned only once, not again on every page.

![Add Source dialog for Sitemap XML with Index site header and Index site footer](https://mintcdn.com/t3planet/UT2hGUOzD8duhzaD/en/latest/ExtNsT3AS/Configuration/images/add-source-sitemap.webp?fit=max\&auto=format\&n=UT2hGUOzD8duhzaD\&q=85\&s=bb6dd1bcc405f9aecbb158d963eed6c6)

Turn them on if your header or footer contains useful information, for example contact details or opening hours.

**Related:** [Training Center](/en/latest/en/latest/ExtNsT3AS/Configuration/TrainingCenter/Index.md) · [Scheduler](/en/latest/en/latest/ExtNsT3AS/Configuration/TrainingCenter/Index.md#scheduler) · [Dashboard](/en/latest/en/latest/ExtNsT3AS/Configuration/Dashboard/Index.md) · [AI Chatbot data sources](/en/latest/en/latest/ExtNsT3AC/FeatureGuide/DataSource/Index.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.