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

# Connect Livingdocs

> Make the published articles, pages, and data records in a Livingdocs project searchable by AI agents.

Connect a Livingdocs project as a Source and Raily keeps a searchable copy of its published content. Once it's connected, any endpoint you wire to it can answer from your articles, pages, and data records.

> [!NOTE]
>
> The Livingdocs Source is available on request. If you don't see **Livingdocs** in the list of sources, [contact Raily](https://www.raily.ai/contact) to turn it on for your Account.

## Before you start

Ask your Livingdocs admin for two things:

* **The server URL** of your Livingdocs instance, for example `https://server.livingdocs.io`. It must use HTTPS.
* **A project API token** for the project you want to search. The token needs the `public-api:read` and `public-api:config:read` permissions. One token covers one project, so connect each project as its own Source.

See the Livingdocs [Public API guide](https://docs.livingdocs.io/reference/public-api/get-started/) for how to create a project token.

## Connect the project

**1. Open the source list**

Go to **Connect a data source** and choose **Livingdocs** from the **CMS** group.

**2. Name the Source**

In **Name**, enter something your team will recognize, such as the publication or project name.

**3. Enter the server URL**

Paste your instance address into **Livingdocs server URL**.

**4. Paste the token**

Paste the project token into **Access token**.

**5. Choose how often to sync**

Pick a **Sync frequency**: **Every hour** (the default), **Every 6 hours**, **Every 12 hours**, **Every day**, or **Every 2 days**.

**6. Check the connection**

Click outside the **Credentials** box. Raily tests the URL and token against Livingdocs and shows **Verified** when they work. You'll also see a message naming the project it found, for example "Connected to Livingdocs project my-project."

**7. Save**

Click **Create Integration**. The button stays disabled until the credentials show **Verified**.

## What happens next

Raily opens the Source's page and starts the first sync right away. The sync card shows progress as **Syncing** with a count of items that are already searchable. A large project can take a while on the first run.

When the sync finishes, Raily writes the search configuration for the new collection on its own. The card then shows **Last sync** with the number of items added, updated, and removed, plus when the next sync is due.

After that, Raily checks Livingdocs on the schedule you picked. Each sync picks up newly published items, refreshes items that were republished, and removes items that were unpublished. To check right away, click **Resync** on the Source's page. Use **Full reindex** from the menu next to it if search results look wrong and you want every item processed again.

To serve the content to agents, wire the collection to an endpoint.

## What Raily indexes

Raily reads the latest published version of every **article**, **page**, and **data record** in the project. That includes the text in your custom components and the text fields of your data records.

Raily does not index drafts, earlier revisions, or media files such as images and video. An image linked from a document can still appear on its result card.

Each item keeps these details, which show on result cards and which Raily can use to narrow a search:

| Detail | What it holds |
| - | - |
| Title | The document title or headline |
| Author | The author or byline, when the document has one |
| Published date | The visible publication date in Livingdocs |
| Modified date | When the document was last updated or republished |
| Language | The document's language, when set |
| Link | The public URL of the document, when Livingdocs provides one |
| Image | The document's lead or teaser image, when it has one |
| Document type | Article, page, or data record |
| Content type | The Livingdocs content type, such as your own article or page variants |
| Channel | The Livingdocs channel the document belongs to |

Searches can filter on published date, language, document type, content type, and channel.

## Change a connected Source

Open the Source and edit it to replace the access token or change the sync frequency. Leave **Access token** empty to keep the saved token.

You can't change the server URL or the project of a connected Source. To search another Livingdocs instance or project, connect a new Source.

## Next steps

> [card] [Create an AI endpoint](https://docs.raily.ai/concepts/ai-endpoints.md)
>
> Let agents search this source

> [card] [Data Catalog](https://docs.raily.ai/integrations/data-catalog.md)
>
> Review the fields agents filter on


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