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

# Docling integration

[Back to list of integrations](https://koreai.mintlify.site/agent-platform/integrations/enterprise-systems.md)

Use the Docling integration to let agents and workflows extract Markdown, tables, images, and page text from documents. Docling needs no credentials.

| Authentication | Actions | Workflow triggers |
| - | - | - |
| None | [1](#supported-actions) | None |

## Supported actions

Actions are Docling operations that an agent runs as Action Tools during a conversation. You can also run them from an [Integration node](https://koreai.mintlify.site/agent-platform/workflows.md#integration-node) in a workflow.

| Action | Use it to |
| - | - |
| [Extract Document](#extract-document) | Extract structured content from a public document URL. |

## Set up the integration

**1. Create the auth profile**

In **Integrations**, select **Docling** > **Connect**. On **Project Auth Profiles**, select **New Profile** > **Integration Profile** > **Docling** > **Continue**. Enter a **Profile Name**, and select **Create Profile**. The **Auth Type** is `none`.

**2. Create the action tool**

In **Tools**, select **New Tool** > **Action** > **Docling** > **Continue**. Select the **Action** and **Auth Profile**, set parameter defaults (leave a value empty for the agent to supply at runtime), and select **Create Tool**. Then [assign the tool to an agent](https://koreai.mintlify.site/agent-platform/tools/actions.md#assign-an-action-to-an-agent).

## Action reference

> [accordion] Extract Document
>
> | Parameter | Type | Description |
> | - | - | - |
> | `fileUrl` | string | Public HTTP(S) URL of the document. |
> | `extractImages` | boolean | Includes images. Default: `True`. |
> | `extractTables` | boolean | Includes tables. Default: `True`. |
> | `ocrEnabled` | boolean | Runs OCR on scanned pages. Default: `True`. |
> | `language` | string | ISO 639-1 language hint, for example `en`. |
> | `ocrLanguages` | array | OCR language hints. RapidOCR supports English and Chinese aliases. |
> | `timeout` | number | Maximum seconds, from 5 to 1800. Default: 60. |

## Troubleshoot common issues

| Issue | Resolution |
| - | - |
| The document can't be downloaded | Use a public URL that returns the file directly. |
| Scanned text is missing | Keep `ocrEnabled` on, and set `ocrLanguages` for the document language. |
| Extraction times out | Increase `timeout`, or split large documents. |

**Related articles:**

* [Auth profiles](https://koreai.mintlify.site/agent-platform/administration/integrations-settings.md#auth-profiles)
* [Action Tools](https://koreai.mintlify.site/agent-platform/tools/actions.md)
* [Azure Document Intelligence integration](https://koreai.mintlify.site/agent-platform/integrations/enterprise-systems/azure-document-intelligence)
* [Amazon Textract integration](https://koreai.mintlify.site/agent-platform/integrations/enterprise-systems/amazon-textract)


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