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

# Self-host Docling Serve with Docker

> An API server that converts PDFs, Office files and images into Markdown, JSON or text for RAG pipelines, using the Docling library on CPU. MIT licensed. The image is about 5 GB, the interactive UI is at /ui and the API docs at /docs. There is no login, so keep it private or behind an auth proxy.

An API server that converts PDFs, Office files and images into Markdown, JSON or text for RAG pipelines, using the Docling library on CPU. MIT licensed. The image is about 5 GB, the interactive UI is at /ui and the API docs at /docs. There is no login, so keep it private or behind an auth proxy.

This page describes the Levelrail template for Docling Serve (AI). It deploys the services below as one Docker Compose app on your own server. Project site: [https://github.com/docling-project/docling-serve](https://github.com/docling-project/docling-serve).

Recommended memory: about 3072 MiB.

## Services, ports and volumes

| Service | Image | Container ports | Volumes |
| - | - | - | - |
| `docling` | `ghcr.io/docling-project/docling-serve-cpu:v1.38.2` | 5001 | none |

## Environment variables

| Service | Variable | Value |
| - | - | - |
| `docling` | `DOCLING_SERVE_ENABLE_UI` | Preset in the template |
| `docling` | `TZ` | Preset in the template |

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

## Security and requirements

Level: **Standard**.

What this template needs:

* Nothing beyond a standard container: no extra privileges, host mounts or published ports.

What Levelrail adds around it:

* Automatic HTTPS and an ingress shield in front of every domain.
* Deploys are gated on the health check before traffic switches.
* One-step rollback to the previous revision.
* Exposure report shows what is reachable from outside.
* Host firewall rules managed for published ports.

## Deploy Docling Serve with Levelrail

In the dashboard, open **Apps**, choose **New app**, then **Browse templates**, and select Docling Serve. Review the Compose body and deploy.

With the CLI:

```bash theme={"dark"}
levelrail-cli templates deploy docling-serve --name my-docling-serve
```

See the [service template catalog](https://docs.levelrail.com/templates-and-registry.md) for how templates work, and [Getting started](https://docs.levelrail.com/getting-started.md) if you have not installed Levelrail yet.

## More AI templates

* [AnythingLLM](https://docs.levelrail.com/self-host/anythingllm.md)
* [ComfyUI](https://docs.levelrail.com/self-host/comfyui.md)
* [Crawl4AI](https://docs.levelrail.com/self-host/crawl4ai.md)
* [Flowise](https://docs.levelrail.com/self-host/flowise.md)
* [Flowise (Postgres + Qdrant)](https://docs.levelrail.com/self-host/flowise-postgres.md)

All templates are listed in the [self-host gallery](https://docs.levelrail.com/self-host.md).


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