Self-host Docling Serve with Levelrail
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.
- Authordocling-project
- LicenceMIT
- Memory3 GiB
- Archarm64
- Services1
How to self-host Docling Serve
-
Pull the images
One image is pulled on your server.
Show images
ghcr.io/docling-project/docling-serve-cpu:v1.38.2
-
Create the app
One service starts in a single Compose app, on port 5001.
-
Fill in the secrets
2 settings are preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
Docling Serve requirements
- Memory
- About 3 GiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 5001
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- MIT, permissive license
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then Docling Serve. New to Levelrail? Install it on a fresh VPS first.
docker pull ghcr.io/glincker/levelrail:latest Then levelrail-cli login --device. See Getting started and the Docling Serve docs page.
Deploy Docling Serve your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy Docling Serve from the CLI
levelrail-cli templates install docling-serve --name my-docling-serve Deploy Docling Serve with the API
curl -X POST -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
https://levelrail.example.com/api/v1/service-templates/docling-serve/install \
-d '{
"name": "my-docling-serve"
}' Docling Serve configuration
Docling Serve services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| docling | ghcr.io/docling-project/docling-serve-cpu:v1.38.2 | 5001 | none |
Docling Serve environment variables
| Variable | Service | Value |
|---|---|---|
| DOCLING_SERVE_ENABLE_UI | docling | Preset by the template |
| TZ | docling | Preset by the template |
Ports and volumes
- Ports
- 5001
- Volumes
- none
Docling Serve FAQ
How much memory does Docling Serve need?
The catalog lists about 3 GiB of memory for Docling Serve.
Does Docling Serve run on arm64?
For Docling Serve, an arm64 image is published; amd64 is image published.
What licence is Docling Serve under?
Docling Serve is licensed under MIT, which is permissive, with few conditions on reuse.
Does Docling Serve need configuration before it starts?
No. The template fills in its own defaults.
Which ports does Docling Serve use?
Docling Serve listens on port 5001 inside the stack.
Can I deploy Docling Serve on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list has an entry with the id docling-serve for this app, so check that entry as well. Dokku deploys container images with its own commands, so the pinned image ghcr.io/docling-project/docling-serve-cpu:v1.38.2 is what you deploy there.