Self-host Paperless-AI with Levelrail
Adds automatic tagging, titles and document chat to a Paperless-ngx server using your choice of AI provider. MIT licensed. A setup wizard collects the Paperless address and token.
- Authorclusterzx
- LicenceMIT
- Memory512 MiB
- Services1
How to self-host Paperless-AI
-
Pull the images
One image is pulled on your server.
Show images
clusterzx/paperless-ai:4.0.0
-
Create the app
One service starts in a single Compose app, with 1 named volume mount for your data, on port 3000.
-
Fill in the secrets
1 setting is 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.
After the first start
- Run the setup wizard with the address and API token of your Paperless-ngx server.
Paperless-AI requirements
- Memory
- About 512 MiB
- Architectures
- amd64 unknown, arm64 unknown
- Ports
- 3000
- 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 Paperless-AI. 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 Paperless-AI docs page.
Deploy Paperless-AI your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy Paperless-AI from the CLI
levelrail-cli templates deploy paperless-ai --name my-paperless-ai Deploy Paperless-AI with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/paperless-ai/deploy Paperless-AI configuration
Paperless-AI services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| paperless-ai | clusterzx/paperless-ai:4.0.0 | 3000 | data -> /app/data |
Paperless-AI environment variables
| Variable | Service | Value |
|---|---|---|
| PAPERLESS_AI_PORT | paperless-ai | Preset by the template |
Ports and volumes
- Ports
- 3000
- Volumes
- 1 named mount: data -> /app/data
Paperless-AI FAQ
How much memory does Paperless-AI need?
The catalog lists about 512 MiB of memory for Paperless-AI.
Does Paperless-AI run on arm64?
For Paperless-AI, arm64 support is not confirmed; amd64 is unknown.
What licence is Paperless-AI under?
Paperless-AI is licensed under MIT, which is permissive, with few conditions on reuse.
Does Paperless-AI need configuration before it starts?
No. The template fills in its own defaults.
Which ports does Paperless-AI use?
Paperless-AI listens on port 3000 inside the stack.
Where does Paperless-AI keep its data?
In a named volume: data mounted at /app/data.
Can I deploy Paperless-AI on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list we compared does not have an entry with the same id for Paperless-AI, so on Dokploy you would use a Docker Compose application with the file from this page. Dokku deploys container images with its own commands, so the pinned image clusterzx/paperless-ai:4.0.0 is what you deploy there.