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

# Deploy Docling Serve

> Set up Docling Serve and connect its dependencies with Spring Winter.

## Deploy with an agent

Copy agent prompt

Help me deploy Docling Serve. Read [https://docs.springwinter.dev/deploy/open-source/docling-serve](https://docs.springwinter.dev/deploy/open-source/docling-serve.md), [https://github.com/docling-project/docling-serve](https://github.com/docling-project/docling-serve), and [https://docs.springwinter.dev/api-reference/agents](https://docs.springwinter.dev/api-reference/agents.md). Fetch the public OpenAPI specification from my Spring Winter origin. Use my local SPRINGWINTER\_TOKEN or existing SPRINGWINTER\_API\_TOKEN. Keep credentials out of chat, logs and source.

Confirm my project, AWS connection, Region and budget. Pin a release. Check its required services, container port, health path, network access and durable storage. Data requirements for this deployment: No SQL database for the single-container conversion service.

1. Select a pinned CPU image from quay.io/docling-project/docling-serve. Size the container for model loading and your expected document sizes.
2. Deploy a Spring Winter web server on port 5001. Configure trusted access before accepting uploads. Keep optional playground access disabled unless your team needs it.
3. Submit work and retrieve results within the service’s documented retention window. Save results to your application’s durable storage. If you choose a distributed processing engine, provision its dependencies first using the release’s instructions.
4. Wait for the HTTP service to be healthy before connecting your ingestion pipeline.

Show me the planned resources, database and migration order, secret names and estimated cost. Identify components that require separate hosting. Wait for approval before making changes. Use documented Spring Winter operations and wait for each workflow to finish. Convert a non-sensitive PDF and inspect the resulting text or structured output. Report resource links and anything you could not verify.

## Before you start

[Connect your AWS account](https://docs.springwinter.dev/connect-aws.md) and choose a project. Review the [upstream deployment instructions](https://github.com/docling-project/docling-serve) for the release you plan to pin.

## Data dependencies

No SQL database for the single-container conversion service.

## Deployment order

1. Select a pinned CPU image from `quay.io/docling-project/docling-serve`. Size the container for model loading and your expected document sizes.
2. Deploy a Spring Winter web server on port 5001. Configure trusted access before accepting uploads. Keep optional playground access disabled unless your team needs it.
3. Submit work and retrieve results within the service’s documented retention window. Save results to your application’s durable storage. If you choose a distributed processing engine, provision its dependencies first using the release’s instructions.
4. Wait for the HTTP service to be healthy before connecting your ingestion pipeline.

Use [Runtime variables](https://docs.springwinter.dev/concepts/environment-variables.md) for runtime credentials. For a [Spring Winter web server](https://docs.springwinter.dev/deploy/web-servers.md), set an app-supported health path that returns HTTP 200 without credentials. Check **History** before running the application check.

## Verify the deployment

Convert a non-sensitive PDF and inspect the resulting text or structured output.


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