> For the complete documentation index, see [llms.txt](https://docs.spice.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.spice.ai/docs/enterprise/deployment/docker.md).

# Docker

Deploy Spice.ai Enterprise using Docker container images.

Enterprise container images are distributed exclusively through the [AWS Marketplace ECR](/docs/enterprise/deployment/aws-marketplace.md) registry. Subscribe to the Spice.ai Enterprise listing on AWS Marketplace, then authenticate with `aws ecr get-login-password` before pulling.

## Prerequisites

* Docker
* AWS CLI (`aws`) installed and configured with credentials for the account subscribed to the [AWS Marketplace](/docs/enterprise/deployment/aws-marketplace.md) listing

## Images

Replace `<repo>` below with either `spiceai-enterprise-byol` (Bring Your Own License) or `spiceai-enterprise-plan` (Marketplace subscription) — see [AWS Marketplace](/docs/enterprise/deployment/aws-marketplace.md) for details. Replace `<version>` with the release to deploy, such as `2.3.2`.

| Image                                                                                        | Description                                                                                                      |
| -------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| `709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/<repo>:<version>-enterprise-models`   | Default distribution: data connectors, accelerators, search, and AI/ML model inference                           |
| `709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/<repo>:<version>-enterprise`          | Data-only distribution: excludes AI/ML model inference                                                           |
| `709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/<repo>:<version>-enterprise-jemalloc` | jemalloc [allocator variant](/docs/enterprise/getting-started/distributions.md#allocator-variants), from `2.2.1` |

{% hint style="info" %}
Marketplace tags are versioned and immutable: an existing tag is never repointed, and there is no `latest` tag. Every deployment names the release it runs.
{% endhint %}

## Pull an Image

```bash
aws ecr get-login-password --region us-east-1 \
  | docker login --username AWS --password-stdin 709825985650.dkr.ecr.us-east-1.amazonaws.com

docker pull 709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol:2.3.2-enterprise-models
```

## Run

```bash
docker run -p 8090:8090 -p 50051:50051 -p 9090:9090 \
  709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol:2.3.2-enterprise-models \
  --http 0.0.0.0:8090 \
  --metrics 0.0.0.0:9090 \
  --flight 0.0.0.0:50051
```

### With a Spicepod Configuration

Mount a Spicepod YAML file into the container:

```bash
docker run -p 8090:8090 -p 50051:50051 -p 9090:9090 \
  -v $(pwd)/spicepod.yaml:/app/spicepod.yaml \
  709825985650.dkr.ecr.us-east-1.amazonaws.com/spice-ai/spiceai-enterprise-byol:2.3.2-enterprise-models
```

## Exposed Ports

| Port    | Protocol | Description         |
| ------- | -------- | ------------------- |
| `8090`  | HTTP     | HTTP/SQL API        |
| `50051` | gRPC     | Apache Arrow Flight |
| `9090`  | HTTP     | Prometheus metrics  |

## Image Details

Enterprise images are built `FROM scratch` with a minimal filesystem containing:

* The `spiced` binary
* CA certificates
* Timezone database
* Required shared libraries

The container runs as UID 65534 (nobody) for security.

### Environment Variables

| Variable        | Default                              |
| --------------- | ------------------------------------ |
| `HOME`          | `/app`                               |
| `HF_HOME`       | `/.cache/huggingface`                |
| `SSL_CERT_FILE` | `/etc/ssl/certs/ca-certificates.crt` |
| `SSL_CERT_DIR`  | `/etc/ssl/certs`                     |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.spice.ai/docs/enterprise/deployment/docker.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.