docs/content/reference/compose-file/models.md at 4cedf2e052d4a0b83a9bb469541bfb7ccc225a72

mirror of https://github.com/docker/docs.git synced 2026-10-23 18:09:02 +03:00

Files

David Karlsson d511fb5636 docs: move AI Compose and MCP docs into product sections (#26180 )

Baby step towards cleaning up the sidenav for the ai/agents section.

<img width="306" height="304" alt="image"
src="https://github.com/user-attachments/assets/57ebd1df-9c7f-4ee8-a84f-a61ffec2cd90"
/>


Moves “Use AI models in Compose” into Compose → How-tos and MCP Catalog
and Toolkit into Docker Desktop → Features and capabilities, removing
both entries from the top-level AI and agents sidebar group.

Updates internal source links and preserves existing public URLs. Scoped
lint and a Hugo build passed; rendered sidebar ancestry, MCP page URLs,
and images were checked locally.

Generated by Codex

2026-09-25 11:42:07 +02:00

1.9 KiB

Raw Blame History

title, description, keywords, weight

title	description	keywords	weight
Models	Learn about the models top-level element	compose, compose specification, models, compose file reference	120

The top-level models section declares AI models that are used by your Compose application. These models are typically pulled as OCI artifacts, run by a model runner, and exposed as an API that your service containers can consume.

Services can only access models when explicitly granted by a models attribute within the services top-level element.

Examples

Example 1

services:
  app:
    image: app
    models:
      - ai_model


models:
  ai_model:
    model: ai/model

In this basic example:

The app service uses the ai_model.
The ai_model is defined as an OCI artifact (ai/model) that is pulled and served by the model runner.
Docker Compose injects connection info, for example AI_MODEL_URL, into the container.

Example 2

services:
  app:
    image: app
    models:
      my_model:
        endpoint_var: MODEL_URL

models:
  my_model:
    model: ai/model
    context_size: 1024
    runtime_flags: 
      - "--a-flag"
      - "--another-flag=42"

In this advanced setup:

The service app references my_model using the long syntax.
Compose injects the model runner's URL as the environment variable MODEL_URL.

Attributes

model (required): The OCI artifact identifier for the model. This is what Compose pulls and runs via the model runner.
context_size: Defines the maximum token context size for the model.
runtime_flags: A list of raw command-line flags passed to the inference engine when the model is started.

Additional resources

For more examples and information on using model, see Use AI models in Compose

1.9 KiB Raw Blame History