mirror of
https://github.com/docker/docs.git
synced 2026-03-27 06:18:55 +07:00
Add Docker for AI labs to guides section with Labs tag (#24208)
<!--Delete sections as needed -->
## Description
This PR:
- adds new labs tag to `data/tags.yaml` and
`content/tags/labs/_index.md`
- creates 4 single-page lab guides under content/guides/:
- lab-agentic-apps.md (7 modules)
- lab-mcp-gateway.md (7 modules)
- lab-fine-tuning.md (4 modules)
- lab-cagent.md (7 modules)
Labs are filterable at `/guides/?tags=labs`
<!-- Tell us what you did and why -->
## Related issues or tickets
<!-- Related issues, pull requests, or Jira tickets -->
## Reviews
<!-- Notes for reviewers here -->
<!-- List applicable reviews (optionally @tag reviewers) -->
- [ ] Technical review
- [ ] Editorial review
- [ ] Product review
---------
Co-authored-by: Alexa Kristensen <81787716+akristen@users.noreply.github.com>
This commit is contained in:
Ajeet Singh Raina, Docker Captain, ARM Innovator
committed by
GitHub
GitHub
parent
048e4d2861
commit
6f39c26e10
77
content/guides/lab-agentic-apps.md
Normal file
77
content/guides/lab-agentic-apps.md
Normal file
@@ -0,0 +1,77 @@
|
||||
---
|
||||
title: "Lab: Building Agentic Apps with Docker"
|
||||
linkTitle: "Lab: Building Agentic Apps"
|
||||
description: |
|
||||
Build agentic applications with Docker Model Runner, MCP Gateway, and Compose
|
||||
in this hands-on interactive lab.
|
||||
summary: |
|
||||
Hands-on lab: Build agentic apps with Docker Model Runner, MCP Gateway, and
|
||||
Compose. Learn about models, tools, and agentic frameworks.
|
||||
keywords: AI, Docker, Model Runner, MCP Gateway, agentic apps, lab, labspace
|
||||
aliases:
|
||||
- /labs/docker-for-ai/agentic-apps/
|
||||
params:
|
||||
tags: [ai, labs]
|
||||
time: 20 minutes
|
||||
resource_links:
|
||||
- title: Docker Model Runner docs
|
||||
url: /ai/model-runner/
|
||||
- title: Docker MCP Gateway docs
|
||||
url: /ai/mcp-gateway/
|
||||
- title: Labspace repository
|
||||
url: https://github.com/dockersamples/labspace-agentic-apps-with-docker
|
||||
---
|
||||
|
||||
Get up and running with building agentic applications using Compose, Docker
|
||||
Model Runner, and the Docker MCP Gateway. This hands-on lab takes you from
|
||||
understanding AI models to building complete agentic applications.
|
||||
|
||||
## What you'll learn
|
||||
|
||||
This lab covers three core areas of agentic application development:
|
||||
|
||||
**Models**: What models are, how to interact with them, configuring Docker
|
||||
Model Runner in Compose, and writing code that connects to the Model Runner
|
||||
|
||||
**Tools**: Understanding tools and how they work, how MCP (Model Context
|
||||
Protocol) fits in, configuring the Docker MCP Gateway, and connecting to the
|
||||
MCP Gateway in code
|
||||
|
||||
**Code**: What agentic frameworks are, defining models and tools in a Compose
|
||||
file, and configuring your app to use those models and tools
|
||||
|
||||
## Modules
|
||||
|
||||
| # | Module | Description |
|
||||
|---|--------|-------------|
|
||||
| 1 | Introduction | Overview of agentic applications and the Docker AI stack |
|
||||
| 2 | Understanding Model Interactions | Learn how to interact with AI models |
|
||||
| 3 | The Docker Model Runner | Configure and use Docker Model Runner with Compose |
|
||||
| 4 | Understanding Tools and MCP | Deep dive into tools, tool calling, and MCP |
|
||||
| 5 | The Docker MCP Gateway | Set up and configure the MCP Gateway |
|
||||
| 6 | Putting It All Together | Build a complete agentic application |
|
||||
| 7 | Conclusion | Summary and next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Install the latest version of Docker Desktop
|
||||
- Enable **Docker Model Runner** by going into Settings in Docker Desktop, choosing AI, then selecting Docker Model Runner
|
||||
- Pull the Gemma 3 model before launching by running this command:
|
||||
|
||||
```console
|
||||
$ docker model pull ai/gemma3
|
||||
```
|
||||
|
||||
## Launch the lab
|
||||
|
||||
Start the labspace:
|
||||
|
||||
```console
|
||||
$ docker compose -f oci://dockersamples/labspace-agentic-apps-with-docker up -d
|
||||
```
|
||||
|
||||
Then open your browser to [http://localhost:3030](http://localhost:3030).
|
||||
|
||||
> [!NOTE]
|
||||
>
|
||||
> It may take a little while to start due to the AI model download.
|
||||
64
content/guides/lab-cagent.md
Normal file
64
content/guides/lab-cagent.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
title: "Lab: Getting Started with cagent"
|
||||
linkTitle: "Lab: Getting Started with cagent"
|
||||
description: |
|
||||
Build intelligent multi-agent teams with cagent and Docker in this hands-on
|
||||
interactive lab.
|
||||
summary: |
|
||||
Hands-on lab: Create, share, and orchestrate intelligent AI agents using
|
||||
cagent, MCP Toolkit, and Docker.
|
||||
keywords: AI, Docker, cagent, agents, multi-agent, MCP Toolkit, lab, labspace
|
||||
aliases:
|
||||
- /labs/docker-for-ai/cagent/
|
||||
params:
|
||||
tags: [ai, labs]
|
||||
time: 20 minutes
|
||||
resource_links:
|
||||
- title: cagent documentation
|
||||
url: https://github.com/docker/cagent
|
||||
- title: Docker MCP Toolkit
|
||||
url: https://docs.docker.com/ai/mcp-catalog-and-toolkit/toolkit/
|
||||
- title: Labspace repository
|
||||
url: https://github.com/ajeetraina/labspace-cagent
|
||||
---
|
||||
|
||||
This lab walks you through building intelligent agents with cagent. You'll learn beginner
|
||||
agent concepts, then build sophisticated multi-agent teams that handle complex
|
||||
real-world tasks. Learn how to create, share, and orchestrate AI agents with
|
||||
Docker.
|
||||
|
||||
## What you'll learn
|
||||
|
||||
- Create simple agents with cagent
|
||||
- Use built-in generic agentic tools for common tasks
|
||||
- Integrate MCP servers from the MCP Toolkit
|
||||
- Share agents using the Docker Registry
|
||||
- Build multi-agent systems for complex workflows
|
||||
- Use Docker Model Runner with cagent (preview)
|
||||
|
||||
## Modules
|
||||
|
||||
| # | Module | Description |
|
||||
|---|--------|-------------|
|
||||
| 1 | Introduction | Overview of cagent and intelligent agent concepts |
|
||||
| 2 | Getting Started | Create your first agent with cagent |
|
||||
| 3 | Using Built-in Tools | Leverage the generic agentic tools in cagent |
|
||||
| 4 | Using MCP | Integrate MCP servers from the MCP Toolkit |
|
||||
| 5 | Sharing Agents | Package and share agents via Docker Registry |
|
||||
| 6 | Introduction to Sub-agents | Build multi-agent systems with sub-agent orchestration |
|
||||
| 7 | Conclusion | Summary and next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Latest version of Docker Desktop
|
||||
- Basic familiarity with Docker
|
||||
|
||||
## Launch the lab
|
||||
|
||||
Start the labspace:
|
||||
|
||||
```console
|
||||
$ docker compose -f oci://dockersamples/labspace-cagent up -d
|
||||
```
|
||||
|
||||
Then open your browser to [http://localhost:3030](http://localhost:3030).
|
||||
8
content/guides/lab-docker-for-ai-redirect.md
Normal file
8
content/guides/lab-docker-for-ai-redirect.md
Normal file
@@ -0,0 +1,8 @@
|
||||
---
|
||||
title: Docker for AI Labs
|
||||
type: redirect
|
||||
target: /guides/?tags=labs
|
||||
aliases:
|
||||
- /labs/
|
||||
- /labs/docker-for-ai/
|
||||
---
|
||||
56
content/guides/lab-fine-tuning.md
Normal file
56
content/guides/lab-fine-tuning.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
title: "Lab: Fine-Tuning Local Models"
|
||||
linkTitle: "Lab: Fine-Tuning Models"
|
||||
description: |
|
||||
Fine-tune AI models using Docker Offload, Docker Model Runner, and Unsloth
|
||||
in this hands-on interactive lab.
|
||||
summary: |
|
||||
Hands-on lab: Fine-tune, validate, and share custom AI models using Docker
|
||||
Offload, Unsloth, and Docker Model Runner.
|
||||
keywords: AI, Docker, fine-tuning, Docker Offload, Unsloth, Model Runner, lab, labspace
|
||||
aliases:
|
||||
- /labs/docker-for-ai/fine-tuning/
|
||||
params:
|
||||
tags: [ai, labs]
|
||||
time: 20 minutes
|
||||
resource_links:
|
||||
- title: Docker Model Runner docs
|
||||
url: /ai/model-runner/
|
||||
- title: Labspace repository
|
||||
url: https://github.com/dockersamples/labspace-fine-tuning
|
||||
---
|
||||
|
||||
This lab provides a hands-on walkthrough of fine-tuning AI models using Docker
|
||||
Offload, Docker Model Runner, and Unsloth. Learn how to customize models for
|
||||
your specific use case, validate the results, and share them via Docker Hub.
|
||||
|
||||
## What you'll learn
|
||||
|
||||
- Use Docker Offload to fine-tune a model with GPU acceleration
|
||||
- Package and share the fine-tuned model on Docker Hub
|
||||
- Run the custom model with Docker Model Runner
|
||||
- Understand the end-to-end workflow from training to deployment
|
||||
|
||||
## Modules
|
||||
|
||||
| # | Module | Description |
|
||||
|---|--------|-------------|
|
||||
| 1 | Introduction | Overview of fine-tuning concepts and the Docker AI stack |
|
||||
| 2 | Fine-Tuning with Docker Offload | Run fine-tuning using Unsloth and Docker Offload |
|
||||
| 3 | Validate and Publish | Test the fine-tuned model and publish to Docker Hub |
|
||||
| 4 | Conclusion | Summary, key takeaways, and next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Docker Desktop with Docker Offload enabled
|
||||
- GPU access with Docker Offload cloud resources
|
||||
|
||||
## Launch the lab
|
||||
|
||||
Ensure you have Docker Offload running, then start the labspace:
|
||||
|
||||
```console
|
||||
$ docker compose -f oci://dockersamples/labspace-fine-tuning up -d
|
||||
```
|
||||
|
||||
Then open your browser to [http://localhost:3030](http://localhost:3030).
|
||||
63
content/guides/lab-mcp-gateway.md
Normal file
63
content/guides/lab-mcp-gateway.md
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
title: "Lab: Docker MCP Gateway"
|
||||
linkTitle: "Lab: Docker MCP Gateway"
|
||||
description: |
|
||||
Run containerized MCP servers safely and securely with the Docker MCP Gateway
|
||||
in this hands-on interactive lab.
|
||||
summary: |
|
||||
Hands-on lab: Configure, secure, and connect MCP servers to your agentic
|
||||
applications using the Docker MCP Gateway.
|
||||
keywords: AI, Docker, MCP, MCP Gateway, MCP servers, lab, labspace
|
||||
aliases:
|
||||
- /labs/docker-for-ai/mcp-gateway/
|
||||
params:
|
||||
tags: [ai, labs]
|
||||
time: 20 minutes
|
||||
resource_links:
|
||||
- title: Docker MCP Gateway docs
|
||||
url: /ai/mcp-gateway/
|
||||
- title: MCP Gateway GitHub
|
||||
url: https://github.com/docker/mcp-gateway
|
||||
- title: Labspace repository
|
||||
url: https://github.com/dockersamples/labspace-mcp-gateway
|
||||
---
|
||||
|
||||
This lab provides a comprehensive, hands-on overview of the Docker MCP Gateway,
|
||||
which enables you to run containerized MCP servers safely and securely. Learn
|
||||
how to configure, secure, and connect MCP servers to your agentic applications.
|
||||
|
||||
## What you'll learn
|
||||
|
||||
- Learn about the Docker MCP Gateway and its architecture
|
||||
- Run the MCP Gateway with a simple MCP server
|
||||
- Inject secrets securely into MCP servers
|
||||
- Filter tools to reduce noise and save tokens
|
||||
- Connect the MCP Gateway to your application using popular agentic frameworks
|
||||
- Configure and use custom MCP servers
|
||||
|
||||
## Modules
|
||||
|
||||
| # | Module | Description |
|
||||
|---|--------|-------------|
|
||||
| 1 | Introduction | Overview of the MCP Gateway and why it matters |
|
||||
| 2 | Adding a Simple MCP Server | Get started with a basic MCP server configuration |
|
||||
| 3 | Adding a Complex MCP Server | Configure MCP servers with secrets and advanced options |
|
||||
| 4 | Filtering Available Tools | Reduce noise and save tokens by filtering tool availability |
|
||||
| 5 | Connecting MCP Gateway to Your App | Integrate the MCP Gateway with agentic frameworks |
|
||||
| 6 | Using a Custom MCP Server | Build and run your own custom MCP server |
|
||||
| 7 | Conclusion | Summary and next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- The latest version of Docker Desktop with Docker Model Runner enabled
|
||||
- Basic familiarity with Docker and Docker Compose
|
||||
|
||||
## Launch the lab
|
||||
|
||||
Start the labspace:
|
||||
|
||||
```console
|
||||
$ docker compose -f oci://dockersamples/labspace-mcp-gateway up -d
|
||||
```
|
||||
|
||||
Then open your browser to [http://localhost:3030](http://localhost:3030).
|
||||
3
content/tags/labs/_index.md
Normal file
3
content/tags/labs/_index.md
Normal file
@@ -0,0 +1,3 @@
|
||||
---
|
||||
title: Labs
|
||||
---
|
||||
@@ -24,6 +24,8 @@ faq:
|
||||
title: FAQ
|
||||
frameworks:
|
||||
title: Frameworks
|
||||
labs:
|
||||
title: Labs
|
||||
networking:
|
||||
title: Networking
|
||||
observability:
|
||||
|
||||
Reference in New Issue
Block a user