Skip to content

Commit 6f39c26

Browse files
ajeetrainaakristen
ajeetraina
and
akristen
authored
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>
1 parent 048e4d2 commit 6f39c26

7 files changed

Lines changed: 273 additions & 0 deletions

File tree

‎content/guides/lab-agentic-apps.md‎

Lines changed: 77 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,77 @@
1+
---
2+
title: "Lab: Building Agentic Apps with Docker"
3+
linkTitle: "Lab: Building Agentic Apps"
4+
description: |
5+
Build agentic applications with Docker Model Runner, MCP Gateway, and Compose
6+
in this hands-on interactive lab.
7+
summary: |
8+
Hands-on lab: Build agentic apps with Docker Model Runner, MCP Gateway, and
9+
Compose. Learn about models, tools, and agentic frameworks.
10+
keywords: AI, Docker, Model Runner, MCP Gateway, agentic apps, lab, labspace
11+
aliases:
12+
- /labs/docker-for-ai/agentic-apps/
13+
params:
14+
tags: [ai, labs]
15+
time: 20 minutes
16+
resource_links:
17+
- title: Docker Model Runner docs
18+
url: /ai/model-runner/
19+
- title: Docker MCP Gateway docs
20+
url: /ai/mcp-gateway/
21+
- title: Labspace repository
22+
url: https://github.com/dockersamples/labspace-agentic-apps-with-docker
23+
---
24+
25+
Get up and running with building agentic applications using Compose, Docker
26+
Model Runner, and the Docker MCP Gateway. This hands-on lab takes you from
27+
understanding AI models to building complete agentic applications.
28+
29+
## What you'll learn
30+
31+
This lab covers three core areas of agentic application development:
32+
33+
**Models**: What models are, how to interact with them, configuring Docker
34+
Model Runner in Compose, and writing code that connects to the Model Runner
35+
36+
**Tools**: Understanding tools and how they work, how MCP (Model Context
37+
Protocol) fits in, configuring the Docker MCP Gateway, and connecting to the
38+
MCP Gateway in code
39+
40+
**Code**: What agentic frameworks are, defining models and tools in a Compose
41+
file, and configuring your app to use those models and tools
42+
43+
## Modules
44+
45+
| # | Module | Description |
46+
|---|--------|-------------|
47+
| 1 | Introduction | Overview of agentic applications and the Docker AI stack |
48+
| 2 | Understanding Model Interactions | Learn how to interact with AI models |
49+
| 3 | The Docker Model Runner | Configure and use Docker Model Runner with Compose |
50+
| 4 | Understanding Tools and MCP | Deep dive into tools, tool calling, and MCP |
51+
| 5 | The Docker MCP Gateway | Set up and configure the MCP Gateway |
52+
| 6 | Putting It All Together | Build a complete agentic application |
53+
| 7 | Conclusion | Summary and next steps |
54+
55+
## Prerequisites
56+
57+
- Install the latest version of Docker Desktop
58+
- Enable **Docker Model Runner** by going into Settings in Docker Desktop, choosing AI, then selecting Docker Model Runner
59+
- Pull the Gemma 3 model before launching by running this command:
60+
61+
```console
62+
$ docker model pull ai/gemma3
63+
```
64+
65+
## Launch the lab
66+
67+
Start the labspace:
68+
69+
```console
70+
$ docker compose -f oci://dockersamples/labspace-agentic-apps-with-docker up -d
71+
```
72+
73+
Then open your browser to [http://localhost:3030](http://localhost:3030).
74+
75+
> [!NOTE]
76+
>
77+
> It may take a little while to start due to the AI model download.

‎content/guides/lab-cagent.md‎

Lines changed: 64 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
---
2+
title: "Lab: Getting Started with cagent"
3+
linkTitle: "Lab: Getting Started with cagent"
4+
description: |
5+
Build intelligent multi-agent teams with cagent and Docker in this hands-on
6+
interactive lab.
7+
summary: |
8+
Hands-on lab: Create, share, and orchestrate intelligent AI agents using
9+
cagent, MCP Toolkit, and Docker.
10+
keywords: AI, Docker, cagent, agents, multi-agent, MCP Toolkit, lab, labspace
11+
aliases:
12+
- /labs/docker-for-ai/cagent/
13+
params:
14+
tags: [ai, labs]
15+
time: 20 minutes
16+
resource_links:
17+
- title: cagent documentation
18+
url: https://github.com/docker/cagent
19+
- title: Docker MCP Toolkit
20+
url: https://docs.docker.com/ai/mcp-catalog-and-toolkit/toolkit/
21+
- title: Labspace repository
22+
url: https://github.com/ajeetraina/labspace-cagent
23+
---
24+
25+
This lab walks you through building intelligent agents with cagent. You'll learn beginner
26+
agent concepts, then build sophisticated multi-agent teams that handle complex
27+
real-world tasks. Learn how to create, share, and orchestrate AI agents with
28+
Docker.
29+
30+
## What you'll learn
31+
32+
- Create simple agents with cagent
33+
- Use built-in generic agentic tools for common tasks
34+
- Integrate MCP servers from the MCP Toolkit
35+
- Share agents using the Docker Registry
36+
- Build multi-agent systems for complex workflows
37+
- Use Docker Model Runner with cagent (preview)
38+
39+
## Modules
40+
41+
| # | Module | Description |
42+
|---|--------|-------------|
43+
| 1 | Introduction | Overview of cagent and intelligent agent concepts |
44+
| 2 | Getting Started | Create your first agent with cagent |
45+
| 3 | Using Built-in Tools | Leverage the generic agentic tools in cagent |
46+
| 4 | Using MCP | Integrate MCP servers from the MCP Toolkit |
47+
| 5 | Sharing Agents | Package and share agents via Docker Registry |
48+
| 6 | Introduction to Sub-agents | Build multi-agent systems with sub-agent orchestration |
49+
| 7 | Conclusion | Summary and next steps |
50+
51+
## Prerequisites
52+
53+
- Latest version of Docker Desktop
54+
- Basic familiarity with Docker
55+
56+
## Launch the lab
57+
58+
Start the labspace:
59+
60+
```console
61+
$ docker compose -f oci://dockersamples/labspace-cagent up -d
62+
```
63+
64+
Then open your browser to [http://localhost:3030](http://localhost:3030).

‎content/guides/lab-docker-for-ai-redirect.md‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
---
2+
title: Docker for AI Labs
3+
type: redirect
4+
target: /guides/?tags=labs
5+
aliases:
6+
- /labs/
7+
- /labs/docker-for-ai/
8+
---

‎content/guides/lab-fine-tuning.md‎

Lines changed: 56 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
---
2+
title: "Lab: Fine-Tuning Local Models"
3+
linkTitle: "Lab: Fine-Tuning Models"
4+
description: |
5+
Fine-tune AI models using Docker Offload, Docker Model Runner, and Unsloth
6+
in this hands-on interactive lab.
7+
summary: |
8+
Hands-on lab: Fine-tune, validate, and share custom AI models using Docker
9+
Offload, Unsloth, and Docker Model Runner.
10+
keywords: AI, Docker, fine-tuning, Docker Offload, Unsloth, Model Runner, lab, labspace
11+
aliases:
12+
- /labs/docker-for-ai/fine-tuning/
13+
params:
14+
tags: [ai, labs]
15+
time: 20 minutes
16+
resource_links:
17+
- title: Docker Model Runner docs
18+
url: /ai/model-runner/
19+
- title: Labspace repository
20+
url: https://github.com/dockersamples/labspace-fine-tuning
21+
---
22+
23+
This lab provides a hands-on walkthrough of fine-tuning AI models using Docker
24+
Offload, Docker Model Runner, and Unsloth. Learn how to customize models for
25+
your specific use case, validate the results, and share them via Docker Hub.
26+
27+
## What you'll learn
28+
29+
- Use Docker Offload to fine-tune a model with GPU acceleration
30+
- Package and share the fine-tuned model on Docker Hub
31+
- Run the custom model with Docker Model Runner
32+
- Understand the end-to-end workflow from training to deployment
33+
34+
## Modules
35+
36+
| # | Module | Description |
37+
|---|--------|-------------|
38+
| 1 | Introduction | Overview of fine-tuning concepts and the Docker AI stack |
39+
| 2 | Fine-Tuning with Docker Offload | Run fine-tuning using Unsloth and Docker Offload |
40+
| 3 | Validate and Publish | Test the fine-tuned model and publish to Docker Hub |
41+
| 4 | Conclusion | Summary, key takeaways, and next steps |
42+
43+
## Prerequisites
44+
45+
- Docker Desktop with Docker Offload enabled
46+
- GPU access with Docker Offload cloud resources
47+
48+
## Launch the lab
49+
50+
Ensure you have Docker Offload running, then start the labspace:
51+
52+
```console
53+
$ docker compose -f oci://dockersamples/labspace-fine-tuning up -d
54+
```
55+
56+
Then open your browser to [http://localhost:3030](http://localhost:3030).

‎content/guides/lab-mcp-gateway.md‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,63 @@
1+
---
2+
title: "Lab: Docker MCP Gateway"
3+
linkTitle: "Lab: Docker MCP Gateway"
4+
description: |
5+
Run containerized MCP servers safely and securely with the Docker MCP Gateway
6+
in this hands-on interactive lab.
7+
summary: |
8+
Hands-on lab: Configure, secure, and connect MCP servers to your agentic
9+
applications using the Docker MCP Gateway.
10+
keywords: AI, Docker, MCP, MCP Gateway, MCP servers, lab, labspace
11+
aliases:
12+
- /labs/docker-for-ai/mcp-gateway/
13+
params:
14+
tags: [ai, labs]
15+
time: 20 minutes
16+
resource_links:
17+
- title: Docker MCP Gateway docs
18+
url: /ai/mcp-gateway/
19+
- title: MCP Gateway GitHub
20+
url: https://github.com/docker/mcp-gateway
21+
- title: Labspace repository
22+
url: https://github.com/dockersamples/labspace-mcp-gateway
23+
---
24+
25+
This lab provides a comprehensive, hands-on overview of the Docker MCP Gateway,
26+
which enables you to run containerized MCP servers safely and securely. Learn
27+
how to configure, secure, and connect MCP servers to your agentic applications.
28+
29+
## What you'll learn
30+
31+
- Learn about the Docker MCP Gateway and its architecture
32+
- Run the MCP Gateway with a simple MCP server
33+
- Inject secrets securely into MCP servers
34+
- Filter tools to reduce noise and save tokens
35+
- Connect the MCP Gateway to your application using popular agentic frameworks
36+
- Configure and use custom MCP servers
37+
38+
## Modules
39+
40+
| # | Module | Description |
41+
|---|--------|-------------|
42+
| 1 | Introduction | Overview of the MCP Gateway and why it matters |
43+
| 2 | Adding a Simple MCP Server | Get started with a basic MCP server configuration |
44+
| 3 | Adding a Complex MCP Server | Configure MCP servers with secrets and advanced options |
45+
| 4 | Filtering Available Tools | Reduce noise and save tokens by filtering tool availability |
46+
| 5 | Connecting MCP Gateway to Your App | Integrate the MCP Gateway with agentic frameworks |
47+
| 6 | Using a Custom MCP Server | Build and run your own custom MCP server |
48+
| 7 | Conclusion | Summary and next steps |
49+
50+
## Prerequisites
51+
52+
- The latest version of Docker Desktop with Docker Model Runner enabled
53+
- Basic familiarity with Docker and Docker Compose
54+
55+
## Launch the lab
56+
57+
Start the labspace:
58+
59+
```console
60+
$ docker compose -f oci://dockersamples/labspace-mcp-gateway up -d
61+
```
62+
63+
Then open your browser to [http://localhost:3030](http://localhost:3030).

‎content/tags/labs/_index.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
---
2+
title: Labs
3+
---

‎data/tags.yaml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,8 @@ faq:
2424
title: FAQ
2525
frameworks:
2626
title: Frameworks
27+
labs:
28+
title: Labs
2729
networking:
2830
title: Networking
2931
observability:

0 commit comments

Comments
 (0)