You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/container-apps/ai-integration.md
+11-9Lines changed: 11 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,45 +4,47 @@ description: Examples for running AI workloads in Azure Container Apps, includin
4
4
author: jefmarti
5
5
ms.author: jefmarti
6
6
ms.service: azure-container-apps
7
-
ms.date: 07/31/2025
7
+
ms.date: 10/03/2025
8
8
---
9
9
10
-
# AI Integration with Azure Container Apps
10
+
# AI integration with Azure Container Apps
11
11
12
12
Azure Container Apps is a serverless container platform that simplifies the deployment and scaling of microservices and AI-powered applications. With native support for GPU workloads, seamless integration with Azure AI services, and flexible deployment options, it is an ideal platform for building intelligent, cloud-native solutions.
13
13
14
14
15
-
## GPU-Powered Inference
15
+
## GPU-powered inference
16
16
17
17
Use GPU accelerated workload profiles to meet a variety of your AI workload needs, including:
18
18
19
-
-**Serverless GPUs**: Ideal for variable traffic scenarios and cost-sensitive inference workloads.
20
-
-**Dedicated GPUs**: Best for continuous, low-latency inference scenarios.
21
-
-**Scale to zero**: Automatically scale down idle GPU resources to minimize costs.
19
+
-**[Serverless GPUs](https://learn.microsoft.com/azure/container-apps/gpu-serverless-overview)**: Ideal for variable traffic scenarios and cost-sensitive inference workloads.
20
+
-**Dedicated GPUs**: best for continuous, low-latency inference scenarios.
21
+
-**Scale to zero**: automatically scale down idle GPU resources to minimize costs.
22
22
23
23
## Dynamic sessions for AI-generated code
24
24
25
25
Dynamic Sessions provide a secure, isolated environment for executing AI-generated code. Perfect for scenarios like sandboxed execution, code evaluation, or AI agents.
26
26
27
27
Supported session types include:
28
-
- Code interpreters
29
-
- Custom containers
28
+
-**[Code interpreters](https://learn.microsoft.com/azure/container-apps/sessions-code-interpreter)**: a platform-managed container that supports executing code in multiple programming languages, including Python and JavaScript.
29
+
-**[Custom containers](https://learn.microsoft.com/azure/container-apps/sessions-custom-container)**: create a sessions pool using a custom container for specialized workloads or additional language support.
30
30
31
31
## Deploying Azure AI Foundry models
32
32
33
33
Azure Container Apps integrates with Azure AI Foundry, which enables you to deploy curated AI models directly into your containerized environments. This integration simplifies model deployment and management, making it easier to build intelligent applications on Container Apps.
34
34
35
35
### Sample projects
36
36
37
-
The following are a few examples that demonstrate AI integration with Azure Container Apps. These samples showcase various AI capabilities, including OpenAI integration, multi-agent coordination, and retrieval-augmented generation (RAG) using Azure AI Search.
37
+
The following are a few examples that demonstrate AI integration with Azure Container Apps. These samples showcase various AI capabilities, including OpenAI integration, multi-agent coordination, and retrieval-augmented generation (RAG) using Azure AI Search. For more samples, visit the [template library](https://azure-sdk.github.io/awesome-azd/?name=azure+container+apps)
38
38
39
39
| Sample | Description |
40
40
|--------|-------------|
41
41
|[container-apps-openai](https://github.com/Azure-Samples/container-apps-openai)| ChatGPT-like apps using OpenAI, LangChain, ChromaDB, and Chainlit deployed to ACA using Terraform. |
42
42
|[azure-container-apps-ai-mcp](https://github.com/Azure-Samples/azure-container-apps-ai-mcp)| Demonstrates multi-agent coordination using the MCP protocol with Azure OpenAI and GitHub models in ACA. |
43
43
|[openai-mcp-agent-dotnet](https://github.com/Azure-Samples/openai-mcp-agent-dotnet)| .NET-based MCP agent app using Azure OpenAI with a TypeScript MCP server, both hosted on ACA. |
44
44
|[mcp-container-ts](https://github.com/Azure-Samples/mcp-container-ts)| TypeScript-based MCP server template for ACA, ideal for building custom AI toolchains. |
45
+
|[python-code-interpreter](https://github.com/Azure-Samples/aca-python-code-interpreter-session)| Dynamic session for executing Python code in a secure environment. |
0 commit comments