Automated sync from private repo (2026-04-09)

.github/.sync-sha

@@ -1 +1 @@
-47eb7873d1c3fe6155df55eb39d8bc107f47db46
+154cef9a84b8bdd6966acebaced70f9a5a0b3d46

samples/python/foundry-models/model-router/.env.sample

@@ -0,0 +1,4 @@
+# Azure OpenAI resource endpoint (used by Chat Completions and Responses examples)
+AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/
+AZURE_OPENAI_API_KEY=your-api-key-here
+MODEL_DEPLOYMENT_NAME=model-router

samples/python/foundry-models/model-router/README.md

@@ -0,0 +1,87 @@
+# Foundry Model Router — API & SDK Samples
+
+Simple "Hello World" Python examples showing how to use [Foundry Model Router](https://learn.microsoft.com/azure/foundry/openai/how-to/model-router) across different Azure OpenAI APIs and SDKs.
+
+Model Router is a deployable AI chat model in Azure AI Foundry that **automatically selects the best underlying LLM** for each prompt in real time. It delivers high performance and cost savings from a single deployment — you use it just like any other chat model.
+
+## Examples
+
+| Folder | API | Auth | Description |
+|--------|-----|------|-------------|
+| [`chat-completions/`](chat-completions/) | Chat Completions | API Key | Basic single-prompt chat completion via `AzureOpenAI` client |
+| [`foundry-responses-sdk/`](foundry-responses-sdk/) | Foundry SDK | Entra ID | Uses `AIProjectClient` → `get_openai_client()` → Responses API |
+
+## Prerequisites
+
+- **Python 3.9+**
+- **Azure subscription** with an Azure OpenAI resource
+- **Model Router deployment** — deploy `model-router` from the model catalog in [Microsoft Foundry](https://ai.azure.com/)
+- For the Foundry SDK example only: **Azure CLI** installed and logged in (`az login`)
+
+## Setup
+
+1. **Create a virtual environment** (recommended)
+
+   ```bash
+   python -m venv .venv
+   # Windows
+   .venv\Scripts\activate
+   # macOS/Linux
+   source .venv/bin/activate
+   ```
+
+2. **Install dependencies**
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **Create your `.env` file**
+
+   ```bash
+   cp .env.sample .env
+   ```
+
+   Edit `.env` with your values:
+
+   ```
+   AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/
+   AZURE_OPENAI_API_KEY=your-api-key-here
+   MODEL_DEPLOYMENT_NAME=model-router
+   AZURE_AI_PROJECT_ENDPOINT=https://your-ai-services-account-name.services.ai.azure.com/api/projects/your-project-name
+   ```
+
+## Run the Examples
+
+### Chat Completions API
+
+```bash
+python model-router-chat-completions.py
+```
+
+### Foundry Responses SDK (Entra ID)
+
+```bash
+az login
+python model-router-foundry-responses-sdk.py
+```
+
+## What to Expect
+
+Each example prints:
+- **Which underlying model** was selected by the router (e.g. `gpt-4.1-mini-2025-04-14`)
+- **The model's response** to the prompt
+- Token usage
+
+The `model` field in the response reveals which LLM the router chose. You control routing behavior (Balanced / Quality / Cost) at deployment time in the Foundry portal — not in code.
+
+## Resources
+
+- [Model Router documentation](https://learn.microsoft.com/azure/foundry/openai/how-to/model-router)
+- [Model Router concepts](https://learn.microsoft.com/azure/foundry/openai/concepts/model-router)
+- [Azure OpenAI Chat Completions quickstart](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/chatgpt)
+- [Azure AI Projects SDK (PyPI)](https://pypi.org/project/azure-ai-projects/)
+
+## License
+
+MIT

samples/python/foundry-models/model-router/model-router-chat-completions.py

@@ -0,0 +1,54 @@
+"""
+Foundry Model Router - Chat Completions API Example
+
+This example demonstrates how to use Azure OpenAI's Chat Completions API
+with a Foundry Model Router deployment. Model Router automatically selects
+the best underlying LLM for each prompt based on your routing mode
+(Balanced, Quality, or Cost).
+
+Prerequisites:
+  - An Azure OpenAI resource with a "model-router" deployment
+  - A .env file in the repo root with AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_KEY,
+    and MODEL_DEPLOYMENT_NAME
+
+Usage:
+  pip install -r ../requirements.txt
+  python model-router-chat-completions.py
+"""
+
+import os
+from pathlib import Path
+
+from dotenv import load_dotenv
+from openai import AzureOpenAI
+
+# Load environment variables from .env in the repo root
+load_dotenv(Path(__file__).resolve().parent.parent / ".env", override=True)
+
+endpoint = os.environ["AZURE_OPENAI_ENDPOINT"]
+api_key = os.environ["AZURE_OPENAI_API_KEY"]
+deployment = os.environ["MODEL_DEPLOYMENT_NAME"]
+
+client = AzureOpenAI(
+    azure_endpoint=endpoint,
+    api_key=api_key,
+    api_version="2024-10-21",
+)
+
+response = client.chat.completions.create(
+    model=deployment,
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {
+            "role": "user",
+            "content": "In one sentence, name the most popular tourist destination in Seattle.",
+        },
+    ],
+)
+
+print("--- Chat Completions Response ---")
+print(f"Routed to model: {response.model}")
+print(f"Response:\n{response.choices[0].message.content}")
+print(
+    f"\nUsage: {response.usage.prompt_tokens} prompt + {response.usage.completion_tokens} completion = {response.usage.total_tokens} total tokens"
+)

samples/python/foundry-models/model-router/model-router-foundry-responses.py

@@ -0,0 +1,51 @@
+"""
+Foundry Model Router - Foundry Responses SDK (AIProjectClient) Example
+
+This example demonstrates how to use the Azure AI Projects SDK
+(AIProjectClient) to get an authenticated OpenAI client and call the
+Responses API with a Foundry Model Router deployment.
+
+NOTE: AIProjectClient requires Entra ID authentication (DefaultAzureCredential),
+      not API keys. You must be logged in via `az login` before running this.
+
+Prerequisites:
+  - An Azure AI Foundry project with a "model-router" deployment
+  - Azure CLI installed and logged in (`az login`)
+  - A .env file in the repo root with AZURE_AI_PROJECT_ENDPOINT and
+    MODEL_DEPLOYMENT_NAME
+
+Usage:
+  pip install -r requirements.txt
+  az login
+  python model-router-foundry-responses-sdk.py
+"""
+
+import os
+from pathlib import Path
+
+from azure.ai.projects import AIProjectClient
+from azure.identity import DefaultAzureCredential
+from dotenv import load_dotenv
+
+# Load environment variables from .env in the repo root
+load_dotenv(Path(__file__).resolve().parent.parent / ".env", override=True)
+
+project_endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
+deployment = os.environ["MODEL_DEPLOYMENT_NAME"]
+
+with (
+    DefaultAzureCredential() as credential,
+    AIProjectClient(endpoint=project_endpoint, credential=credential) as project_client,
+    project_client.get_openai_client() as openai_client,
+):
+    response = openai_client.responses.create(
+        model=deployment,
+        input="In one sentence, name the most popular tourist destination in Seattle.",
+    )
+
+    print("--- Foundry Responses SDK Output ---")
+    print(f"Routed to model: {response.model}")
+    print(f"Response:\n{response.output_text}")
+    print(
+        f"\nUsage: {response.usage.input_tokens} input + {response.usage.output_tokens} output = {response.usage.total_tokens} total tokens"
+    )

samples/python/foundry-models/model-router/requirements.txt

@@ -0,0 +1,4 @@
+openai>=1.75.0
+python-dotenv
+azure-ai-projects>=2.0.0
+azure-identity

samples/python/foundry-models/model-router/sample.yaml

@@ -0,0 +1,5 @@
+name: Model Router Quickstart with Chat Completions & Foundry Responses SDK
+description: Basic quickstart sample demonstrating the use of Model Router with Foundry APIs and SDKs.
+
+build: "pip install -r requirements.txt"
+validate: "python -m py_compile *.py"