added sk module

buzahid · buzahid · commit 577488ef55ec · 2025-03-17T07:05:35.000-07:00
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/1-introduction.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/1-introduction.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.introduction
+title: Introduction
+metadata:
+  title: Introduction
+  description: Learn how to design multi-agent solutions with Semantic Kernel and Azure AI Foundry.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 2
+content: |
+  [!include[](includes/1-introduction.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/2-understand-agent-framework.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/2-understand-agent-framework.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.understand-agent-framework
+title: Understand the Semantic Kernel Agent Framework
+metadata:
+  title: Understand the Semantic Kernel Agent Framework
+  description: This unit explains the Semantic Kernel Agent Framework.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 6
+content: |
+  [!include[](includes/2-understand-agent-framework.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/4-create-azure-ai-agent.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/4-create-azure-ai-agent.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.create-azure-ai-agent
+title: Create an Azure AI Agent
+metadata:
+  title: Create an Azure AI Agent
+  description: This unit explains how to create an Azure AI Agent with the Semantic Kernel.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 5
+content: |
+  [!include[](includes/4-create-azure-ai-agent.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/5-add-plugins-to-agents.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/5-add-plugins-to-agents.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.add-plugins-to-agents
+title: Add plugins to agents
+metadata:
+  title: Add plugins to agents
+  description: Learn how to add plugins to agents.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 6
+content: |
+  [!include[](includes/5-add-plugins-to-agents.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/6-design-agent-collaboration.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/6-design-agent-collaboration.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.design-agent-collaboration
+title: Add plugins to agents
+metadata:
+  title: Design agent collaboration
+  description: Learn how to design mutli-agent collaboration solutions
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 6
+content: |
+  [!include[](includes/5-design-agent-collaboration.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/7-exercise.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/7-exercise.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.orchestrate-sk-multi-agent-solution.exercise
+title: Exercise - Develop a multi-agent soluton
+metadata:
+  title: Exercise - Develop a multi-agent soluton
+  description: Learn how to build a multi-agent solution. This unit provides a hands-on exercise to develop a multi-agent solution with the Semantic Kernel Agent Framework.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 30
+content: |
+  [!include[](includes/7-exercise.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/8-knowledge-check.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/8-knowledge-check.yml
@@ -0,0 +1,20 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.develop-ai-agent-azure.knowledge-check
+title: Knowledge check
+metadata:
+  title: Knowledge check
+  description: This unit contains a knowledge check which can help learners reinforce their understanding of the material.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 3
+content: |
+quiz:
+  questions:
+  - content: ""  
+    choices:  
+      - content: ""  
+        isCorrect: true  
+        explanation: ""  
+  
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/9-summary.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/9-summary.yml
@@ -0,0 +1,13 @@
+### YamlMime:ModuleUnit
+uid: learn.wwl.develop-ai-agent-azure.summary
+title: Summary
+metadata:
+  title: Summary
+  description: This unit summarizes the key concepts covered in the module, including key features and how to use Azure AI Agent Service.
+  author: buzahid
+  ms.author: buzahid
+  ms.date: 03/14/2025
+  ms.topic: unit
+durationInMinutes: 2
+content: |
+  [!include[](includes/7-summary.md)]
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/1-introduction.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/1-introduction.md
@@ -0,0 +1,8 @@
+TODO fluff intro, devops scenario
+
+In this module, you'll learn how to use the Semantic Kernel SDK to develop your own AI agents that can collaborate for a multi-agent solution.
+
+After completing this module, you'll be able to:
+  - Build AI agents using the Semantic Kernel SDK
+  - Create custom plugin functions for your AI agents
+  - Develop multi-agent solutions
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/2-understand-agent-framework.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/2-understand-agent-framework.md
@@ -0,0 +1,45 @@
+Semantic Kernel is an open-source SDK that enables developers to integrate AI models into their applications. Using the SDK, developers can create "plugins" to interface with the LLMs and perform various tasks. Semantic Kernel bridges the gap between AI and software development by offering tools to create AI-driven agents that can execute tasks, interact with APIs, and perform complex workflows.
+
+## What is the Semantic Kernel Agent Framework?
+
+The Semantic Kernel Agent Framework is a framework designed to help developers build AI-powered agents. These agents can process user inputs, make decisions, and execute tasks autonomously by leveraging large language models and traditional programming logic. The framework provides structured components for defining AI-driven workflows, enabling agents to interact with users, APIs, and external services.
+
+### Core Concepts
+
+- **Kernel** 
+
+    The kernel is the central component of the Semantic Kernel. The kernel acts as the execution engine, managing AI interactions, function orchestration, and memory.
+
+- **Agents**
+    
+    Agents are intelligent, AI-driven entities capable of reasoning and executing tasks. They use language models, functions, and memory to make decisions dynamically.
+
+- **Plugins**
+
+    Agents use plugins to perform specific tasks. Plugin functions enable agents to dynamically interact with external services or execute complex tasks.
+
+- **History**
+
+    Agents can maintain chat history across multiple interactions, allowing them to track previous interactions and adapt responses accordingly.
+
+### Types of Agents
+
+The Semantic Kernel Agent Framework supports several different types of agents.
+
+- Chat Completion Agent
+- OpenAI Assistant Agent
+- Azure AI Agent
+
+## Why Use the Semantic Kernel Agent Framework?
+
+TODO
+
+### Getting Started
+
+TODO - Create AI Foundry Project
+
+To use the Semantic Kernel Agent Framework, install the necessary package with dependencies:
+
+```sh
+pip install semantic-kernel[azure]
+```
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/4-create-azure-ai-agent.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/4-create-azure-ai-agent.md
@@ -0,0 +1,88 @@
+An `AzureAIAgent` is a specialized type of agent within the Semantic Kernel Agent Framework. This type of agent integrates Azure OpenAI services to process user inputs, make decisions, and execute tasks. These agents leverage a large language model to provide intelligent, context-aware interactions in applications. To use an `AzureAIAgent`, you must have an Azure AI Foundry Project.
+
+## Connect to your Azure AI Foundry Project 
+
+Before creating your agent, you must define your Azure AI Foundry Project settings in your development environment. You can do this by setting the properties in your .env file.
+
+```
+AZURE_AI_AGENT_PROJECT_CONNECTION_STRING="your-project-connection-string"
+AZURE_AI_AGENT_MODEL_DEPLOYMENT_NAME="your-language-model"
+```
+
+Afterwards you can connect your Semantic Kernel project to your Azure AI service:
+
+```python
+from azure.identity.aio import DefaultAzureCredential
+from semantic_kernel.agents.azure_ai import AzureAIAgent, AzureAIAgentSettings
+
+async def main():
+    ai_agent_settings = AzureAIAgentSettings.create()
+
+    async with (
+        DefaultAzureCredential() as creds,
+        AzureAIAgent.create_client(credential=creds) as client,
+    ):
+```
+
+TODO explain **AzureAIAgentSettings**
+TODO explain **DefaultAzureCredential**
+TODO explain **AzureAIAgent.create_client**
+
+## Define your Azure AI Agent
+
+To create an Azure AI Agent, you need to provide a definition for the agent that contains its instructions:
+
+```python
+# Define an agent on the Azure AI agent service
+agent_definition = await client.agents.create_agent(
+    model=ai_agent_settings.model_deployment_name,
+    name="<agent-name>",
+    instructions="<agent-instructions>",
+
+)
+
+# Create a Semantic Kernel agent based on the agent definition
+agent = AzureAIAgent(
+    client=client,
+    definition=incident_agent_definition
+)
+```
+
+## Create a chat thread
+
+To interact with your agent, you can create a chat thread for user-agent interaction:
+
+```python
+USER_INPUTS = ["Hello", "What's your name?"]
+
+# Create a chat thread to interact with the agent
+thread = await client.agents.create_thread()
+
+try:
+    for user_input in USER_INPUTS:
+        await agent.add_chat_message(thread_id=thread.id, message=user_input)
+        response = await agent.get_response(thread_id=thread.id)
+        print(response)
+finally:
+    # Delete the chat thread when finished
+    await client.agents.delete_thread(thread.id)
+```
+
+## Retrieve existing agents
+
+An existing agent can be retrieved and reused with the `agent_id`:
+
+```python
+agent = await client.agents.get_agent(agent_id="your-agent-id")
+```
+
+## Delete an agent
+
+Agents and their associated threads can be deleted when no longer needed:
+
+```python
+await client.agents.delete_thread(thread.id)
+await client.agents.delete_agent(agent.id)
+```
+
+Next, you can expand your agent by adding plugin functions to create a more robust experience.
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/5-add-plugins-to-agents.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/5-add-plugins-to-agents.md
@@ -0,0 +1,50 @@
+You can give your AI agent capabilities beyond language processing by using plugins. Plugins are containers for native code that can be added to your agent with the Semantic Kernel. Configuring plugin functions enables your agent to interact with external services, process user input, and automate workflows. 
+
+Using plugins allows you to leverage your existing skills as an app developer to extend the capabilities of your AI agents. Behind the scenes, the Semantic Kernel describes the plugin to the AI agent, allowing the agent to understand the capabilities of the plugin and how to use its functions.
+
+## Create a plugin
+
+To create a plugin, you can start with a class and add methods with the `KernelFunction` attribute. For example, this plugin class retrieves weather information:
+
+```python
+class WeatherPlugin:
+    def __init__(self):
+        self.conditions = ["Sunny", "Cloudy", "Rainy"]
+    
+    @kernel_function(name="GetWeather", description="Gets the current weather for a city")
+    def get_weather(self, city: str):
+        """Retrieve mock weather data for a given city."""
+        weather_data = {
+            "city": city,
+            "temperature": round(random.uniform(-10, 40), 1),
+            "condition": random.choice(self.conditions)
+        }
+        return weather_data
+```
+
+The `name` and `description` fields help the AI agent understand the function and its purpose.
+
+## Add the plugin to the agent definitions
+
+To add your plugin to an `AzureAIAgent` you can include it in the list of plugins in the constructor:
+
+```python
+agent_incident = AzureAIAgent(
+    client=client,
+    definition=incident_agent_definition,
+    plugins=[WeatherPlugin()]
+)
+```
+
+The agent can call **get_weather** dynamically when needed. For example:
+
+```python
+# Create a chat thread to test the incident manager agent
+thread = await client.agents.create_thread()
+
+await agent.add_chat_message(thread_id=thread.id, message="What is the weather in Chicago?")
+response = await agent.get_response(thread_id=thread.id)
+print(response)
+```
+
+When the user asks about the weather in a city, the agent automatically invokes the `get_weather` function to complete the request. Now you can equip your AI agent with skills to perform tasks based on the user's needs.
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/6-design-agent-collaboration.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/6-design-agent-collaboration.md
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/7-exercise.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/7-exercise.md
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/9-summary.md b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/includes/9-summary.md
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/index.yml b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/index.yml
diff --git a/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/media/launch-exercise.png b/learn-pr/wwl-data-ai/orchestrate-sk-multi-agent-solution/media/launch-exercise.png
