Merge pull request #158 from microsoft/copilot/fix-157

Update documentation to correctly reference code samples in lesson 3

Author: elbruno

03-CoreGenerativeAITechniques/01-lm-completions-functions.md

@@ -61,6 +61,8 @@ Console.WriteLine(response.Text);
 > 🗒️**Note:** This example showed GitHub Models as the hosting service. If you want to use Ollama, [check out this example](./src/BasicChat-03Ollama/) (it instantiates a different `IChatClient`).
 > 
 > If you want to use Azure AI Foundry you can use the same code, but you will need to change the endpoint and the credentials.
+>
+> If you want to use both Ollama and Semantic Kernel together, [check out the BasicChat-04OllamaSK example](./src/BasicChat-04OllamaSK/).
 > 
 > For instructions on how to set up Ollama, refer to [Getting Started with Ollama](../02-SetupDevEnvironment/getting-started-ollama.md).
 
@@ -135,6 +137,8 @@ When building AI applications you are not limited to just text-based interaction
 There are a couple of setup steps you need to take in order to call functions with MEAI.
 
 > 🧑‍💻**Sample code**: [Here is a working example of function calling](./src/MEAIFunctions/) you can follow along with. To run this example, follow the same steps as for the previous examples, but navigate to `03-CoreGenerativeAITechniques/src/MEAIFunctions` directory.
+>
+> We also have examples showing function calling with [Azure OpenAI](./src/MEAIFunctionsAzureOpenAI/) and [Ollama](./src/MEAIFunctionsOllama/).
 
 1. First, of course, define the function that you want the chatbot to be able to call. In this example we're going to get the weather forecast.
 

03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md

@@ -35,9 +35,15 @@ You may have heard of vector databases. These are databases that store data in a
 
 We'll use the Microsoft.Extension.AI along with the [Microsoft.Extensions.VectorData](https://www.nuget.org/packages/Microsoft.Extensions.VectorData.Abstractions/) and [Microsoft.SemanticKernel.Connectors.InMemory](https://www.nuget.org/packages/Microsoft.SemanticKernel.Connectors.InMemory) libraries to implement RAG below.
 
-> 🧑‍💻**Sample code:** You can follow along with the [sample code here](../03-CoreGenerativeAITechniques/src/RAGSimple-02MEAIVectorsMemory/).
+> 🧑‍💻**Sample code:** You can follow along with the [sample code here](./src/RAGSimple-02MEAIVectorsMemory/).
 > 
 > You can also see how to implement a RAG app [using Semantic Kernel by itself in our sample source code here](./src/RAGSimple-01SK/).
+>
+> We have additional RAG examples for different vector stores and models:
+> - [RAGSimple-03MEAIVectorsAISearch](./src/RAGSimple-03MEAIVectorsAISearch/) - Using Azure AI Search as a vector store
+> - [RAGSimple-04MEAIVectorsQdrant](./src/RAGSimple-04MEAIVectorsQdrant/) - Using Qdrant as a vector store
+> - [RAGSimple-10SKOllama](./src/RAGSimple-10SKOllama/) - Using Semantic Kernel with Ollama
+> - [RAGSimple-15Ollama-DeepSeekR1](./src/RAGSimple-15Ollama-DeepSeekR1/) - Using Ollama with DeepSeek-R1 model
 
 ### Populating the knowledge store
 

03-CoreGenerativeAITechniques/03-vision-audio.md

@@ -21,6 +21,11 @@ Ok - so we're going to put the model through its paces and ask it if it can tell
 ![A composite showing both images the example will use. The first is several runners but only showing their legs. The second is a German restaurant receipt](./images/example-visual-image.png)
 
 > 🧑‍💻**Sample code**: You can follow [along with sample code here](./src/Vision-01MEAI-GitHubModels/).
+>
+> We also have examples showing vision capabilities with:
+> - [Ollama](./src/Vision-02MEAI-Ollama/) - Using local Ollama models for vision tasks
+> - [Azure OpenAI](./src/Vision-03MEAI-AOAI/) - Using Azure OpenAI for vision tasks
+> - [Azure OpenAI with Spectre UI](./src/Vision-04MEAI-AOAI-Spectre/) - A more advanced UI using the Spectre console library
 
 1. We're using MEAI and GitHub Models, so instantiate the `IChatClient` as we have been. Also start to create a chat history.
 

03-CoreGenerativeAITechniques/04-agents.md

@@ -20,7 +20,10 @@ We'll be working with a couple of new concepts in order to build an AI agent in
 
 > 🧑‍💻**Sample code**: We'll be working from the [AgentLabs-01-Simple sample](./src/AgentLabs-01-Simple/) for this lesson.
 >
-> We did include some more advanced samples in the `/src/` folder as well. You can view the README's of [AgentLabs-02-Functions](./src/AgentLabs-02-Functions/) or [AgentLabs-03-OpenAPIs](./src/AgentLabs-03-OpenAPIs/) or [AgentLabs-03-PythonParksInformationServer](./src/AgentLabs-03-PythonParksInformationServer/) for more info on them.
+> We also have more advanced agent examples:
+> - [AgentLabs-02-Functions](./src/AgentLabs-02-Functions/) - Showing how to create custom functions for your agents
+> - [AgentLabs-03-OpenAPIs](./src/AgentLabs-03-OpenAPIs/) - Demonstrating how agents can use OpenAPI specifications
+> - [AgentLabs-03-PythonParksInformationServer](./src/AgentLabs-03-PythonParksInformationServer/) - A Python server that works with the OpenAPI example
 
 ### Azure AI Agent Service
 

03-CoreGenerativeAITechniques/06-AIToolkitAndDockerModels.md

@@ -60,6 +60,39 @@ docker run -d -p 12434:8080 \
   deepseek-ai/deepseek-llm-7b-chat
 ```
 
+## Sample Code: Using AI Toolkit for Windows with .NET
+
+The AI Toolkit for Windows provides a way to run AI models locally on Windows machines. We have two examples that demonstrate how to interact with AI Toolkit models using .NET:
+
+### 1. Semantic Kernel with AI Toolkit
+
+The [AIToolkit-01-SK-Chat](./src/AIToolkit-01-SK-Chat/) project shows how to use Semantic Kernel to chat with a model running via AI Toolkit for Windows.
+
+```csharp
+// Example code demonstrating AI Toolkit with Semantic Kernel integration
+var builder = Kernel.CreateBuilder();
+// Configure to use a locally installed model through AI Toolkit
+builder.AddAzureOpenAIChatCompletion(
+    modelId: modelId,
+    endpoint: new Uri(endpoint),
+    apiKey: apiKey);
+var kernel = builder.Build();
+// Create a chat history and use it with the kernel
+```
+
+### 2. Microsoft Extensions for AI with AI Toolkit
+
+The [AIToolkit-02-MEAI-Chat](./src/AIToolkit-02-MEAI-Chat/) project demonstrates how to use Microsoft Extensions for AI to interact with AI Toolkit models.
+
+```csharp
+// Example code demonstrating AI Toolkit with MEAI
+OpenAIClientOptions options = new OpenAIClientOptions();
+options.Endpoint = new Uri(endpoint);
+ApiKeyCredential credential = new ApiKeyCredential(apiKey);
+// Create a chat client using local model through AI Toolkit
+ChatClient client = new OpenAIClient(credential, options).GetChatClient(modelId);
+```
+
 ## Sample Code: Using Docker Models with .NET
 
 In this repository, we have two examples that demonstrate how to interact with Docker-based models using .NET: