Merge pull request #441 from microsoft/workshop-update

Workshop update

Author: aniaroramsft

workshop/docs/workshop/Challenge-0/CU-Challenge.md

@@ -3,18 +3,19 @@
 ## Step 1: Create a Content Understanding Project
 
 - Navigate to the [AI Foundry homepage](https://ai.azure.com) and select Try Content Understanding.
+> **Note**: You will need to create a project in one of the following regions: westus, swedencentral, or australiaeast
 
   ![AI Foundry Homepage](../img/ai-services-landing-page.png)   
 
 - Select + Create to create a new Content Understand project.
 
-  ![CU Landing Page](../img/cu-create-project.png)
+  ![CU Landing Page](../img/cu-landing-page.png)
 
 - Provide a name for your project (i.e. call_analyzer), select create a new hub, keep the default Azure AI service connection and select Next
   ![create project](../img/create_project.png)
 - Keep the default storage account, select next and select Create project. 
 
-- Select Browse file to upload the [sample audio file](../data/convo_2c703f97-6657-4a15-b8b2-db6b96630b2d_2024-12-06%2006_00_00.wav).
+- Select Browse file to upload the sample audio file included in this [workshop](../data/convo_2c703f97-6657-4a15-b8b2-db6b96630b2d_2024-12-06%2006_00_00.wav).
 
   ![CU upload document](../img/cu-upload-document.png)
 

workshop/docs/workshop/Challenge-1/App_Authentication.md

@@ -7,20 +7,20 @@ To access and explore the ingested data:
 2. Locate the Resource Group where the solution is deployed
 
 3. Click on the Storage Account associated with the solution
-      ![image](../img/storage-blob.png)
+      ![image](../../img/storage-blob.png)
 
 4. Navigate to Containers section
-      ![image](../img/storage-container.png)
+      ![image](../../img/storage-container.png)
 
 5. Open the container named data
 
 You’ll see two folders:
 
 - audiodata → Contains uploaded call recordings
-      ![image](../img/audio-folder.png)
+      ![image](../../img/audio-folder.png)
 
 call_transcripts → Stores the transcript text used for AI processing
-      ![image](../img/call_transcripts.png)
+      ![image](../../img/call_transcripts.png)
 <!-- The Sample dataset used for this solution contains customer interactions categorized into various topics. Each entry includes:
 
 - **ConversationId**: Unique identifier for each conversation.

…ocs/workshop/Challenge-1/data-explore.md …ge-1/Code_Walkthrough/01_Data_Explore.mdworkshop/docs/workshop/Challenge-1/data-explore.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/01_Data_Explore.md workshop/docs/workshop/Challenge-1/data-explore.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/01_Data_Explore.md

@@ -5,7 +5,7 @@
 
 The frontend is a **React-based web interface** that allows users to explore insights from conversations, interact with an AI-powered chatbot, and view dynamic visualizations.
 
-![image](../support-docs/Images/ReadMe/ckm-ui.png)
+![image](../../../../../docs/Images/ReadMe/ui.png)
 
 ### Features
 

…op/docs/workshop/Challenge-1/Frontend.md …llenge-1/Code_Walkthrough/02_Frontend.mdworkshop/docs/workshop/Challenge-1/Frontend.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/02_Frontend.md workshop/docs/workshop/Challenge-1/Frontend.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/02_Frontend.md

@@ -3,7 +3,7 @@ We will set up the initial environment for you to build on top of during your Mi
 
 ### **Prerequisites**
 
-- To deploy this solution accelerator, ensure you have access to an [Azure subscription](https://azure.microsoft.com/free/) with the necessary permissions to create **resource groups and resources**. Follow the steps in  [Azure Account Set Up](../support-docs/AzureAccountSetUp.md)
+- To deploy this solution accelerator, ensure you have access to an [Azure subscription](https://azure.microsoft.com/free/) with the necessary permissions to create **resource groups and resources**. Follow the steps in  [Azure Account Set Up](../../../../docs/AzureAccountSetUp.md)
 - [VS Code](https://code.visualstudio.com/download) installed locally
 
 
@@ -15,20 +15,20 @@ Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/g
 - Azure AI Content Understanding
 - Embedding Deployment Capacity  
 - GPT Model Capacity
-- [Azure Semantic Search](../support-docs/AzureSemanticSearchRegion.md)  
+- [Azure Semantic Search](../../../../docs/AzureSemanticSearchRegion.md)  
 
 Here are some example regions where the services are available: East US2
 
 ### ⚠️ Important: Check Azure OpenAI Quota Availability  
 
-➡️ To ensure sufficient quota is available in your subscription, please follow **[Quota check instructions guide](../support-docs/quota_check.md)** before you deploy the solution.
+➡️ To ensure sufficient quota is available in your subscription, please follow **[Quota check instructions guide](../../../../docs/QuotaCheck.md)** before you deploy the solution.
 
 
 ### Quota Recommendations  
 By default, the **GPT model capacity** in deployment is set to **30k tokens**.  
 > **We recommend increasing the capacity to 120k tokens for optimal performance.** 
 
-To adjust quota settings, follow these [steps](../support-docs/AzureGPTQuotaSettings.md)  
+To adjust quota settings, follow these [steps](../../../../docs/AzureGPTQuotaSettings.md)  
 
 
 
@@ -47,6 +47,7 @@ To adjust quota settings, follow these [steps](../support-docs/AzureGPTQuotaSett
         python -m venv .venv
         # Windows
         .venv\Scripts\activate
+        
         # macOS/Linux
         source .venv/bin/activate
 
@@ -81,8 +82,8 @@ Once deployment completes:
 Additional Steps
 </h2>
 
-1. **Add App Authentication**
+1. **Optional**: Add App Authentication
 
-    Follow steps in [App Authentication](./App-Authentication.md) to configure authenitcation in app service.
+    Follow steps in [App Authentication](../../../../docs/AppAuthentication.md) to configure authenitcation in app service.
 
     Note: Authentication changes can take up to 10 minutes 

…hop/docs/workshop/Challenge-1/Backend.md …allenge-1/Code_Walkthrough/03_Backend.mdworkshop/docs/workshop/Challenge-1/Backend.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/03_Backend.md workshop/docs/workshop/Challenge-1/Backend.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/03_Backend.md

@@ -2,7 +2,7 @@
 <!-- ## Overview -->
 The Conversation Knowledge Mining Solution Accelerator is a robust application designed to extract actionable insights from conversational data. It leverages Azure AI services and provides an interactive user interface for querying and visualizing data. The solution is built with a modular architecture, combining a React-based frontend, a FastAPI backend, and Azure services for data processing and storage.
 
-![image](../support-docs/Images/ReadMe/ckm-sol-arch.png)
+![image](../../../../docs/Images/ReadMe/solution-architecture.png)
 
 The solution extracts insights from call audio files or transcripts and enables users to interact with the data via a chatbot and dynamic charts:
 

workshop/docs/workshop/Challenge-1/Api.md …p/Challenge-1/Code_Walkthrough/04_Api.mdworkshop/docs/workshop/Challenge-1/Api.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/04_Api.md workshop/docs/workshop/Challenge-1/Api.md renamed to workshop/docs/workshop/Challenge-1/Code_Walkthrough/04_Api.md

@@ -4,24 +4,23 @@ One of the easiest and most fun changes you can make to the app is updating the
 
 ---
 
-### Step 1: Prepare Your New Logo**
-1. Create or use a new logo (e.g contosoImg logo) in `src/app/src/Assets/`.
+### Step 1: Prepare Your New Logo
+1. Create or use a new logo (e.g [Contoso Img logo](../../../../src/App/src/Assets/ContosoImg.png)) in `src/app/src/Assets/`.
 2. Save the logo as an image file (e.g., `logo.png`).
 3. Ensure the image has a reasonable size (e.g., 100x100 pixels) for better display.
 4. Place the logo file in the following folder:
     `src/app/src/Assets/`
 
 ---
 
-
 ### Step 2: Update the Logo Component
 
 1. Open the `App.tsx` file located at:  
    ```
    src/App/src/App.tsx
    ```
 
-2. Comment out the original import on **line 24**:
+2. Comment out the original import on **line 29**:
 
    ```tsx
    // import { AppLogo } from "./components/Svg/Svg";
@@ -69,8 +68,12 @@ One of the easiest and most fun changes you can make to the app is updating the
    ```bash
       cd src/
    ```
-10. Make sure your Python virtual environment is activated, as done in the Challenge 1 deployment steps.
-
+10. Make sure your Python virtual environment is activated, as done in the [Challenge 1 deployment](../Challenge-1/Deployment.md) steps.
+      * This script will perform the following: 
+         * Take the environment variables from the deployment and populate the rest of the varibales in the .env file to run the app locally. 
+         * Copy the .env file from the src folder to the workshop folder for the next challenges. 
+         * Assign the needed roles for the Azure SQL database and Azure Cosmos DB
+         * Run the app locally
 11. Start the application:
 
    ```bash
@@ -81,3 +84,5 @@ One of the easiest and most fun changes you can make to the app is updating the
 Once the app starts, you should see your new logo!
 
 
+
+

workshop/docs/workshop/Challenge-1/Deployment.md

@@ -59,57 +59,32 @@ This function lets users ask questions that are better answered using full-text
 
 ---
 
-<!-- ## Challenge 5: Create an AI Agent
-
-Once your plugin is ready, you’ll create an **Azure AI Agent** that uses it.
-
-### The Agent Includes:
-- A **system prompt** that defines the assistant’s behavior  
-  (e.g. "You're a helpful assistant. Only respond to relevant questions.")
-- The three **plugin functions** from above
-- Basic logic to route questions to the right function (greeting, SQL, or search)
-
-You’ll test the agent by giving it natural questions and seeing how it responds using your actual data!
-
---- -->
-
-## Bonus: Responsible AI (RAI) Principles
-
-Take a moment to review how the system prompt reflects **RAI principles**:
-
-- What the assistant should or shouldn't say
-- How it handles unknown or inappropriate questions
-- How it maintains transparency and trust
-
-Feel free to enhance the agent prompt with RAI-friendly language.
-
----
 ### Prerequisites
 - Azure AI project credentials.
 - [Python 3.9+](https://www.python.org/downloads/)
 - [Microsoft ODBC Driver 17](https://learn.microsoft.com/en-us/sql/connect/odbc/download-odbc-driver-for-sql-server?view=sql-server-ver16#version-17)
 - Python environment with required libraries installed (`azure-ai-evaluation`, `pandas`, etc.).
 - Access to the Azure API endpoint.
+- Completed [Challenge 3](./Challenge-3.md) 
 
-If did not create a virtual environment during the deployment, please follow the steps [here](../Challenge-1/Deployment.md) 
+If did not create a virtual environment during Challenge 3, please follow the steps [here](../Challenge-3-and-4/Challenge-3.md) 
 1. Navigate to the `workshop/docs/workshop` folder in the terminal in your local repository and run the following command.
 * Install the requirements
 ```shell
 pip install -r requirements.txt
 ```
 2. Open the `.env` in the `workshop/docs/workshop` folder to validate the variables were updated with the details of your solution. 
 3. Follow the steps in [Challenge-4](./Challenge-4.md) to run the notebook. 
-<!-- 
-## 🧪 Sample Run
 
-You’ll find example queries in the notebook. Try things like:
-- `"What’s the average wait time for support calls?"`
-- `"Summarize what the customer said about the new pricing."`
-- `"Hello!"`
+## Bonus: Responsible AI (RAI) Principles
 
-Observe which plugin each query triggers — and how it responds.
+Take a moment to review how the system prompt reflects **RAI principles**:
 
---- -->
+- What the assistant should or shouldn't say
+- How it handles unknown or inappropriate questions
+- How it maintains transparency and trust
+
+Feel free to enhance the agent prompt with RAI-friendly language.
 
 ## Recap