fix

Author: leestott

Diff for: imgs/01/02/03/aifoundry_home.png

@@ -46,15 +46,15 @@ Developers should apply responsible AI best practices and are responsible for en
 
 After fine-tuning a model, we highly recommend leveraging [Azure AI Content Safety](https://learn.microsoft.com/azure/ai-services/content-safety/overview) measures to monitor the content generated by the models, identify and block potential risks, threats, and quality issues.
 
-![Phi3AISafety](../../../imgs/01/01.phi3aisafety.png)
+![Phi3AISafety](../../../imgs/01/01/01.phi3aisafety.png)
 
 [Azure AI Content Safety](https://learn.microsoft.com/azure/ai-services/content-safety/overview) supports both text and image content. It can be deployed in the cloud, disconnected containers, and on edge/embedded devices.
 
 ## Overview of Azure AI Content Safety
 
 Azure AI Content Safety is not a one-size-fits-all solution; it can be customized to align with businesses’ specific policies. Additionally, its multi-lingual models enable it to understand multiple languages simultaneously.
 
-![AIContentSafety](../../../imgs/01/01.AIcontentsafety.png)
+![AIContentSafety](../../../imgs/01/01/01.AIcontentsafety.png)
 
 - **Azure AI Content Safety**
 - **Microsoft Developer**

Diff for: md/01.Introduction/01/01.AISafety.md

@@ -165,11 +165,11 @@ You need to create a Hub before creating the Project. A Hub acts like a Resource
 
 1. Select **+ New project** from the navigation menu.
 
-    ![Select new project.](../../../../imgs/03/Evaluation-AIFoundry/select-new-project.png)
+    ![Select new project.](../../../../imgs/03/AIFoundry/select-new-project.png)
 
 1. Enter **Project name**. It must be a unique value.
 
-    ![Create project.](../../../../imgs/03/Evaluation-AIFoundry/create-project.png)
+    ![Create project.](../../../../imgs/03/AIFoundry/create-project.png)
 
 1. Select **Create a project**.
 
@@ -369,7 +369,7 @@ You need to integrate the fine-tuned Phi-3 / Phi-3.5 model into a Prompt flow. H
 
 1. Select **Validate and parse input** to renew parameters.
 
-    ![Validate input.](../../../../imgs/03/Evaluation-AIFoundry/validate-input.png)
+    ![Validate input.](../../../../imgs/02/Evaluation-AIFoundry/validate-input.png)
 
 1. Select the **Value** of the **connection** to the custom connection you created. For example, *connection*.
 
@@ -395,7 +395,7 @@ To evaluate the Phi-3 / Phi-3.5 model in Azure AI Foundry, you need to deploy an
 
 1. Navigate to the Azure AI Foundry project that you created.
 
-    ![Select Project.](../../../../imgs/03/Evaluation-AIFoundry/select-project-created.png)
+    ![Select Project.](../../../../imgs/02/Evaluation-AIFoundry/select-project-created.png)
 
 1. In the Project that you created, select **Deployments** from the left side tab.
 

Diff for: md/02.Application/01.TextAndChat/Phi3/E2E_Phi-3-Evaluation_AIFoundry.md

@@ -425,7 +425,7 @@ In this exercise, you will:
 
 1. Select **Fine-tune** from the navigation menu.
 
-    ![Select fine tune.](../../../../imgs/03/FineTuning-PromptFlow-AIFoundry/06-06-select-fine-tune.png)
+    ![Select fine tune.](../../../../imgs/02/FineTuning-PromptFlow-AIFoundry/06-06-select-fine-tune.png)
 
 1. Perform the following tasks:
 

Diff for: md/02.Application/01.TextAndChat/Phi3/E2E_Phi-3-FineTuning_PromptFlow_Integration_AIFoundry.md

@@ -2,79 +2,64 @@
 
 With the development of Generative AI, we hope to use a unified platform to manage different LLM and SLM, enterprise data integration, fine-tuning/RAG operations, and the evaluation of different enterprise businesses after integrating LLM and SLM, etc., so that generative AI can Smart applications are better implemented. [Azure AI Foundry](https://ai.azure.com) is an enterprise-level generative AI application platform.
 
-![aistudo](../../imgs/02/AIStudio/ai-studio-home.png)
+![aistudo](../../imgs/01/02/03/aifoundry_home.png)
 
 With Azure AI Foundry, you can evaluate large language model (LLM) responses and orchestrate prompt application components with prompt flow for better performance. The platform facilitates scalability for transforming proof of concepts into full-fledged production with ease. Continuous monitoring and refinement support long-term success.
 
 We can quickly deploy the Phi-3 model on Azure AI Foundry through simple steps, and then use Azure AI Foundry to complete Phi-3 related Playground/Chat, Fine-tuning, evaluation and other related work.
 
 ## **1. Preparation**
 
-## [AZD AI Foundry Starter Template](https://azure.github.io/awesome-azd/?name=AI+Studio)
-
-### Azure AI Foundry Starter
-
-This is Bicep template that deploys everything you need to get started with Azure AI Foundry. Includes AI Hub with dependent resources, AI project, AI Services and an online endpoint
-
-### Quick Use
-
 If you already have the [Azure Developer CLI](https://learn.microsoft.com/azure/developer/azure-developer-cli/overview?WT.mc_id=aiml-138114-kinfeylo) installed on your machine, using this template is as simple as running this command in a new directory.
 
-### Terminal Command
-
-```bash
-azd init -t azd-aistudio-starter
-```
-
-Or
-If using the azd VS Code extension you can paste this URL in the VS Code command terminal.
-
-### Terminal URL
+## Manual Creation
 
-```bash
-azd-aistudio-starter
-```
+Creating a Microsoft Azure AI Foundry project and hub is a great way to organize and manage your AI work. Here's a step-by-step guide to get you started:
 
-## Manual Creation
+### Creating a Project in Azure AI Foundry
 
-Create Azure AI Foundry on [Azure Portal](https://portal.azure.com?WT.mc_id=aiml-138114-kinfeylo)
+1. **Go to Azure AI Foundry**: Sign in to the Azure AI Foundry portal.
+2. **Create a Project**:
+   - If you're in a project, select "Azure AI Foundry" at the top left of the page to go to the Home page.
+   - Select "+ Create project".
+   - Enter a name for the project.
+   - If you have a hub, it will be selected by default. If you have access to more than one hub, you can select a different one from the dropdown. If you want to create a new hub, select "Create new hub" and supply a name.
+   - Select "Create".
 
-![portal](../../imgs/02/AIStudio/ai-studio-portal.png)
+### Creating a Hub in Azure AI Foundry
 
-After completing the naming of the studio and setting the region, you can create it
+1. **Go to Azure AI Foundry**: Sign in with your Azure account.
+2. **Create a Hub**:
+   - Select the Management center from the left menu.
+   - Select "All resources", then the down arrow next to "+ New project" and select "+ New hub".
+   - In the "Create a new hub" dialog, enter a name for your hub (e.g., contoso-hub) and modify the other fields as desired.
+   - Select "Next", review the information, and then select "Create".
 
-![settings](../../imgs/02/AIStudio/ai-studio-settings.png)
+For more detailed instructions, you can refer to the official [Microsoft documentation](https://learn.microsoft.com/azure/ai-studio/how-to/create-projects).
 
 After successful creation, you can access the studio you created through [ai.azure.com](https://ai.azure.com/)
 
-![page](../../imgs/02/AIStudio/ai-studio-page.png)
-
 There can be multiple projects on one AI Foundry. Create a project in AI Foundry to prepare.
 
-![proj](../../imgs/02/AIStudio/ai-studio-proj.png)
+Create Azure AI Foundry [QuickStarts](https://learn.microsoft.com/azure/ai-studio/quickstarts/get-started-code)
 
-## **2. Deploy the Phi-3 model in Azure AI Foundry**
 
-Click the Explore option of the project to enter the Model Catalog and select Phi-3
+## **2. Deploy a Phi model in Azure AI Foundry**
 
-![model](../../imgs/02/AIStudio/ai-studio-model.png)
+Click the Explore option of the project to enter the Model Catalog and select Phi-3
 
 Select Phi-3-mini-4k-instruct
 
-![phi3](../../imgs/02/AIStudio/ai-studio-phi3.png)
-
 Click 'Deploy' to deploy the Phi-3-mini-4k-instruct model
 
 > [!NOTE]
 >
 > You can select computing power when deploying
 
-## **3. Playground Chat Phi-3 in Azure AI Foundry**
+## **3. Playground Chat Phi in Azure AI Foundry**
 
 Go to the deployment page, select Playground, and chat with Phi-3 of Azure AI Foundry
 
-![chat](../../imgs/02/AIStudio/ai-studio-chat.png)
-
 ## **4. Deploying the Model from Azure AI Foundry**
 
 To deploy a model from the Azure Model Catalog, you can follow these steps:
@@ -92,16 +77,9 @@ To deploy a model from the Azure Model Catalog, you can follow these steps:
 > [!NOTE]
 > Please note that your account must have the Azure AI Developer role permissions on the Resource Group to perform these steps.
 
-## **5. Using Phi-3 API in Azure AI Foundry**
+## **5. Using Phi API in Azure AI Foundry**
 
 You can access https://{Your project name}.region.inference.ml.azure.com/swagger.json through Postman GET and combine it with Key to learn about the provided interfaces
 
-![swagger](../../imgs/02/AIStudio/ai-studio-swagger.png)
-
-such as access score api 
-
-![score](../../imgs/02/AIStudio/ai-studio-score.png)
-
-You can get the request parameters very conveniently, as well as the response parameters. This is Postman result
+You can get the request parameters very conveniently, as well as the response parameters.
 
-![result](../../imgs/02/AIStudio/ai-studio-result.png)

Diff for: md/02.QuickStart/AzureAIFoundry_QuickStart.md

@@ -2,15 +2,15 @@
 
 Welcome to [GitHub Models](https://github.com/marketplace/models)! We've got everything fired up and ready for you to explore AI Models hosted on Azure AI.
 
-![GitHubModel](../../imgs/02/GitHub/GitHub_ModelCatalog.png)
+![GitHubModel](../../imgs/01/02/02/GitHub_ModelCatalog.png)
 
 For more information about the Models available on GitHub Models, check out the [GitHub Model Marketplace](https://github.com/marketplace/models)
 
 ## Models Available
 
 Each model has a dedicated playground and sample code 
 
-![Phi-3Model_Github](../../imgs/02/GitHub/GitHub_ModelPlay.png)
+![Phi-3Model_Github](../../imgs/01/02/02/GitHub_ModelPlay.png/)
 
 ### Phi-3 Models in GitHub Model Catalog
 
@@ -36,7 +36,7 @@ There are a few basic examples that are ready for you to run. You can find them
 
 There is also a dedicated Codespaces Environment for running the samples and models. 
 
-![Getting Started](../../imgs/02/GitHub/GitHub_ModelGetStarted.png)
+![Getting Started](../../imgs/01/02/02/GitHub_ModelGetStarted.png)
 
 
 ## Sample Code 
@@ -419,7 +419,7 @@ curl -X POST "https://models.inference.ai.azure.com/chat/completions" \
 
 ## FREE Usage and Rate limits for GitHub Models
 
-![Model Catalog](../../imgs/02/GitHub/GitHub_Model.png)
+![Model Catalog](../../imgs/01/02/02/GitHub_Model.png)
 
 The [rate limits for the playground and free API usage](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits) are intended to help you experiment with models and prototype your AI application. For use beyond those limits, and to bring your application to scale, you must provision resources from an Azure account, and authenticate from there instead of your GitHub personal access token. You don't need to change anything else in your code. Use this link to discover how to go beyond the free tier limits in Azure AI.
 

Diff for: md/02.QuickStart/GitHubModel_QuickStart.md

@@ -33,7 +33,7 @@ python -m mlx_lm.generate --model microsoft/Phi-3-mini-4k-instruct --max-token 2
 
 The result (my env is Apple M1 Max,64GB) is
 
-![Terminal](../../imgs/03/MLX/01.png)
+![Terminal](../../../imgs/01/03/MLX/01.png)
 
 ### **3. Quantizing Phi-3-mini with MLX in Terminal**
 
@@ -59,15 +59,15 @@ python -m mlx_lm.generate --model ./mlx_model/ --max-token 2048 --prompt  "<|use
 
 The result is
 
-![INT4](../../imgs/03/MLX/02.png)
+![INT4](../../../imgs/01/03/MLX/02.png)
 
 
 ### **4. Running Phi-3-mini with MLX in Jupyter Notebook**
 
 
-![Notebook](../../imgs/03/MLX/03.png)
+![Notebook](../../../imgs/01/03/MLX/03.png)
 
-***Note:*** Please read this sample [click this link](../../code/03.Inference/MLX/MLX_DEMO.ipynb)
+***Note:*** Please read this sample [click this link](../../../code/03.Inference/MLX/MLX_DEMO.ipynb)
 
 
 ## **Resources**