Merge pull request #42 from microsoft/readmeupdates

add information to read me for adding/modifying model deployments

Author: sethsteenken

README.md

@@ -37,6 +37,7 @@ The diagram below illustrates the capabilities included in the template.
 
 - Provides the ability to [add additional Azure services during deployment](docs/add_additional_services.md), configured to connect via isolation to enrich your AI project.
     (API Management, CosmosDB, Azure SQL DB)
+- Provides the ability to [define the models deployed into the hub](docs/modify_deployed_models.md) when the deployment runs. 
 
 ## Prerequisites and high-level steps
 
@@ -98,9 +99,6 @@ You can estimate the cost of this project's architecture with [Azure's pricing c
 
 This template has [Managed Identity](https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview) built in to eliminate the need for developers to manage these credentials. Applications can use managed identities to obtain Microsoft Entra tokens without having to manage any credentials.
 
-<h2>
-Supporting documents
-</h2>
 
 ## Resources
 

docs/modify_deployed_models.md

@@ -0,0 +1,37 @@
+## Update AI Model Deployments
+The AI Models that can be deployed and attached to the Foundry hub can be modified by changing the parameters within the [main.parameters.json](../infra/main.parameters.json) file.
+
+By modifying the parameters listed in the parameters.json 'aiModelDeployments' section, additional or different models can be deployed with the solution and ready for use after the deployment. Simply modify the values to your liking in each of the objects, or add additional objects to the array. 
+```powershell
+
+
+    "aiModelDeployments": {
+      "value": [
+        {
+          "name": "textembed",
+          "model": {
+            "name": modelName,
+            "format": modelPublisherFormat,
+            "version": modelVersion
+          },
+          "sku": {
+            "name": skuName,
+            "capacity": capacity
+          }
+        },
+        {
+          "name": "gpt",
+          "model": {
+            "name": "gpt-4o",
+            "version": "2024-05-13",
+            "format": "OpenAI"
+          },
+          "sku": {
+            "name": "GlobalStandard",
+            "capacity": 10
+          }
+        }
+      ]
+    }
+```
+To find and validate additional model information, the [AI Foundry](https://ai.azure.com/explore/models) model page has the above parameters to refer to, as does the Microsoft Learn page for [Azure OpenAI Service Models](https://learn.microsoft.com/en-us/azure/ai-services/openai_) information.