Update readme, enable AI search by default, update model, change tpm (#4)

* allow users to set the model for the agent by environment variable
* update the readme
* enable AI Search Service by default
* remove example images, add architecture diagram (to be updated later)
* change default tokens per minute of model deployment from 30,000 to 50,000
* still need to rename repo to azure-ai-agents-chat
* still need to implement functionality for agent export from AI Foundry and agents.yaml configuration
* still need to finalize troubleshooting guide at the end

Author: sophia-ramsey

README.md

@@ -0,0 +1,96 @@
+
+# Getting Started with Agents Using Azure AI Foundry: Deployment customization
+
+This document describes how to customize the deployment of the Agents Chat with Azure AI Foundry. Once you follow the steps here, you can run `azd up` as described in the [Deploying](./README.md#deploying) steps.
+
+* [Disabling resources](#disabling-resources)
+* [Customizing resource names](#customizing-resource-names)
+* [Customizing model deployments](#customizing-model-deployments)
+
+## Disabling resources
+
+Disabling a resource will stop that resource from being created and deployed to your Azure Project. 
+
+* To disable AI Search, run `azd env set USE_SEARCH_SERVICE false`
+* To disable Application Insights, run `azd env set USE_APPLICATION_INSIGHTS false`
+* To disable Container Registry, run `azd env set USE_CONTAINER_REGISTRY false`
+
+Once you disable these resources, they will not be deployed when you run `azd up`.
+
+## Customizing resource names
+
+By default, this template will use a naming convention with unique strings to prevent naming collisions within Azure.
+To override default naming conventions, the following keys can be set:
+
+* `AZURE_AIHUB_NAME` - The name of the AI Foundry Hub resource
+* `AZURE_AIPROJECT_NAME` - The name of the AI Foundry Project
+* `AZURE_AIENDPOINT_NAME` - The name of the AI Foundry online endpoint used for deployments
+* `AZURE_AISERVICES_NAME` - The name of the Azure AI service
+* `AZURE_SEARCH_SERVICE_NAME` - The name of the Azure Search service
+* `AZURE_STORAGE_ACCOUNT_NAME` - The name of the Storage Account
+* `AZURE_KEYVAULT_NAME` - The name of the Key Vault
+* `AZURE_CONTAINER_REGISTRY_NAME` - The name of the container registry
+* `AZURE_APPLICATION_INSIGHTS_NAME` - The name of the Application Insights instance
+* `AZURE_LOG_ANALYTICS_WORKSPACE_NAME` - The name of the Log Analytics workspace used by Application Insights
+
+To override any of those resource names, run `azd env set <key> <value>` before running `azd up`.
+
+## Customizing model deployments
+
+For more information on the Azure OpenAI models and non-Microsoft models that can be used in your deployment, view the [list of models supported by Azure AI Agent Service](https://learn.microsoft.com/azure/ai-services/agents/concepts/model-region-support)
+
+To customize the model deployments, you can set the following environment variables:
+
+### Using a different chat model
+
+Change the chat deployment name:
+
+```shell
+azd env set AZURE_AI_CHAT_DEPLOYMENT_NAME Phi-3.5-MoE-instruct
+```
+
+Change the chat model format (either OpenAI or Microsoft):
+
+```shell
+azd env set AZURE_AI_CHAT_MODEL_FORMAT Microsoft
+```
+
+Change the chat model name:
+
+```shell
+azd env set AZURE_AI_CHAT_MODEL_NAME Phi-3.5-MoE-instruct
+```
+
+Set the version of the chat model:
+
+```shell
+azd env set AZURE_AI_CHAT_MODEL_VERSION 2
+```
+
+### Setting capacity and deployment SKU
+
+For quota regions, you may find yourself needing to modify the default capacity and deployment SKU. The default tokens per minute deployed in this template is 50,000. 
+
+Change the capacity (in thousands of tokens per minute) of the chat deployment:
+
+```shell
+azd env set AZURE_AI_CHAT_DEPLOYMENT_CAPACITY 50
+```
+
+Change the SKU of the chat deployment:
+
+```shell
+azd env set AZURE_AI_CHAT_DEPLOYMENT_SKU Standard
+```
+
+Change the capacity (in thousands of tokens per minute) of the embeddings deployment:
+
+```shell
+azd env set AZURE_AI_EMBED_DEPLOYMENT_CAPACITY 50
+```
+
+Change the SKU of the embeddings deployment:
+
+```shell
+azd env set AZURE_AI_EMBED_DEPLOYMENT_SKU Standard
+```

assets/DeploymentError.png

@@ -48,7 +48,7 @@
       "value": "${USE_APPLICATION_INSIGHTS=true}"
     },
     "useSearchService": {
-      "value": "${USE_SEARCH_SERVICE=false}"
+      "value": "${USE_SEARCH_SERVICE=true}"
     },
     "chatDeploymentName": {
       "value": "${AZURE_AI_CHAT_DEPLOYMENT_NAME=gpt-4o-mini}"
@@ -66,7 +66,7 @@
       "value": "${AZURE_AI_CHAT_DEPLOYMENT_SKU=GlobalStandard}"
     },
     "chatDeploymentCapacity": {
-      "value": "${AZURE_AI_CHAT_DEPLOYMENT_CAPACITY=30}"
+      "value": "${AZURE_AI_CHAT_DEPLOYMENT_CAPACITY=50}"
     },
     "embedDeploymentName": {
       "value": "${AZURE_AI_EMBED_DEPLOYMENT_NAME=text-embedding-ada-002}"
@@ -84,7 +84,7 @@
       "value": "${AZURE_AI_EMBED_DEPLOYMENT_SKU=Standard}"
     },
     "embedDeploymentCapacity": {
-      "value": "${AZURE_AI_EMBED_DEPLOYMENT_CAPACITY=30}"
+      "value": "${AZURE_AI_EMBED_DEPLOYMENT_CAPACITY=50}"
     },
     "apiAppExists": {
       "value": "${SERVICE_API_RESOURCE_EXISTS=false}"

assets/FileSearchAgent.png

@@ -54,7 +54,7 @@ async def lifespan(app: fastapi.FastAPI):
         )
         logger.info("Created AIProjectClient")
 
-        file_names = ["product_info_1.md", "product_info_2.md"]
+        file_names = ["product_info_1.md", "product_info_2.md"] #TODO: can we get the file names from the folder so customers can upload? 
         for file_name in file_names:
             file_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'files', file_name))
             file = await ai_client.agents.upload_file_and_poll(file_path=file_path, purpose=FilePurpose.AGENTS)
@@ -73,12 +73,14 @@ async def lifespan(app: fastapi.FastAPI):
         toolset.add(file_search_tool)
 
         agent = await ai_client.agents.create_agent(
-            model="gpt-4o-mini", 
+            model=os.environ["AZURE_AI_CHAT_DEPLOYMENT_NAME"],
             name="my-assistant", 
             instructions="You are helpful assistant",
             toolset=toolset
         )
         logger.info(f"Created agent, agent ID: {agent.id}")
+        logger.info(f"Created agent, model name: {agent.model}")
+
     except Exception as e:
         logger.error(f"Error creating agent: {e}", exc_info=True)
         raise RuntimeError(f"Failed to create the agent: {e}")