Merge pull request #372 from microsoft/fix/error-analyzer-path-not-found

fix: Deploy AI model and Process Sample data manually

Author: Avijit-Microsoft

.devcontainer/devcontainer.json

@@ -3,7 +3,12 @@
     "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
     "forwardPorts": [50505],
     "features": {
-        "ghcr.io/azure/azure-dev/azd:latest": {}
+        "ghcr.io/azure/azure-dev/azd:latest": {},
+        "ghcr.io/jlaundry/devcontainer-features/mssql-odbc-driver:1": {
+            "version": "18"
+        },
+        "ghcr.io/devcontainers/features/azure-cli:1": {},
+        "ghcr.io/devcontainers/features/powershell:1": {}
     },
     "customizations": {
         "vscode": {
@@ -16,7 +21,7 @@
             ]
         }
     },
-    "postStartCommand": "git pull origin main && python3 -m pip install -r infra/scripts/index_scripts/requirements.txt && curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash && chmod +x ./infra/scripts/quota_check_params.sh",
+    "postStartCommand": "git pull origin main && python3 -m pip install -r infra/scripts/index_scripts/requirements.txt && chmod +x ./infra/scripts/quota_check_params.sh",
     "remoteUser": "vscode",
     "hostRequirements": {
         "memory": "4gb"

.gitignore

@@ -10,3 +10,5 @@
 .fake
 .azure
 .idea
+scriptenv/
+__pycache__/

README.md

@@ -136,6 +136,7 @@ If you're not using one of the above options for opening the project, then you'l
     * [Docker Desktop](https://www.docker.com/products/docker-desktop/)
     * [Git](https://git-scm.com/downloads)
     * [Powershell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.5)<br/>Required for Windows users only. Follow the steps [here](./docs/PowershellSetup.md) to add it to the Windows PATH.
+    * [ODBC Driver 18 for SQL Server](https://learn.microsoft.com/sql/connect/odbc/download-odbc-driver-for-sql-server)
 
 2. Download the project code:
 
@@ -189,10 +190,17 @@ To change the azd parameters from the default values, follow the steps [here](./
 
 3. Provide an `azd` environment name (like "ckmapp")
 4. Select a subscription from your Azure account, and select a location which has quota for all the resources. 
-    * This deployment will take *7-10 minutes* to provision the resources in your account and set up the solution with sample data. 
+    * This deployment will take *7-10 minutes* to provision the resources in your account. 
     * If you get an error or timeout with deployment, changing the location can help, as there may be availability constraints for the resources.
-
-5. Once the deployment has completed successfully, open the [Azure Portal](https://portal.azure.com/), go to the deployed resource group, find the App Service and get the app URL from `Default domain`.
+5. Once the infrastructure deployment completes successfully, you can proceed with deploying the AI model by running the bash command displayed in the terminal. The command will look similar to the following: 
+    ```shell 
+    bash ./infra/scripts/deploy_ai_model.sh <Resource-Group-Name> <Solution-Name> <OpenAI-Model-Deployment-Type> <OpenAI-Deployment-Model> <OpenAI-Deployment-Model-Capacity> <OpenAI-Embedding-Model> <OpenAI-Embedding-Model-Capacity> <Managed-Identity-Client-ID>
+    ```
+6. After the AI model deployment finishes, if you wish to load the sample data, you can then run the corresponding sample data processing command, which will also be shown in the terminal: 
+    ```shell 
+    bash ./infra/scripts/process_sample_data.sh <Storage-Account-Name> <Storage-Container-Name> <Managed-Identity-Client-ID> <Key-Vault-Name> <SQLDB-Server> <SQLDB-Database> <Resource-Group-Name> <API-App-Managed-Identity-Client-ID> <API-App-Managed-Identity-Name>
+    ```
+7. Once the deployment has completed successfully, open the [Azure Portal](https://portal.azure.com/), go to the deployed resource group, find the App Service and get the app URL from `Default domain`.
 
 6. You can now delete the resources by running `azd down`, if you are done trying out the application. 
 <!-- 6. You can now proceed to run the [development server](#development-server) to test the app locally, or if you are done trying out the app, you can delete the resources by running `azd down`. -->
@@ -302,4 +310,4 @@ You acknowledge that the Software and Microsoft Products and Services (1) are no
 
 You acknowledge the Software is not subject to SOC 1 and SOC 2 compliance audits. No Microsoft technology, nor any of its component technologies, including the Software, is intended or made available as a substitute for the professional advice, opinion, or judgement of a certified financial services professional. Do not use the Software to replace, substitute, or provide professional financial advice or judgment.  
 
-BY ACCESSING OR USING THE SOFTWARE, YOU ACKNOWLEDGE THAT THE SOFTWARE IS NOT DESIGNED OR INTENDED TO SUPPORT ANY USE IN WHICH A SERVICE INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE COULD RESULT IN THE DEATH OR SERIOUS BODILY INJURY OF ANY PERSON OR IN PHYSICAL OR ENVIRONMENTAL DAMAGE (COLLECTIVELY, “HIGH-RISK USE”), AND THAT YOU WILL ENSURE THAT, IN THE EVENT OF ANY INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE, THE SAFETY OF PEOPLE, PROPERTY, AND THE ENVIRONMENT ARE NOT REDUCED BELOW A LEVEL THAT IS REASONABLY, APPROPRIATE, AND LEGAL, WHETHER IN GENERAL OR IN A SPECIFIC INDUSTRY. BY ACCESSING THE SOFTWARE, YOU FURTHER ACKNOWLEDGE THAT YOUR HIGH-RISK USE OF THE SOFTWARE IS AT YOUR OWN RISK.  
+BY ACCESSING OR USING THE SOFTWARE, YOU ACKNOWLEDGE THAT THE SOFTWARE IS NOT DESIGNED OR INTENDED TO SUPPORT ANY USE IN WHICH A SERVICE INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE COULD RESULT IN THE DEATH OR SERIOUS BODILY INJURY OF ANY PERSON OR IN PHYSICAL OR ENVIRONMENTAL DAMAGE (COLLECTIVELY, “HIGH-RISK USE”), AND THAT YOU WILL ENSURE THAT, IN THE EVENT OF ANY INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE, THE SAFETY OF PEOPLE, PROPERTY, AND THE ENVIRONMENT ARE NOT REDUCED BELOW A LEVEL THAT IS REASONABLY, APPROPRIATE, AND LEGAL, WHETHER IN GENERAL OR IN A SPECIFIC INDUSTRY. BY ACCESSING THE SOFTWARE, YOU FURTHER ACKNOWLEDGE THAT YOUR HIGH-RISK USE OF THE SOFTWARE IS AT YOUR OWN RISK.  

azure.yaml

@@ -14,17 +14,21 @@ hooks:
       run: |
         Write-Host "Web app URL: "
         Write-Host "$env:WEB_APP_URL" -ForegroundColor Cyan
+        Write-Host "🚀 If you want to deploy the AI Model, run the following command in the Bash terminal:"
+        Write-Host "bash ./infra/scripts/deploy_ai_model.sh $env:RESOURCE_GROUP_NAME $env:SOLUTION_NAME $env:AZURE_OPEN_AI_MODEL_DEPLOYMENT_TYPE $env:AZURE_OPEN_AI_DEPLOYMENT_MODEL $env:AZURE_OPEN_AI_DEPLOYMENT_MODEL_CAPACITY $env:AZURE_OPENAI_EMBEDDING_MODEL $env:AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY $env:MANAGED_IDENTITY_CLIENT_ID" -ForegroundColor Cyan
         Write-Host "✅ If you want to use the Sample Data, run the following command in the Bash terminal to process it:"
-        Write-Host "bash ./infra/scripts/process_sample_data.sh <storage_account_name> <storage_container_name> <managed_client_id> <key_vault_name> <sql_server_name> <sql_database_name> <resource_group_name>" -ForegroundColor Cyan
+        Write-Host "bash ./infra/scripts/process_sample_data.sh $env:STORAGE_ACCOUNT_NAME $env:STORAGE_CONTAINER_NAME $env:MANAGED_IDENTITY_CLIENT_ID $env:KEY_VAULT_NAME $env:SQLDB_SERVER $env:SQLDB_DATABASE $env:RESOURCE_GROUP_NAME $env:API_APP_MANAGED_IDENTITY_CLIENT_ID $env:API_APP_MANAGED_IDENTITY_NAME" -ForegroundColor Cyan
       shell: pwsh
       continueOnError: false
       interactive: true
     posix:
       run: |
         echo "Web app URL: "
         echo $WEB_APP_URL
+        echo "🚀 If you want to deploy the AI Model, run the following command in the Bash terminal:"
+        echo "bash ./infra/scripts/deploy_ai_model.sh $RESOURCE_GROUP_NAME $SOLUTION_NAME $AZURE_OPEN_AI_MODEL_DEPLOYMENT_TYPE $AZURE_OPEN_AI_DEPLOYMENT_MODEL $AZURE_OPEN_AI_DEPLOYMENT_MODEL_CAPACITY $AZURE_OPENAI_EMBEDDING_MODEL $AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY $MANAGED_IDENTITY_CLIENT_ID"
         echo "✅ If you want to use the Sample Data, run the following command in the Bash terminal to process it:"
-        echo "bash ./infra/scripts/process_sample_data.sh <storage_account_name> <storage_container_name> <managed_client_id> <key_vault_name> <sql_server_name> <sql_database_name> <resource_group_name>"
+        echo "bash ./infra/scripts/process_sample_data.sh $STORAGE_ACCOUNT_NAME $STORAGE_CONTAINER_NAME $MANAGED_IDENTITY_CLIENT_ID $KEY_VAULT_NAME $SQLDB_SERVER $SQLDB_DATABASE $RESOURCE_GROUP_NAME $API_APP_MANAGED_IDENTITY_CLIENT_ID $API_APP_MANAGED_IDENTITY_NAME"
       shell: sh
       continueOnError: false
       interactive: true

docs/CustomizingAzdParameters.md

@@ -8,41 +8,41 @@ By default this template will use the environment name as the prefix to prevent
 Change the Content Understanding Location (allowed values: Sweden Central, Australia East)
 
 ```shell
-azd env set AZURE_ENV_CU_LOCATION 'swedencentral'
+azd env set AZURE_CONTENT_UNDERSTANDING_LOCATION 'swedencentral'
 ```
 
 Change the Secondary Location (example: eastus2, westus2, etc.)
 
 ```shell
-azd env set AZURE_ENV_SECONDARY_LOCATION eastus2
+azd env set AZURE_SECONDARY_LOCATION eastus2
 ```
 
 Change the Model Deployment Type (allowed values: Standard, GlobalStandard)
 
 ```shell
-azd env set AZURE_ENV_MODEL_DEPLOYMENT_TYPE GlobalStandard
+azd env set AZURE_OPEN_AI_MODEL_DEPLOYMENT_TYPE GlobalStandard
 ```
 
 Set the Model Name (allowed values: gpt-4o-mini, gpt-4o, gpt-4)
 
 ```shell
-azd env set AZURE_ENV_MODEL_NAME gpt-4o-mini
+azd env set AZURE_OPEN_AI_DEPLOYMENT_MODEL gpt-4o-mini
 ```
 
 Change the Model Capacity (choose a number based on available GPT model capacity in your subscription)
 
 ```shell
-azd env set AZURE_ENV_MODEL_CAPACITY 30
+azd env set AZURE_OPEN_AI_DEPLOYMENT_MODEL_CAPACITY 30
 ```
 
 Change the Embedding Model 
 
 ```shell
-azd env set AZURE_ENV_EMBEDDING_MODEL_NAME text-embedding-ada-002
+azd env set AZURE_OPENAI_EMBEDDING_MODEL text-embedding-ada-002
 ```
 
 Change the Embedding Deployment Capacity (choose a number based on available embedding model capacity in your subscription)
 
 ```shell
-azd env set AZURE_ENV_EMBEDDING_MODEL_CAPACITY 80
+azd env set AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY 80
 ```

infra/deploy_ai_foundry.bicep

@@ -29,26 +29,6 @@ var aiHubDescription = 'AI Hub for KM template'
 var aiProjectName = '${solutionName}-aiproject'
 var aiProjectFriendlyName = aiProjectName
 var aiSearchName = '${solutionName}-search'
-var aiModelDeployments = [
-  {
-    name: gptModelName
-    model: gptModelName
-    sku: {
-      name: deploymentType
-      capacity: gptDeploymentCapacity
-    }
-    raiPolicyName: 'Microsoft.Default'
-  }
-  {
-    name: embeddingModel
-    model: embeddingModel
-    sku: {
-      name: 'Standard'
-      capacity: embeddingDeploymentCapacity
-    }
-    raiPolicyName: 'Microsoft.Default'
-  }
-]
 
 var containerRegistryNameCleaned = replace(containerRegistryName, '-', '')
 
@@ -217,23 +197,6 @@ resource aiServices_CU 'Microsoft.CognitiveServices/accounts@2024-04-01-preview'
   }
 }
 
-@batchSize(1)
-resource aiServicesDeployments 'Microsoft.CognitiveServices/accounts/deployments@2023-05-01' = [for aiModeldeployment in aiModelDeployments: {
-  parent: aiServices //aiServices_m
-  name: aiModeldeployment.name
-  properties: {
-    model: {
-      format: 'OpenAI'
-      name: aiModeldeployment.model
-    }
-    raiPolicyName: aiModeldeployment.raiPolicyName
-  }
-  sku:{
-    name: aiModeldeployment.sku.name
-    capacity: aiModeldeployment.sku.capacity
-  }
-}]
-
 resource aiSearch 'Microsoft.Search/searchServices@2023-11-01' = {
     name: aiSearchName
     location: solutionLocation
@@ -421,7 +384,7 @@ resource aiHub 'Microsoft.MachineLearningServices/workspaces@2023-08-01-preview'
       }
     }
     dependsOn: [
-      aiServicesDeployments,aiSearch
+      aiSearch
     ]
   }
 
@@ -445,7 +408,7 @@ resource aiHub 'Microsoft.MachineLearningServices/workspaces@2023-08-01-preview'
     }
   }
   dependsOn: [
-    aiServicesDeployments,aiSearch
+    aiSearch
   ]
 }
 

infra/deploy_ai_model.bicep

@@ -0,0 +1,48 @@
+param solutionName string
+param deploymentType string
+param gptModelName string
+param gptDeploymentCapacity int
+param embeddingModel string
+param embeddingDeploymentCapacity int
+var aiServicesName = '${solutionName}-aiservices'
+var aiModelDeployments = [
+  {
+    name: gptModelName
+    model: gptModelName
+    sku: {
+      name: deploymentType
+      capacity: gptDeploymentCapacity
+    }
+    raiPolicyName: 'Microsoft.Default'
+  }
+  {
+    name: embeddingModel
+    model: embeddingModel
+    sku: {
+      name: 'Standard'
+      capacity: embeddingDeploymentCapacity
+    }
+    raiPolicyName: 'Microsoft.Default'
+  }
+]
+
+resource existingAiServices 'Microsoft.CognitiveServices/accounts@2024-10-01' existing = {
+  name: aiServicesName
+}
+
+@batchSize(1)
+resource aiServicesDeployments 'Microsoft.CognitiveServices/accounts/deployments@2023-05-01' = [for aiModeldeployment in aiModelDeployments: {
+  parent: existingAiServices
+  name: aiModeldeployment.name
+  properties: {
+    model: {
+      format: 'OpenAI'
+      name: aiModeldeployment.model
+    }
+    raiPolicyName: aiModeldeployment.raiPolicyName
+  }
+  sku:{
+    name: aiModeldeployment.sku.name
+    capacity: aiModeldeployment.sku.capacity
+  }
+}]

infra/main.bicep

@@ -71,8 +71,6 @@ var resourceGroupLocation = resourceGroup().location
 // var resourceGroupName = resourceGroup().name
 
 var solutionLocation = resourceGroupLocation
-var baseUrl = 'https://raw.githubusercontent.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator/main/'
-
 
 // ========== Managed Identity ========== //
 module managedIdentityModule 'deploy_managed_identity.bicep' = {
@@ -244,4 +242,43 @@ module frontend_docker 'deploy_frontend_docker.bicep'= {
   scope: resourceGroup(resourceGroup().name)
 }
 
+output SOLUTION_NAME string = solutionPrefix
+output RESOURCE_GROUP_NAME string = resourceGroup().name
+output RESOURCE_GROUP_LOCATION string = resourceGroupLocation
+output ENVIRONMENT_NAME string = environmentName
+output AZURE_CONTENT_UNDERSTANDING_LOCATION string = contentUnderstandingLocation
+output AZURE_SECONDARY_LOCATION string = secondaryLocation
+output APPINSIGHTS_INSTRUMENTATIONKEY string = ''
+output AZURE_AI_PROJECT_CONN_STRING string = ''
+output AZURE_AI_SEARCH_API_KEY string = ''
+output AZURE_AI_SEARCH_ENDPOINT string = aifoundry.outputs.aiSearchTarget
+output AZURE_AI_SEARCH_INDEX string = 'call_transcripts_index'
+output AZURE_COSMOSDB_ACCOUNT string = cosmosDBModule.outputs.cosmosAccountName
+output AZURE_COSMOSDB_CONVERSATIONS_CONTAINER string = 'conversations'
+output AZURE_COSMOSDB_DATABASE string = 'db_conversation_history'
+output AZURE_COSMOSDB_ENABLE_FEEDBACK string = 'True'
+output AZURE_OPEN_AI_DEPLOYMENT_MODEL string = gptModelName
+output AZURE_OPEN_AI_DEPLOYMENT_MODEL_CAPACITY int = gptDeploymentCapacity
+output AZURE_OPEN_AI_ENDPOINT string = aifoundry.outputs.aiServicesTarget
+output AZURE_OPENAI_API_KEY string = ''
+output AZURE_OPEN_AI_MODEL_DEPLOYMENT_TYPE string = deploymentType
+output AZURE_OPENAI_EMBEDDING_MODEL string = embeddingModel
+output AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY int = embeddingDeploymentCapacity
+output AZURE_OPENAI_API_VERSION string = azureOpenAIApiVersion
+output AZURE_OPENAI_RESOURCE string = aifoundry.outputs.aiServicesName
+output OPENAI_API_VERSION string = azureOpenAIApiVersion
+output SQLDB_DATABASE string = sqlDBModule.outputs.sqlDbName
+output SQLDB_SERVER string = sqlDBModule.outputs.sqlServerName
+output SQLDB_USER_MID string = managedIdentityModule.outputs.managedIdentityBackendAppOutput.clientId
+output SQLDB_USERNAME string = sqlDBModule.outputs.sqlDbUser
+output USE_AI_PROJECT_CLIENT string = 'False'
+output USE_CHAT_HISTORY_ENABLED string = 'True'
+
+output MANAGED_IDENTITY_CLIENT_ID string = managedIdentityModule.outputs.managedIdentityOutput.clientId
+output STORAGE_ACCOUNT_NAME string = storageAccount.outputs.storageName
+output STORAGE_CONTAINER_NAME string = storageAccount.outputs.storageContainer
+output KEY_VAULT_NAME string = kvault.outputs.keyvaultName
+output API_APP_MANAGED_IDENTITY_CLIENT_ID string = managedIdentityModule.outputs.managedIdentityBackendAppOutput.clientId
+output API_APP_MANAGED_IDENTITY_NAME string = managedIdentityModule.outputs.managedIdentityBackendAppOutput.name
+output API_APP_URL string = backend_docker.outputs.appUrl
 output WEB_APP_URL string = frontend_docker.outputs.appUrl

infra/main.bicepparam

@@ -1,10 +1,10 @@
 using './main.bicep'
 
 param environmentName = readEnvironmentVariable('AZURE_ENV_NAME', 'env_name')
-param contentUnderstandingLocation = readEnvironmentVariable('AZURE_ENV_CU_LOCATION', 'swedencentral')
-param secondaryLocation = readEnvironmentVariable('AZURE_ENV_SECONDARY_LOCATION', 'eastus2')
-param deploymentType = readEnvironmentVariable('AZURE_ENV_MODEL_DEPLOYMENT_TYPE', 'GlobalStandard')
-param gptModelName = readEnvironmentVariable('AZURE_ENV_MODEL_NAME', 'gpt-4o-mini')
-param gptDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_MODEL_CAPACITY', '30'))
-param embeddingModel = readEnvironmentVariable('AZURE_ENV_EMBEDDING_MODEL_NAME', 'text-embedding-ada-002')
-param embeddingDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_EMBEDDING_MODEL_CAPACITY', '80'))
+param contentUnderstandingLocation = readEnvironmentVariable('AZURE_CONTENT_UNDERSTANDING_LOCATION', 'swedencentral')
+param secondaryLocation = readEnvironmentVariable('AZURE_SECONDARY_LOCATION', 'eastus2')
+param deploymentType = readEnvironmentVariable('AZURE_OPEN_AI_MODEL_DEPLOYMENT_TYPE', 'GlobalStandard')
+param gptModelName = readEnvironmentVariable('AZURE_OPEN_AI_DEPLOYMENT_MODEL', 'gpt-4o-mini')
+param gptDeploymentCapacity = int(readEnvironmentVariable('AZURE_OPEN_AI_DEPLOYMENT_MODEL_CAPACITY', '30'))
+param embeddingModel = readEnvironmentVariable('AZURE_OPENAI_EMBEDDING_MODEL', 'text-embedding-ada-002')
+param embeddingDeploymentCapacity = int(readEnvironmentVariable('AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY', '80'))