Use data_utils

.devcontainer/Dockerfile

@@ -0,0 +1,8 @@
+ARG VARIANT=bullseye
+FROM mcr.microsoft.com/vscode/devcontainers/base:0-${VARIANT}
+RUN export DEBIAN_FRONTEND=noninteractive \
+     && apt-get update && apt-get install -y xdg-utils \
+     && apt-get clean -y && rm -rf /var/lib/apt/lists/*
+RUN mkdir -p /opt/microsoft/azd \
+     && curl -L https://github.com/Azure/azure-dev/releases/download/azure-dev-cli_0.9.0-beta.2/azd-linux-arm64-beta.tar.gz | tar zxvf - -C /opt/microsoft/azd \
+     && ln -s /opt/microsoft/azd/azd-linux-arm64 /usr/local/bin/azd

.devcontainer/devcontainer.json

@@ -0,0 +1,33 @@
+{
+    "name": "Azure Developer CLI",
+    "build": {
+        "dockerfile": "Dockerfile",
+        "args": {
+            "VARIANT": "bullseye"
+        }
+    },
+    "features": {
+        "ghcr.io/devcontainers/features/node:1": {
+            "version": "16",
+            "nodeGypDependencies": false
+        },
+        "ghcr.io/devcontainers/features/azure-cli:1.0.8": {}
+    },
+    "customizations": {
+        "vscode": {
+            "extensions": [
+                "ms-azuretools.azure-dev",
+                "ms-azuretools.vscode-bicep",
+                "ms-python.python"
+            ]
+        }
+    },
+    "forwardPorts": [
+        5000
+    ],
+    "postCreateCommand": "",
+    "remoteUser": "vscode",
+    "hostRequirements": {
+        "memory": "8gb"
+    }
+}

.gitignore

@@ -1,4 +1,6 @@
 .venv
 frontend/node_modules
 .env
-static
+static
+.azure/
+__pycache__/

README_azd.md

@@ -0,0 +1,70 @@
+# (Preview) Sample Chat App with AOAI
+
+## Deploying with the Azure Developer CLI
+
+> **IMPORTANT:** In order to deploy and run this example, you'll need an **Azure subscription with access enabled for the Azure OpenAI service**. You can request access [here](https://aka.ms/oaiapply). You can also visit [here](https://azure.microsoft.com/free/cognitive-search/) to get some free Azure credits to get you started.
+
+> **AZURE RESOURCE COSTS** by default this sample will create Azure App Service and Azure Cognitive Search resources that have a monthly cost, as well as Form Recognizer resource that has cost per document page. You can switch them to free versions of each of them if you want to avoid this cost by changing the parameters file under the infra folder (though there are some limits to consider; for example, you can have up to 1 free Cognitive Search resource per subscription, and the free Form Recognizer resource only analyzes the first 2 pages of each document.)
+
+### Prerequisites
+
+If you open this project in GitHub Codespaces or a local Dev Container, these will be available in the environment.
+Otherwise, you need to install them locally.
+
+- [Azure Developer CLI](https://aka.ms/azure-dev/install)
+- [Python 3+](https://www.python.org/downloads/)
+    - **Important**: Python and the pip package manager must be in the path in Windows for the setup scripts to work.
+- [Node.js](https://nodejs.org/en/download/)
+- [Git](https://git-scm.com/downloads)
+- [Powershell 7+ (pwsh)](https://github.com/powershell/powershell) - For Windows users only.
+   - **Important**: Ensure you can run `pwsh.exe` from a PowerShell command. If this fails, you likely need to upgrade PowerShell.
+
+>NOTE: Your Azure Account must have `Microsoft.Authorization/roleAssignments/write` permissions, such as [User Access Administrator](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles#user-access-administrator) or [Owner](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles#owner).  
+
+### Starting from scratch:
+
+If you don't have any pre-existing Azure services (i.e. OpenAI or Cognitive Search service), then you can provision
+all resources from scratch by following these steps:
+
+1. Run `azd up` - This will provision Azure resources and deploy this sample to those resources, including building the search index based on the files found in the `./data` folder.
+1. After the application has been successfully deployed you will see a URL printed to the console.  Click that URL to interact with the application in your browser.
+    > NOTE: It may take a minute for the application to be fully deployed. If you see a "Python Developer" welcome screen, then wait a minute and refresh the page.
+
+### Use existing resources:
+
+If you have existing Azure resources that you want to reuse, then you must first set `azd` environment variables _before_ running `azd up`.
+
+Run the following commands based on what you want to customize:
+
+* `azd env set AZURE_OPENAI_RESOURCE {Name of existing OpenAI service}`
+* `azd env set AZURE_OPENAI_RESOURCE_GROUP {Name of existing resource group that OpenAI service is provisioned to}`
+* `azd env set AZURE_OPENAI_SKU_NAME {Name of OpenAI SKU}`. Defaults to 'S0'.
+* `azd env set AZURE_SEARCH_SERVICE {Name of existing Cognitive Search service}`
+* `azd env set AZURE_SEARCH_SERVICE_RESOURCE_GROUP {Name of existing resource group that Cognitive Search service is provisioned to}`
+* `azd env set AZURE_SEARCH_SKU_NAME {Name of Cognitive Search SKY}`. Defaults to 'standard'.
+* `azd env set AZURE_STORAGE_ACCOUNT {Name of existing Storage account}`. Used by prepdocs.py for uploading docs.
+* `azd env set AZURE_STORAGE_ACCOUNT_RESOURCE_GROUP {Name of existing resource group that Storage account is provisioned to}`. 
+* `azd env set AZURE_FORMRECOGNIZER_SERVICE {Name of existing Form Recognizer service}`. Used by prepdocs.py for text extraction from docs.
+* `azd env set AZURE_FORMRECOGNIZER_SERVICE_RESOURCE_GROUP {Name of existing resource group that Form Recognizer service is provisioned to}`.
+* `azd env set AZURE_FORMRECOGNIZER_SKU_NAME {Name of Form Recognizer SKU}`. Defaults to 'S0'.
+
+
+1. Run `azd up`. This will provision any missing Azure resources and deploy this sample to those resources, including building the search index based on the files found in the `./data` folder.
+1. After the application has been successfully deployed you will see a URL printed to the console.  Click that URL to interact with the application in your browser.
+    > NOTE: It may take a minute for the application to be fully deployed. If you see a "Python Developer" welcome screen, then wait a minute and refresh the page.
+
+
+### Re-deploying changes
+
+If you make any changes to the app code (JS or Python), you can re-deploy the app code to App Service by running the `azd deploy` command.
+
+If you change any of the Bicep files in the infra folder, then you should re-run `azd up` to both provision resources and deploy code.
+
+### Running locally:
+
+1. Run `azd auth login`
+3. Run `./start.cmd` or `./start.sh` to start the project locally.
+
+### Note
+
+>Note: The PDF documents used in this demo contain information generated using a language model (Azure OpenAI Service). The information contained in these documents is only for demonstration purposes and does not reflect the opinions or beliefs of Microsoft. Microsoft makes no representations or warranties of any kind, express or implied, about the completeness, accuracy, reliability, suitability or availability with respect to the information contained in this document. All rights reserved to Microsoft.

app.py

@@ -10,6 +10,9 @@
 
 app = Flask(__name__)
 
+# setup basic logging
+logging.basicConfig(level=logging.INFO)
+
 @app.route("/", defaults={"path": "index.html"})
 @app.route("/<path:path>")
 def static_file(path):
@@ -26,6 +29,7 @@ def static_file(path):
 AZURE_SEARCH_CONTENT_COLUMNS = os.environ.get("AZURE_SEARCH_CONTENT_COLUMNS")
 AZURE_SEARCH_FILENAME_COLUMN = os.environ.get("AZURE_SEARCH_FILENAME_COLUMN")
 AZURE_SEARCH_TITLE_COLUMN = os.environ.get("AZURE_SEARCH_TITLE_COLUMN")
+print('title', AZURE_SEARCH_TITLE_COLUMN)
 AZURE_SEARCH_URL_COLUMN = os.environ.get("AZURE_SEARCH_URL_COLUMN")
 
 # AOAI Integration Settings
@@ -44,7 +48,7 @@ def static_file(path):
 SHOULD_STREAM = True if AZURE_OPENAI_STREAM.lower() == "true" else False
 
 def is_chat_model():
-    if 'gpt-4' in AZURE_OPENAI_MODEL_NAME.lower():
+    if 'gpt-4' in AZURE_OPENAI_MODEL_NAME.lower() or 'gpt-35' in AZURE_OPENAI_MODEL_NAME.lower():
         return True
     return False
 
@@ -85,7 +89,7 @@ def prepare_body_headers_with_data(request):
             }
         ]
     }
-
+    app.logger.info(body)
     chatgpt_url = f"https://{AZURE_OPENAI_RESOURCE}.openai.azure.com/openai/deployments/{AZURE_OPENAI_MODEL}"
     if is_chat_model():
         chatgpt_url += "/chat/completions?api-version=2023-03-15-preview"
@@ -138,7 +142,7 @@ def stream_with_data(body, headers, endpoint):
                         deltaText = lineJson["choices"][0]["messages"][0]["delta"]["content"]
                         if deltaText != "[DONE]":
                             response["choices"][0]["messages"][1]["content"] += deltaText                
-
+                    app.logger.info(response)
                     yield json.dumps(response).replace("\n", "\\n") + "\n"
     except Exception as e:
         yield json.dumps({"error": str(e)}).replace("\n", "\\n") + "\n"

azure.yaml

@@ -0,0 +1,34 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/Azure/azure-dev/main/schemas/v1.0/azure.yaml.json
+
+name: sample-app-aoai-chatgpt
+metadata:
+  template: [email protected]
+services:
+  backend:
+    project: .
+    language: py
+    host: appservice
+    hooks:
+      prepackage:
+        windows:
+          shell: pwsh
+          run:  cd ./frontend;npm install;npm run build
+          interactive: true
+          continueOnError: false
+        posix:
+          shell: sh
+          run:  cd ./frontend;npm install;npm run build
+          interactive: true
+          continueOnError: false
+hooks:
+    postprovision:
+      windows:
+        shell: pwsh
+        run: $output = azd env get-values; Add-Content -Path .env -Value $output;
+        interactive: true
+        continueOnError: false
+      posix:
+        shell: sh
+        run: azd env get-values > .env
+        interactive: true
+        continueOnError: false

infra/abbreviations.json

@@ -0,0 +1,135 @@
+{
+  "analysisServicesServers": "as",
+  "apiManagementService": "apim-",
+  "appConfigurationConfigurationStores": "appcs-",
+  "appManagedEnvironments": "cae-",
+  "appContainerApps": "ca-",
+  "authorizationPolicyDefinitions": "policy-",
+  "automationAutomationAccounts": "aa-",
+  "blueprintBlueprints": "bp-",
+  "blueprintBlueprintsArtifacts": "bpa-",
+  "cacheRedis": "redis-",
+  "cdnProfiles": "cdnp-",
+  "cdnProfilesEndpoints": "cdne-",
+  "cognitiveServicesAccounts": "cog-",
+  "cognitiveServicesFormRecognizer": "cog-fr-",
+  "cognitiveServicesTextAnalytics": "cog-ta-",
+  "computeAvailabilitySets": "avail-",
+  "computeCloudServices": "cld-",
+  "computeDiskEncryptionSets": "des",
+  "computeDisks": "disk",
+  "computeDisksOs": "osdisk",
+  "computeGalleries": "gal",
+  "computeSnapshots": "snap-",
+  "computeVirtualMachines": "vm",
+  "computeVirtualMachineScaleSets": "vmss-",
+  "containerInstanceContainerGroups": "ci",
+  "containerRegistryRegistries": "cr",
+  "containerServiceManagedClusters": "aks-",
+  "databricksWorkspaces": "dbw-",
+  "dataFactoryFactories": "adf-",
+  "dataLakeAnalyticsAccounts": "dla",
+  "dataLakeStoreAccounts": "dls",
+  "dataMigrationServices": "dms-",
+  "dBforMySQLServers": "mysql-",
+  "dBforPostgreSQLServers": "psql-",
+  "devicesIotHubs": "iot-",
+  "devicesProvisioningServices": "provs-",
+  "devicesProvisioningServicesCertificates": "pcert-",
+  "documentDBDatabaseAccounts": "cosmos-",
+  "eventGridDomains": "evgd-",
+  "eventGridDomainsTopics": "evgt-",
+  "eventGridEventSubscriptions": "evgs-",
+  "eventHubNamespaces": "evhns-",
+  "eventHubNamespacesEventHubs": "evh-",
+  "hdInsightClustersHadoop": "hadoop-",
+  "hdInsightClustersHbase": "hbase-",
+  "hdInsightClustersKafka": "kafka-",
+  "hdInsightClustersMl": "mls-",
+  "hdInsightClustersSpark": "spark-",
+  "hdInsightClustersStorm": "storm-",
+  "hybridComputeMachines": "arcs-",
+  "insightsActionGroups": "ag-",
+  "insightsComponents": "appi-",
+  "keyVaultVaults": "kv-",
+  "kubernetesConnectedClusters": "arck",
+  "kustoClusters": "dec",
+  "kustoClustersDatabases": "dedb",
+  "logicIntegrationAccounts": "ia-",
+  "logicWorkflows": "logic-",
+  "machineLearningServicesWorkspaces": "mlw-",
+  "managedIdentityUserAssignedIdentities": "id-",
+  "managementManagementGroups": "mg-",
+  "migrateAssessmentProjects": "migr-",
+  "networkApplicationGateways": "agw-",
+  "networkApplicationSecurityGroups": "asg-",
+  "networkAzureFirewalls": "afw-",
+  "networkBastionHosts": "bas-",
+  "networkConnections": "con-",
+  "networkDnsZones": "dnsz-",
+  "networkExpressRouteCircuits": "erc-",
+  "networkFirewallPolicies": "afwp-",
+  "networkFirewallPoliciesWebApplication": "waf",
+  "networkFirewallPoliciesRuleGroups": "wafrg",
+  "networkFrontDoors": "fd-",
+  "networkFrontdoorWebApplicationFirewallPolicies": "fdfp-",
+  "networkLoadBalancersExternal": "lbe-",
+  "networkLoadBalancersInternal": "lbi-",
+  "networkLoadBalancersInboundNatRules": "rule-",
+  "networkLocalNetworkGateways": "lgw-",
+  "networkNatGateways": "ng-",
+  "networkNetworkInterfaces": "nic-",
+  "networkNetworkSecurityGroups": "nsg-",
+  "networkNetworkSecurityGroupsSecurityRules": "nsgsr-",
+  "networkNetworkWatchers": "nw-",
+  "networkPrivateDnsZones": "pdnsz-",
+  "networkPrivateLinkServices": "pl-",
+  "networkPublicIPAddresses": "pip-",
+  "networkPublicIPPrefixes": "ippre-",
+  "networkRouteFilters": "rf-",
+  "networkRouteTables": "rt-",
+  "networkRouteTablesRoutes": "udr-",
+  "networkTrafficManagerProfiles": "traf-",
+  "networkVirtualNetworkGateways": "vgw-",
+  "networkVirtualNetworks": "vnet-",
+  "networkVirtualNetworksSubnets": "snet-",
+  "networkVirtualNetworksVirtualNetworkPeerings": "peer-",
+  "networkVirtualWans": "vwan-",
+  "networkVpnGateways": "vpng-",
+  "networkVpnGatewaysVpnConnections": "vcn-",
+  "networkVpnGatewaysVpnSites": "vst-",
+  "notificationHubsNamespaces": "ntfns-",
+  "notificationHubsNamespacesNotificationHubs": "ntf-",
+  "operationalInsightsWorkspaces": "log-",
+  "portalDashboards": "dash-",
+  "powerBIDedicatedCapacities": "pbi-",
+  "purviewAccounts": "pview-",
+  "recoveryServicesVaults": "rsv-",
+  "resourcesResourceGroups": "rg-",
+  "searchSearchServices": "srch-",
+  "serviceBusNamespaces": "sb-",
+  "serviceBusNamespacesQueues": "sbq-",
+  "serviceBusNamespacesTopics": "sbt-",
+  "serviceEndPointPolicies": "se-",
+  "serviceFabricClusters": "sf-",
+  "signalRServiceSignalR": "sigr",
+  "sqlManagedInstances": "sqlmi-",
+  "sqlServers": "sql-",
+  "sqlServersDataWarehouse": "sqldw-",
+  "sqlServersDatabases": "sqldb-",
+  "sqlServersDatabasesStretch": "sqlstrdb-",
+  "storageStorageAccounts": "st",
+  "storageStorageAccountsVm": "stvm",
+  "storSimpleManagers": "ssimp",
+  "streamAnalyticsCluster": "asa-",
+  "synapseWorkspaces": "syn",
+  "synapseWorkspacesAnalyticsWorkspaces": "synw",
+  "synapseWorkspacesSqlPoolsDedicated": "syndp",
+  "synapseWorkspacesSqlPoolsSpark": "synsp",
+  "timeSeriesInsightsEnvironments": "tsi-",
+  "webServerFarms": "plan-",
+  "webSitesAppService": "app-",
+  "webSitesAppServiceEnvironment": "ase-",
+  "webSitesFunctions": "func-",
+  "webStaticSites": "stapp-"
+}

infra/core/ai/cognitiveservices.bicep

@@ -0,0 +1,40 @@
+param name string
+param location string = resourceGroup().location
+param tags object = {}
+
+param customSubDomainName string = name
+param deployments array = []
+param kind string = 'OpenAI'
+param publicNetworkAccess string = 'Enabled'
+param sku object = {
+  name: 'S0'
+}
+
+resource account 'Microsoft.CognitiveServices/accounts@2022-10-01' = {
+  name: name
+  location: location
+  tags: tags
+  kind: kind
+  properties: {
+    customSubDomainName: customSubDomainName
+    publicNetworkAccess: publicNetworkAccess
+  }
+  sku: sku
+}
+
+@batchSize(1)
+resource deployment 'Microsoft.CognitiveServices/accounts/deployments@2022-10-01' = [for deployment in deployments: {
+  parent: account
+  name: deployment.name
+  properties: {
+    model: deployment.model
+    raiPolicyName: contains(deployment, 'raiPolicyName') ? deployment.raiPolicyName : null
+    scaleSettings: deployment.scaleSettings
+  }
+}]
+
+output endpoint string = account.properties.endpoint
+output id string = account.id
+output name string = account.name
+output skuName string = account.sku.name
+output key string = account.listKeys().key1