keyvault

.gitignore

@@ -1 +1,2 @@
-.azure
+.azure
+local/

README.md

@@ -1,84 +1,69 @@
 # GPT on Your Data
 
-## Main components
+Reference implementation of the Retrieval-Augmented Generation (RAG) pattern. 
 
-1) [Data ingestion](https://github.com/Azure/gpt-rag-ingestion)
-
-2) [Orchestrator](https://github.com/Azure/gpt-rag-orchestrator)
-
-3) [App Front-End](https://github.com/Azure/gpt-rag-frontend)
-
-## General Architecture Overview
+## Architecture Overview
 
 <img src="media/oyd-rag.png" alt="imagem" width="1024">
 
+Components: 
+
+[1 Data ingestion](https://github.com/Azure/gpt-rag-ingestion) ;
+[2 Orchestrator](https://github.com/Azure/gpt-rag-orchestrator) ;
+[3 App Front-End](https://github.com/Azure/gpt-rag-frontend)
 
 ## A Simple Retrieval-Augmented Generation Model
 
 <img src="media/RAG.png" alt="imagem" width="1024">
 
-
 ## Zero Trust Architecture Overview
 
 <img src="media/GPT-RAG_35.png" alt="imagem" width="1024">
 
+<!-- ## Prerequisites
 
+- [Azure Developer CLI](https://aka.ms/azure-dev/install) -->
 
-## Prerequisites
+## Deploy
 
-- [Azure Developer CLI](https://aka.ms/azure-dev/install)
+To deploy this solution you just need to execute the next four steps:
 
-## Deploy
+**1) Provision required Azure services**
+
+You can do it by clicking on the following button
 
-1) Create a new folder and switch to it in the terminal.
-2) Run `azd auth login` (if you did not run this before).
-3) If did not clone the repo already, run `azd init -t azure/gpt-rag`.
-4) There are 2 options how you can set the name of the resources created on Azure:
-
-  - Pick the name for each resource at `infra/main.parameters.json`. Add a key and value for each of the next keys within the `parameters` map:
-  ```json
-    "resourceGroupName": {
-      "value": "name-for-the-resource-group"
-    },
-    "keyVaultName": {
-      "value": "name-for-key-vault"
-    },
-    "azureFunctionsServicePlanName":{
-      "value": "name-for-service-plan"
-    },
-    "orchestratorFunctionsName":{
-      "value": "name-for-orchestrator-function"
-    },
-    "dataIngestionFunctionsName":{
-      "value": "name-for-data-ingestion-function"
-    },
-    "searchServiceName": {
-      "value": "name-for-search-service"
-    }
-    "openAiServiceName": {
-      "value": "name-for-open-ai-service"
-    }
-  ```
-
--   Alternately, you can set the name of each resource and save it within the azd-environment. Add the `infra` and `parameters` fields within the `config.json` file, next to the azd .env file. For example `.azure/azd-env-name/config.json`.
-
-```json
-  "infra": {
-    "parameters": {
-      "azureFunctionsServicePlanName": "the-plan",
-      "dataIngestionFunctionsName": "data-ingest-func",
-      "keyVaultName": "vv-kv-vh2",
-      "openAiServiceName": "ai-s-r",
-      "orchestratorFunctionsName": "o-fun",
-      "resourceGroupName": "viva-rg",
-      "searchServiceName": "sea"
-    }
-  }
+[![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fazure%2Fgpt-rag%2Fmain%2Finfra%2Fmain.json)
+
+or by installing [Azure Developer CLI (azd)](https://aka.ms/azure-dev/install) and executing the following lines in terminal
+
+```
+azd auth login
+azd init -t azure/gpt-rag
+azd up
 ```
 
-5) Run `azd up`.
+\* Important: when selecting the target location check [here](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models) the regions that currently support the Azure OpenAI models you want to use.
+
+**2) Ingestion Component**
+
+Use [Data ingestion](https://github.com/Azure/gpt-rag-ingestion) repo template to create your data ingestion git repo and execute the steps in its **Deploy** section.
+
+**3) Orchestrator Component**
+
+Use [Orchestrator](https://github.com/Azure/gpt-rag-orchestrator) repo template to create your orchestrator git repo and execute the steps in its **Deploy** section.
+
+**4) Front-end Component**
+
+Use [App Front-end](https://github.com/Azure/gpt-rag-frontend) repo template to create your own frontend git repo and execute the steps in its **Deploy** section.
+
+<!-- ## Main components
+
+1) [Data ingestion](https://github.com/Azure/gpt-rag-ingestion)
+
+2) [Orchestrator](https://github.com/Azure/gpt-rag-orchestrator)
+
+3) [App Front-End](https://github.com/Azure/gpt-rag-frontend) -->
 
-* For the target location, the regions that currently support the models used in this sample are **East US** or **South Central US**. For an up-to-date list of regions and models, check [here](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/models)
 
 ## References
 

infra/core/ai/cognitiveservices.bicep

@@ -39,3 +39,5 @@ resource deployment 'Microsoft.CognitiveServices/accounts/deployments@2023-05-01
 output endpoint string = account.properties.endpoint
 output id string = account.id
 output name string = account.name
+// output apiKey string = listkeys(account.id, '2023-05-01').key1
+output apiKey string = account.listKeys().key1

infra/core/db/cosmos.bicep

@@ -0,0 +1,123 @@
+@description('Cosmos DB account name, max length 44 characters, lowercase')
+param accountName string
+
+@description('Location for the Cosmos DB account.')
+param location string = resourceGroup().location
+
+param tags object = {}
+
+@description('The default consistency level of the Cosmos DB account.')
+@allowed([
+  'Eventual'
+  'ConsistentPrefix'
+  'Session'
+  'BoundedStaleness'
+  'Strong'
+])
+param defaultConsistencyLevel string = 'Session'
+
+@description('Max stale requests. Required for BoundedStaleness. Valid ranges, Single Region: 10 to 2147483647. Multi Region: 100000 to 2147483647.')
+@minValue(10)
+@maxValue(2147483647)
+param maxStalenessPrefix int = 100000
+
+@description('Max lag time (minutes). Required for BoundedStaleness. Valid ranges, Single Region: 5 to 84600. Multi Region: 300 to 86400.')
+@minValue(5)
+@maxValue(86400)
+param maxIntervalInSeconds int = 300
+
+@description('Enable system managed failover for regions')
+param systemManagedFailover bool = true
+
+@description('The name for the database')
+param databaseName string
+
+@description('The name for the container')
+param containerName string
+
+@description('Maximum autoscale throughput for the container')
+@minValue(1000)
+@maxValue(1000000)
+param autoscaleMaxThroughput int = 1000
+
+var consistencyPolicy = {
+  Eventual: {
+    defaultConsistencyLevel: 'Eventual'
+  }
+  ConsistentPrefix: {
+    defaultConsistencyLevel: 'ConsistentPrefix'
+  }
+  Session: {
+    defaultConsistencyLevel: 'Session'
+  }
+  BoundedStaleness: {
+    defaultConsistencyLevel: 'BoundedStaleness'
+    maxStalenessPrefix: maxStalenessPrefix
+    maxIntervalInSeconds: maxIntervalInSeconds
+  }
+  Strong: {
+    defaultConsistencyLevel: 'Strong'
+  }
+}
+var locations = [
+  {
+    locationName: location
+    failoverPriority: 0
+    isZoneRedundant: false
+  }
+]
+
+resource account 'Microsoft.DocumentDB/databaseAccounts@2022-05-15' = {
+  name: toLower(accountName)
+  kind: 'GlobalDocumentDB'
+  location: location
+  tags: tags
+  properties: {
+    consistencyPolicy: consistencyPolicy[defaultConsistencyLevel]
+    locations: locations
+    databaseAccountOfferType: 'Standard'
+    enableAutomaticFailover: systemManagedFailover
+  }
+}
+
+resource database 'Microsoft.DocumentDB/databaseAccounts/sqlDatabases@2022-05-15' = {
+  parent: account
+  name: databaseName
+  properties: {
+    resource: {
+      id: databaseName
+    }
+  }
+}
+
+resource container 'Microsoft.DocumentDB/databaseAccounts/sqlDatabases/containers@2022-05-15' = {
+  parent: database
+  name: containerName
+  properties: {
+    resource: {
+      id: containerName
+      partitionKey: {
+        paths: [
+          '/id'
+        ]
+        kind: 'Hash'
+      }
+      indexingPolicy: {
+        indexingMode: 'consistent'
+        includedPaths: [
+          {
+            path: '/*'
+          }
+        ]
+      }
+      defaultTtl: 86400
+    }
+    options: {
+      autoscaleSettings: {
+        maxThroughput: autoscaleMaxThroughput
+      }
+    }
+  }
+}
+
+output azureDBkey string = account.listKeys().primaryMasterKey

infra/core/delay.bicep

@@ -0,0 +1,24 @@
+param location string = resourceGroup().location
+param utcValue string = utcNow()
+param sleepName string = 'sleep-1'
+param sleepSeconds int = 120
+resource sleepDelay 'Microsoft.Resources/deploymentScripts@2020-10-01' = {
+  name: sleepName
+  location: location
+  kind: 'AzurePowerShell'  
+  properties: {
+    forceUpdateTag: utcValue
+    azPowerShellVersion: '8.3'
+    timeout: 'PT10M'    
+    arguments: '-seconds ${sleepSeconds}'    
+    scriptContent: '''
+    param ( [string] $seconds )    
+    Write-Output Sleeping for: $seconds ....
+    Start-Sleep -Seconds $seconds   
+    Write-Output Sleep over - resuming ....
+    '''
+    cleanupPreference: 'OnSuccess'
+    retentionInterval: 'P1D'
+  }
+}
+output location string = sleepDelay.location

infra/core/host/appinsights.bicep

@@ -0,0 +1,14 @@
+param applicationInsightsName string
+param appInsightsLocation string
+
+resource applicationInsights 'Microsoft.Insights/components@2020-02-02' = {
+  name: applicationInsightsName
+  location: appInsightsLocation
+  kind: 'web'
+  properties: {
+    Application_Type: 'web'
+    Request_Source: 'rest'
+  }
+}
+
+output instrumentationKey string = applicationInsights.properties.InstrumentationKey