Apply PRs #81, #85, and #91 to cosmos-native branch

.devcontainer/devcontainer.json

@@ -21,13 +21,9 @@
                 "ms-azuretools.vscode-bicep",
                 "ms-azuretools.vscode-docker",
                 "ms-vscode.js-debug"            ]
-        },
-		"settings": {
-			"remote.autoForwardPorts": true,
-			"dotnet.defaultSolution": "cosmos-copilot.sln"
-		}
+        }
     },
-	"postStartCommand": "dotnet dev-certs https --trust"
+
 	// Use 'forwardPorts' to make a list of ports inside the container available locally.
 	// "forwardPorts": [5000, 5001],
 	// "portsAttributes": {
@@ -39,6 +35,9 @@
 	// Use 'postCreateCommand' to run commands after the container is created.
 	// "postCreateCommand": "dotnet restore",
 
+	// Configure tool-specific properties.
+	// "customizations": {},
+
 	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
 	// "remoteUser": "root"
 }

.gitignore

@@ -399,10 +399,3 @@ FodyWeavers.xsd
 # JetBrains Rider
 *.sln.iml
 
-appsettings.Development.json
-src/cosmos-copilot.WebApp/Properties/ServiceDependencies/local/*
-serviceDependencies.local.json
-
-# Bicep compiled files
-infra/**/*.json
-!infra/**/main.parameters.json

README.md

@@ -1,29 +1,28 @@
 ---
 page_type: sample
 languages:
-  - azdeveloper
-  - bicep
-  - aspx-csharp
-  - csharp
-  - dockerfile
-  - nosql
+- azdeveloper
+- bicep
+- aspx-csharp
+- csharp
+- dockerfile
+- nosql
 products:
-  - azure
-  - azure-cosmos-db
-  - azure-app-service
-  - azure-openai
+- azure
+- azure-cosmos-db
+- azure-app-service
+- azure-openai
 urlFragment: ai-samples
 name: Build Copilot app using Azure Cosmos DB for NoSQL
-description: Build a Copilot app using Azure Cosmos DB for NoSQL, Azure OpenAI Service, Semantic Kernel, and .NET Aspire
+description: Build a Copilot app using Azure Cosmos DB for NoSQL, Azure OpenAI Service, Azure App Service and Semantic Kernel
 ---
 
-# Build a Copilot app using Azure Cosmos DB for NoSQL, Azure OpenAI Service, with Semantic Kernel
+# Build a Copilot app using Azure Cosmos DB for NoSQL, Azure OpenAI Service, Azure App Service and Semantic Kernel
 
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/AzureCosmosDB/cosmosdb-nosql-copilot)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)]([placeholder](https://codespaces.new/AzureCosmosDB/cosmosdb-nosql-copilot))
 [![Open in Dev Containers](https://img.shields.io/static/v1?style=for-the-badge&label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/AzureCosmosDB/cosmosdb-nosql-copilot)
-[![Unit Tests](https://github.com/AzureCosmosDB/cosmosdb-nosql-copilot/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/AzureCosmosDB/cosmosdb-nosql-copilot/actions/workflows/unit-tests.yml)
 
-This sample application shows how to build a multi-tenant, multi-user, Generative-AI RAG Pattern application using Azure Cosmos DB for NoSQL with its new vector database capabilities, including full-text and hybrid search with Azure OpenAI Service using Semantic Kernel. The sample provides practical guidance on many concepts you will need to design and build these types of applications. Note that some features are implemented using Cosmos DB native SDK until Semantic Kernel can support them.
+This sample application shows how to build a multi-tenant, multi-user, Generative-AI RAG Pattern application using Azure Cosmos DB for NoSQL with its new vector database capabilities with Azure OpenAI Service on Azure App Service. This sample shows both using Native SDKs as well as Semantic Kernel integration. The sample provides practical guidance on many concepts you will need to design and build these types of applications.
 
 ## Important Security Notice
 
@@ -33,63 +32,53 @@ This template, the application code and configuration it contains, has been buil
 
 This application demonstrates the following concepts and how to implement them:
 
-- How to build a highly scalable, multi-tenant & user, RAG Pattern application.
-- Generating embeddings and completions.
+- How to build a highly scalable, multi-tenant & user, Generative-AI chat application using Azure Cosmos DB for NoSQL.
+- Generating completions and embeddings using Azure OpenAI Service.
 - Managing a context window (chat history) for natural conversational interactions with an LLM.
-- Manage per-request token consumption for Azure OpenAI Service requests.
-- Building a semantic cache for improved performance and cost.
-- Implementing full-text and hybrid search using Azure Cosmos DB for NoSQL.
+- Manage per-request token consumption and payload sizes for Azure OpenAI Service requests.
+- Building a semantic cache using Azure Cosmos DB for NoSQL vector search for improved performance and cost.
+- Using the Semantic Kernel SDK for completion and embeddings generation.
+- Implementing RAG Pattern using vector search in Azure Cosmos DB for NoSQL on custom data to augment generated responses from an LLM. 
 
 ### Architecture Diagram
 
 ![Architecture Diagram](./media/cosmos-nosql-copilot-diagram.png)
 
 ### User Experience
-
 ![Cosmos Copilot app user interface](./media/screenshot.png)
 
+
 ## Getting Started
 
 ### Prerequisites
 
 - Azure subscription.
 - Subscription access to Azure OpenAI service. Start here to [Request Access to Azure OpenAI Service](https://aka.ms/oaiapply). If you have access, see below for ensuring enough quota to deploy.
+- Enroll in the [Azure Cosmos DB for NoSQL Vector Search Preview](https://learn.microsoft.com/azure/cosmos-db/nosql/vector-search#enroll-in-the-vector-search-preview-feature) (See below for more details)
 - .NET 8 or above. [Download](https://dotnet.microsoft.com/download/dotnet/8.0)
 - [Azure Developer CLI](https://aka.ms/azd-install)
 - Visual Studio, VS Code, GitHub Codespaces or another editor to edit or view the source for this sample.
 
-#### Deploying Azure OpenAI supported regions
-
-The models used for this sample are **gpt-4o** and **text-3-large**. These models are not deployed in all regions and are not always present in the same region. The regions shown in the main.bicep are the known regions both models are supported in at the time this readme was last updated. To check if these models are available in additional regions, see [Azure OpenAI Service Models](https://learn.microsoft.com/azure/ai-services/openai/concepts/models)
-
-#### Checking Azure OpenAI quota limits
-
-For this sample to deploy successfully, there needs to be enough Azure OpenAI quota for the models used by this sample within your subscription. This sample deploys a new Azure OpenAI account with two models, **gpt-4o with 10K tokens** per minute and **text-3-large with 5k tokens** per minute. For more information on how to check your model quota and change it, see [Manage Azure OpenAI Service Quota](https://learn.microsoft.com/azure/ai-services/openai/how-to/quota)
 
-#### Azure Subscription Permission Requirements
+    #### Vector search Preview details
+    This lab utilizes a preview feature, **Vector search for Azure Cosmos DB for NoSQL** which requires preview feature registration. Follow the below steps to register. You must be enrolled before you can deploy this solution:
+
+    1. Navigate to your Azure Cosmos DB for NoSQL resource page.
+    1. Select the "Features" pane under the "Settings" menu item.
+    1. Select for “Vector Search in Azure Cosmos DB for NoSQL”.
+    1. Read the description to confirm you want to enroll in the preview.
+    1. Select "Enable" to enroll in the Vector Search preview.
 
-This solution deploys [user-assigned managed identities](https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview) and defines then applies Azure Cosmos DB RBAC permissions to this identity. At a minimum you will need the following Azure RBAC roles assigned to your identity in your Azure subscription or [Subscription Owner](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/privileged#owner) access which will give you both of the following.
+    #### Checking Azure OpenAI quota limits
 
-- [Manged Identity Contributor](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/identity#managed-identity-contributor)
-- [DocumentDB Account Contributor](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/databases#documentdb-account-contributor)
+    For this sample to deploy successfully, there needs to be enough Azure OpenAI quota for the models used by this sample within your subscription. This sample deploys a new Azure OpenAI account with two models, **gpt-4o with 10K tokens** per minute and **text-3-large with 5k tokens** per minute. For more information on how to check your model quota and change it, see [Manage Azure OpenAI Service Quota](https://learn.microsoft.com/azure/ai-services/openai/how-to/quota)
 
-#### Full-Text & Hyrbrid Search Feature
+    #### Azure Subscription Permission Requirements
 
-Full-text and hybrid search in Azure Cosmos DB is in Preview and only available to a subset of regions at this time. This feature is commented out in the GetChatCompletionAsync() function in the ChatService. To use this feature you must deploy this sample in either `northcentralus` or `uksouth`.
+    This solution deploys [user-assigned managed identities](https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview) and defines then applies Azure Cosmos DB RBAC permissions to this identity. At a minimum you will need the following Azure RBAC roles assigned to your identity in your Azure subscription or [Subscription Owner](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/privileged#owner) access which will give you both of the following.
 
-To utilize this feature during preview, update **main.bicep** in the section below and enter either of the two regions listed above as the value for `location`
-
-```bicep
-module database 'app/database.bicep' = {
-  name: 'database'
-  scope: resourceGroup
-  params: {
-    accountName: !empty(cosmosDbAccountName) ? cosmosDbAccountName : '${abbreviations.cosmosDbAccount}-${resourceToken}'
-    location: 'northcentralus'
-    tags: tags
-  }
-}
-```
+    - [Manged Identity Contributor](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/identity#managed-identity-contributor)
+    - [DocumentDB Account Contributor](https://learn.microsoft.com/azure/role-based-access-control/built-in-roles/databases#documentdb-account-contributor)
 
 ### GitHub Codespaces
 
@@ -143,25 +132,23 @@ A related option is VS Code Dev Containers, which will open the project in your
 
 1. Run the following command to download the solution locally to your machine:
 
-   ```bash
-   azd init -t AzureCosmosDB/cosmosdb-nosql-copilot
-   ```
+    ```bash
+    azd init -t AzureCosmosDB/cosmosdb-nosql-copilot
+    ```
 
 1. From the terminal, navigate to the /infra directory in this solution.
 
 1. Log in to AZD.
-
-   ```bash
-   azd auth login
-   ```
+    
+    ```bash
+    azd auth login
+    ```
 
 1. Provision the Azure services, build your local solution container, and deploy the application.
-
-   ```bash
-   azd up
-   ```
-
-1. Follow the prompts for the subscription and select a region to deploy. **NOTE:** If intending to use the Full-Text or Hybrid search feature please see [Full-Text & Hyrbrid Search Feature](#full-text--hyrbrid-search-feature)
+
+    ```bash
+    azd up
+    ```
 
 ### Setting up local debugging
 
@@ -174,35 +161,35 @@ To modify values for the Quickstarts, locate the value of `UserSecretsId` in the
   <UserSecretsId>your-guid-here</UserSecretsId>
 </PropertyGroup>
 ```
-
 Locate the secrets.json file and open with a text editor.
 
 - Windows: `C:\Users\<YourUserName>\AppData\Roaming\Microsoft\UserSecrets\<UserSecretsId>\secrets.json`
 - macOS/Linux: `~/.microsoft/usersecrets/<UserSecretsId>/secrets.json`
 
+
 ### Quickstart
 
 Follow the Quickstarts in this solution to go through the concepts for building RAG Pattern apps and the features in this sample and how to implement them yourself.
 
 Please see [Quickstarts](quickstart.md)
 
+
 ## Clean up
 
 1. Open a terminal and navigate to the /infra directory in this solution.
 
-1. Type azd down (--force and --purge ensure the Azure OpenAI models are deleted)
-
-   ```bash
-   azd down --force --purge
-   ```
+1. Type azd down
+    
+    ```bash
+    azd down
+    ```
 
 ## Guidance
 
 ### Region Availability
 
-This template uses gpt-4o and text-embedding-3-large models which may not be available in all Azure regions. Check for [up-to-date region availability](https://learn.microsoft.com/azure/ai-services/openai/concepts/models) and select a region during deployment accordingly.
-  * We recommend using 'canadaeast', 'eastus', 'eastus2', 'francecentral', 'japaneast', 'norwayeast', 'polandcentral', 'southindia'
-  'swedencentral', 'switzerlandnorth', or 'westus3'
+This template uses gpt-4o and text-embedding-3-large models which may not be available in all Azure regions. Check for [up-to-date region availability](https://learn.microsoft.com/azure/ai-services/openai/concepts/models#standard-deployment-model-availability) and select a region during deployment accordingly
+  * We recommend using `eastus2', 'eastus', 'japaneast', 'uksouth', 'northeurope', or 'westus3'
 
 ### Costs
 
@@ -220,7 +207,7 @@ Average Monthly Cost:
 
 To learn more about the services and features demonstrated in this sample, see the following:
 
-- [Azure Cosmos DB for NoSQL Vector Search announcement](https://aka.ms/VectorSearchGaFtsPreview)
+- [Azure Cosmos DB for NoSQL Vector Search announcement](https://aka.ms/CosmosDBDiskANNBlog/)
 - [Azure OpenAI Service documentation](https://learn.microsoft.com/azure/cognitive-services/openai/)
 - [Semantic Kernel](https://learn.microsoft.com/semantic-kernel/overview)
 - [Azure App Service documentation](https://learn.microsoft.com/azure/app-service/)

azure.yaml

@@ -5,7 +5,7 @@ metadata:
   template: cosmos-copilot
 services:
   web:
-    project: ./src/cosmos-copilot.WebApp/cosmos-copilot.WebApp.csproj
+    project: ./src
     language: csharp
     host: appservice
 hooks:
@@ -27,19 +27,17 @@ hooks:
             'OpenAi:Endpoint' = $env:AZURE_OPENAI_ACCOUNT_ENDPOINT
             'OpenAi:CompletionDeploymentName' = $env:AZURE_OPENAI_COMPLETION_DEPLOYMENT_NAME
             'OpenAi:EmbeddingDeploymentName' = $env:AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME
-            'OpenAi:MaxRagTokens' = $env:AZURE_OPENAI_MAX_RAG_TOKENS
-            'OpenAi:MaxContextTokens' = $env:AZURE_OPENAI_MAX_CONTEXT_TOKENS
             'CosmosDb:Endpoint' = $env:AZURE_COSMOS_DB_ENDPOINT
             'CosmosDb:Database' = $env:AZURE_COSMOS_DB_DATABASE_NAME
             'CosmosDb:ChatContainer' = $env:AZURE_COSMOS_DB_CHAT_CONTAINER_NAME
             'CosmosDb:CacheContainer' = $env:AZURE_COSMOS_DB_CACHE_CONTAINER_NAME
             'CosmosDb:ProductContainer' = $env:AZURE_COSMOS_DB_PRODUCT_CONTAINER_NAME
-            'CosmosDb:ProductDataSourceURI' = $env:AZURE_COSMOS_DB_PRODUCT_DATA_SOURCE_URI
-            'Chat:MaxContextWindow' = $env:AZURE_CHAT_MAX_CONTEXT_WINDOW
+            'CosmosDb:ProductDataSourceURI' = $env:AZURE_COSMOS_DB_PRODUCT_DATA_SOURCE
+            'Chat:MaxConversationTokens' = $env:AZURE_CHAT_MAX_CONVERSATION_TOKENS
             'Chat:CacheSimilarityScore' = $env:AZURE_CHAT_CACHE_SIMILARITY_SCORE
             'Chat:ProductMaxResults' = $env:AZURE_CHAT_PRODUCT_MAX_RESULTS
         }
-        $userSecrets | ConvertTo-Json | dotnet user-secrets set --project ./src/cosmos-copilot.WebApp/cosmos-copilot.WebApp.csproj
+        $userSecrets | ConvertTo-Json | dotnet user-secrets set --project ./src/cosmos-copilot.csproj
       shell: pwsh
       continueOnError: false
       interactive: true
@@ -49,19 +47,17 @@ hooks:
             --arg openAiEndpoint $AZURE_OPENAI_ACCOUNT_ENDPOINT \
             --arg openAiCompletionDeploymentName $AZURE_OPENAI_COMPLETION_DEPLOYMENT_NAME \
             --arg openAiEmbeddingDeploymentName $AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME \
-            --arg openAiMaxRagTokens $AZURE_OPENAI_MAX_RAG_TOKENS \
-            --arg openAiMaxContextTokens $AZURE_OPENAI_MAX_CONTEXT_TOKENS \
             --arg cosmosDbEndpoint $AZURE_COSMOS_DB_ENDPOINT \
             --arg cosmosDbDatabase $AZURE_COSMOS_DB_DATABASE_NAME \
             --arg cosmosDbChatContainer $AZURE_COSMOS_DB_CHAT_CONTAINER_NAME \
             --arg cosmosDbCacheContainer $AZURE_COSMOS_DB_CACHE_CONTAINER_NAME \
             --arg cosmosDbProductContainer $AZURE_COSMOS_DB_PRODUCT_CONTAINER_NAME \
-            --arg cosmosDbProductDataSourceURI $AZURE_COSMOS_DB_PRODUCT_DATA_SOURCE_URI \
-            --arg chatMaxContextWindow $AZURE_CHAT_MAX_CONTEXT_WINDOW \
-            --arg chatCacheSimilarityScore $AZURE_CHAT_CACHE_SIMILARITY_SCORE \
-            --arg chatProductMaxResults $AZURE_CHAT_PRODUCT_MAX_RESULTS \
-            '{"OpenAi:Endpoint":$openAiEndpoint,"OpenAi:CompletionDeploymentName":$openAiCompletionDeploymentName,"OpenAi:EmbeddingDeploymentName":$openAiEmbeddingDeploymentName,"OpenAi:MaxRagTokens":$openAiMaxRagTokens,"OpenAi:MaxContextTokens":$openAiMaxContextTokens,"CosmosDb:Endpoint":$cosmosDbEndpoint,"CosmosDb:Database":$cosmosDbDatabase,"CosmosDb:ChatContainer":$cosmosDbChatContainer,"CosmosDb:CacheContainer":$cosmosDbCacheContainer,"CosmosDb:ProductContainer":$cosmosDbProductContainer,"CosmosDb:ProductDataSourceURI":$cosmosDbProductDataSourceURI,"Chat:MaxContextWindow":$chatMaxContextWindow,"Chat:CacheSimilarityScore":$chatCacheSimilarityScore,"Chat:ProductMaxResults":$chatProductMaxResults}')
-        echo $userSecrets | dotnet user-secrets set --project ./src/cosmos-copilot.WebApp/cosmos-copilot.WebApp.csproj
+            --arg cosmosDbProductDataSourceURI $AZURE_COSMOS_DB_PRODUCT_DATA_SOURCE \
+            --arg maxConversationTokens $AZURE_CHAT_MAX_CONVERSATION_TOKENS \
+            --arg cacheSimilarityScore $AZURE_CHAT_CACHE_SIMILARITY_SCORE \
+            --arg productMaxResults $AZURE_CHAT_PRODUCT_MAX_RESULTS \
+            '{"OpenAi:Endpoint":$openAiEndpoint,"OpenAi:CompletionDeploymentName":$openAiCompletionDeploymentName,"OpenAi:EmbeddingDeploymentName":$openAiEmbeddingDeploymentName,"CosmosDb:Endpoint":$cosmosDbEndpoint,"CosmosDb:Database":$cosmosDbDatabase,"CosmosDb:ChatContainer":$cosmosDbChatContainer,"CosmosDb:CacheContainer":$cosmosDbCacheContainer,"CosmosDb:ProductContainer":$cosmosDbProductContainer,"CosmosDb:ProductDataSource":$cosmosDbProductDataSourceURI,"Chat:MaxConversationTokens":$maxConversationTokens,"Chat:CacheSimilarityScore":$cacheSimilarityScore,"Chat:ProductMaxResults":$productMaxResults}')
+        echo $userSecrets | dotnet user-secrets set --project ./src/cosmos-copilot.csproj
       shell: sh
       continueOnError: false
       interactive: true