New vector search quickstart (#43894)

* New vector search quickstart --------- Co-authored-by: Genevieve Warren <[email protected]>
dotnet · Dec 18, 2024 · ddd0d3c · ddd0d3c
1 parent 02b71ef
commit ddd0d3c
Show file tree

Hide file tree

Showing 10 changed files with 375 additions and 142 deletions.
diff --git a/docs/ai/quickstarts/includes/prerequisites-azure-openai.md b/docs/ai/quickstarts/includes/prerequisites-azure-openai.md
@@ -7,7 +7,7 @@ ms.topic: include
 
 ## Prerequisites
 
-- .NET 8 SDK - [Install the .NET 8 SDK](https://dotnet.microsoft.com/download/dotnet/8.0).
+- .NET 8.0 SDK or higher - [Install the .NET 8 SDK](https://dotnet.microsoft.com/download/dotnet/8.0).
 - An Azure subscription - [Create one for free](https://azure.microsoft.com/free).
 - Access to [Azure OpenAI service](/azure/ai-services/openai/overview#how-do-i-get-access-to-azure-openai).
 - Azure Developer CLI (Optional) - [Install or update the Azure Developer CLI](/azure/developer/azure-developer-cli/install-azd).
diff --git a/docs/ai/quickstarts/includes/prerequisites-openai.md b/docs/ai/quickstarts/includes/prerequisites-openai.md
@@ -7,6 +7,5 @@ ms.topic: include
 
 ## Prerequisites
 
-- .NET 8.0 SDK - [Install the .NET 8.0 SDK](https://dotnet.microsoft.com/download/dotnet/8.0).
+- .NET 8.0 SDK or higher - [Install the .NET 8.0 SDK](https://dotnet.microsoft.com/download/dotnet/8.0).
 - An [API key from OpenAI](https://platform.openai.com/docs/quickstart/account-setup) so you can run this sample.
-- On Windows, PowerShell `v7+` is required. To validate your version, run `pwsh` in a terminal. It should return the current version. If it returns an error, execute the following command: `dotnet tool update --global PowerShell`.
diff --git a/docs/ai/quickstarts/quickstart-ai-chat-with-data.md b/docs/ai/quickstarts/quickstart-ai-chat-with-data.md
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/CloudService.cs b/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/CloudService.cs
@@ -0,0 +1,24 @@
+using Microsoft.Extensions.VectorData;
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Text;
+using System.Threading.Tasks;
+
+namespace VectorDataAI
+{
+    internal class CloudService
+    {
+        [VectorStoreRecordKey]
+        public int Key { get; set; }
+
+        [VectorStoreRecordData]
+        public string Name { get; set; }
+
+        [VectorStoreRecordData]
+        public string Description { get; set; }
+
+        [VectorStoreRecordVector(384, DistanceFunction.CosineSimilarity)]
+        public ReadOnlyMemory<float> Vector { get; set; }
+    }
+}
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/Program.cs b/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/Program.cs
@@ -0,0 +1,88 @@
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Extensions.AI;
+using Microsoft.Extensions.VectorData;
+using Microsoft.Extensions.Configuration;
+using Microsoft.SemanticKernel.Connectors.InMemory;
+using VectorDataAI;
+
+var cloudServices = new List<CloudService>()
+{
+    new CloudService
+        {
+            Key=0,
+            Name="Azure App Service",
+            Description="Host .NET, Java, Node.js, and Python web applications and APIs in a fully managed Azure service. You only need to deploy your code to Azure. Azure takes care of all the infrastructure management like high availability, load balancing, and autoscaling."
+        },
+    new CloudService
+        {
+            Key=1,
+            Name="Azure Service Bus",
+            Description="A fully managed enterprise message broker supporting both point to point and publish-subscribe integrations. It's ideal for building decoupled applications, queue-based load leveling, or facilitating communication between microservices."
+        },
+    new CloudService
+        {
+            Key=2,
+            Name="Azure Blob Storage",
+            Description="Azure Blob Storage allows your applications to store and retrieve files in the cloud. Azure Storage is highly scalable to store massive amounts of data and data is stored redundantly to ensure high availability."
+        },
+    new CloudService
+        {
+            Key=3,
+            Name="Microsoft Entra ID",
+            Description="Manage user identities and control access to your apps, data, and resources.."
+        },
+    new CloudService
+        {
+            Key=4,
+            Name="Azure Key Vault",
+            Description="Store and access application secrets like connection strings and API keys in an encrypted vault with restricted access to make sure your secrets and your application aren't compromised."
+        },
+    new CloudService
+        {
+            Key=5,
+            Name="Azure AI Search",
+            Description="Information retrieval at scale for traditional and conversational search applications, with security and options for AI enrichment and vectorization."
+        }
+};
+
+// Load the configuration values
+var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
+string endpoint = config["AZURE_OPENAI_ENDPOINT"];
+string model = config["AZURE_OPENAI_GPT_NAME"];
+
+// Create the embedding generator
+IEmbeddingGenerator<string, Embedding<float>> generator =
+    new AzureOpenAIClient(
+        new Uri(endpoint),
+        new DefaultAzureCredential())
+            .AsEmbeddingGenerator(modelId: model);
+
+// Create and populate the vector store
+var vectorStore = new InMemoryVectorStore();
+var cloudServicesStore = vectorStore.GetCollection<int, CloudService>("cloudServices");
+await cloudServicesStore.CreateCollectionIfNotExistsAsync();
+
+foreach (var service in cloudServices)
+{
+    service.Vector = await generator.GenerateEmbeddingVectorAsync(service.Description);
+    await cloudServicesStore.UpsertAsync(service);
+}
+
+// Convert a search query to a vector and search the vector store
+var query = "Which Azure service should I use to store my Word documents?";
+var queryEmbedding = await generator.GenerateEmbeddingVectorAsync(query);
+
+var results = await cloudServicesStore.VectorizedSearchAsync(queryEmbedding, new VectorSearchOptions()
+{
+    Top = 1,
+    VectorPropertyName = "Vector"
+});
+
+await foreach (var result in results.Results)
+{
+    Console.WriteLine($"Name: {result.Record.Name}");
+    Console.WriteLine($"Description: {result.Record.Description}");
+    Console.WriteLine($"Vector match score: {result.Score}");
+    Console.WriteLine();
+}
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/VectorDataAI.csproj b/docs/ai/quickstarts/snippets/chat-with-data/azure-openai/VectorDataAI.csproj
@@ -0,0 +1,20 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Azure.Identity" Version="1.13.1" />
+    <PackageReference Include="Azure.AI.OpenAI" Version="2.0.0" />
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="9.0.1-preview.1.24570.5" />
+    <PackageReference Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.0.0-preview.1.24523.1" />
+    <PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" Version="1.31.0-preview" />
+    <PackageReference Include="Microsoft.Extensions.Configuration" Version="9.0.0" />
+    <PackageReference Include="Microsoft.Extensions.Configuration.UserSecrets" Version="9.0.0" />
+  </ItemGroup>
+
+</Project>
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/openai/CloudService.cs b/docs/ai/quickstarts/snippets/chat-with-data/openai/CloudService.cs
@@ -0,0 +1,24 @@
+using Microsoft.Extensions.VectorData;
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Text;
+using System.Threading.Tasks;
+
+namespace VectorDataAI
+{
+    internal class CloudService
+    {
+        [VectorStoreRecordKey]
+        public int Key { get; set; }
+
+        [VectorStoreRecordData]
+        public string Name { get; set; }
+
+        [VectorStoreRecordData]
+        public string Description { get; set; }
+
+        [VectorStoreRecordVector(384, DistanceFunction.CosineSimilarity)]
+        public ReadOnlyMemory<float> Vector { get; set; }
+    }
+}
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/openai/Program.cs b/docs/ai/quickstarts/snippets/chat-with-data/openai/Program.cs
@@ -0,0 +1,86 @@
+using Microsoft.Extensions.AI;
+using OpenAI;
+using Microsoft.Extensions.VectorData;
+using Microsoft.SemanticKernel.Connectors.InMemory;
+using VectorDataAI;
+using System.ClientModel;
+using Microsoft.Extensions.Configuration;
+
+var cloudServices = new List<CloudService>()
+{
+    new CloudService
+        {
+            Key=0,
+            Name="Azure App Service",
+            Description="Host .NET, Java, Node.js, and Python web applications and APIs in a fully managed Azure service. You only need to deploy your code to Azure. Azure takes care of all the infrastructure management like high availability, load balancing, and autoscaling."
+        },
+    new CloudService
+        {
+            Key=1,
+            Name="Azure Service Bus",
+            Description="A fully managed enterprise message broker supporting both point to point and publish-subscribe integrations. It's ideal for building decoupled applications, queue-based load leveling, or facilitating communication between microservices."
+        },
+    new CloudService
+        {
+            Key=2,
+            Name="Azure Blob Storage",
+            Description="Azure Blob Storage allows your applications to store and retrieve files in the cloud. Azure Storage is highly scalable to store massive amounts of data and data is stored redundantly to ensure high availability."
+        },
+    new CloudService
+        {
+            Key=3,
+            Name="Microsoft Entra ID",
+            Description="Manage user identities and control access to your apps, data, and resources.."
+        },
+    new CloudService
+        {
+            Key=4,
+            Name="Azure Key Vault",
+            Description="Store and access application secrets like connection strings and API keys in an encrypted vault with restricted access to make sure your secrets and your application aren't compromised."
+        },
+    new CloudService
+        {
+            Key=5,
+            Name="Azure AI Search",
+            Description="Information retrieval at scale for traditional and conversational search applications, with security and options for AI enrichment and vectorization."
+        }
+};
+
+// Load the configuration values
+var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
+string model = config["ModelName"];
+string key = config["OpenAIKey"];
+
+// Create the embedding generator
+IEmbeddingGenerator<string, Embedding<float>> generator =
+    new OpenAIClient(new ApiKeyCredential(key))
+            .AsEmbeddingGenerator(modelId: model);
+
+// Create and populate the vector store
+var vectorStore = new InMemoryVectorStore();
+var cloudServicesStore = vectorStore.GetCollection<int, CloudService>("cloudServices");
+await cloudServicesStore.CreateCollectionIfNotExistsAsync();
+
+foreach (var service in cloudServices)
+{
+    service.Vector = await generator.GenerateEmbeddingVectorAsync(service.Description);
+    await cloudServicesStore.UpsertAsync(service);
+}
+
+// Convert a search query to a vector and search the vector store
+var query = "Which Azure service should I use to store my Word documents?";
+var queryEmbedding = await generator.GenerateEmbeddingVectorAsync(query);
+
+var results = await cloudServicesStore.VectorizedSearchAsync(queryEmbedding, new VectorSearchOptions()
+{
+    Top = 1,
+    VectorPropertyName = "Vector"
+});
+
+await foreach (var result in results.Results)
+{
+    Console.WriteLine($"Name: {result.Record.Name}");
+    Console.WriteLine($"Description: {result.Record.Description}");
+    Console.WriteLine($"Vector match score: {result.Score}");
+    Console.WriteLine();
+}
diff --git a/docs/ai/quickstarts/snippets/chat-with-data/openai/VectorDataAI.csproj b/docs/ai/quickstarts/snippets/chat-with-data/openai/VectorDataAI.csproj
@@ -0,0 +1,18 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="9.0.1-preview.1.24570.5" />
+    <PackageReference Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.0.0-preview.1.24523.1" />
+    <PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" Version="1.31.0-preview" />
+    <PackageReference Include="Microsoft.Extensions.Configuration" Version="9.0.0" />
+    <PackageReference Include="Microsoft.Extensions.Configuration.UserSecrets" Version="9.0.0" />
+  </ItemGroup>
+
+</Project>
diff --git a/docs/ai/toc.yml b/docs/ai/toc.yml
@@ -19,7 +19,7 @@ items:
     href: quickstarts/quickstart-openai-summarize-text.md
   - name: Build a chat app
     href: quickstarts/get-started-openai.md
-  - name: Create an app to chat about your data
+  - name: Build a .NET AI vector search app
     href: quickstarts/quickstart-ai-chat-with-data.md
   - name: Execute a local .NET function
     href: quickstarts/quickstart-azure-openai-tool.md