Mirrors/SqlDatabaseVectorSearch
1
0
Fork 0
mirror of https://github.com/marcominerva/SqlDatabaseVectorSearch.git synced 2026-06-20 12:23:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Azure OpenAI services and Semantic Kernel version

Browse Source 
- Updated `VectorSearchService.cs` to replace the text embedding generation service with an embedding generator and adjusted embedding generation and vector search logic.
- Changed `Microsoft.SemanticKernel` package version from 1.50.0 to 1.51.0 in `SqlDatabaseVectorSearch.csproj` and modified `NoWarn` property settings.
This commit is contained in:
Marco Minerva
2025-05-16 17:42:38 +02:00
parent 2a511a8836
commit 2d979fd8f0
3 changed files with 21 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SqlDatabaseVectorSearch/Program.cs
+2 -2
View File
@@ -60,8 +60,8 @@ builder.Services.ConfigureHttpClientDefaults(configure =>
// Semantic Kernel is used to generate embeddings and to reformulate questions taking into account all the previous interactions,
// so that embeddings themselves can be generated more accurately.
builder.Services.AddKernel()
.AddAzureOpenAITextEmbeddingGeneration(aiSettings.Embedding.Deployment, aiSettings.Embedding.Endpoint, aiSettings.Embedding.ApiKey, dimensions: aiSettings.Embedding.Dimensions)
.AddAzureOpenAIChatCompletion(aiSettings.ChatCompletion.Deployment, aiSettings.ChatCompletion.Endpoint, aiSettings.ChatCompletion.ApiKey);
.AddAzureOpenAIEmbeddingGenerator(aiSettings.Embedding.Deployment, aiSettings.Embedding.Endpoint, aiSettings.Embedding.ApiKey, modelId: aiSettings.Embedding.ModelId, dimensions: aiSettings.Embedding.Dimensions)
.AddAzureOpenAIChatCompletion(aiSettings.ChatCompletion.Deployment, aiSettings.ChatCompletion.Endpoint, aiSettings.ChatCompletion.ApiKey, modelId: aiSettings.ChatCompletion.ModelId);
builder.Services.AddSingleton<TokenizerService>();
builder.Services.AddSingleton<ChatService>();
SqlDatabaseVectorSearch/Services/VectorSearchService.cs
+9 -7
View File
@@ -1,18 +1,19 @@
using System.Data;
using System.Runtime.CompilerServices;
using Microsoft.EntityFrameworkCore;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.Options;
using Microsoft.SemanticKernel.Embeddings;
using SqlDatabaseVectorSearch.ContentDecoders;
using SqlDatabaseVectorSearch.DataAccessLayer;
using SqlDatabaseVectorSearch.Models;
using SqlDatabaseVectorSearch.Settings;
using SqlDatabaseVectorSearch.TextChunkers;
using ChatResponse = SqlDatabaseVectorSearch.Models.ChatResponse;
using Entities = SqlDatabaseVectorSearch.DataAccessLayer.Entities;
namespace SqlDatabaseVectorSearch.Services;
public class VectorSearchService(IServiceProvider serviceProvider, ApplicationDbContext dbContext, DocumentService documentService, ITextEmbeddingGenerationService textEmbeddingGenerationService, TokenizerService tokenizerService, ChatService chatService, TimeProvider timeProvider, IOptions<AppSettings> appSettingsOptions, ILogger<VectorSearchService> logger)
public class VectorSearchService(IServiceProvider serviceProvider, ApplicationDbContext dbContext, DocumentService documentService, IEmbeddingGenerator<string, Embedding<float>> embeddingGenerator, TokenizerService tokenizerService, ChatService chatService, TimeProvider timeProvider, IOptions<AppSettings> appSettingsOptions, ILogger<VectorSearchService> logger)
{
private readonly AppSettings appSettings = appSettingsOptions.Value;
@@ -42,14 +43,15 @@ public class VectorSearchService(IServiceProvider serviceProvider, ApplicationDb
// Split the content into chunks and generate the embeddings for each one.
var textChunker = serviceProvider.GetRequiredKeyedService<ITextChunker>(contentType);
var paragraphs = textChunker.Split(content);
var embeddings = await textEmbeddingGenerationService.GenerateEmbeddingsAsync(paragraphs, cancellationToken: cancellationToken);
var embeddings = await embeddingGenerator.GenerateAndZipAsync(paragraphs, cancellationToken: cancellationToken);
// Save the document chunks and the corresponding embedding in the database.
foreach (var (index, paragraph) in paragraphs.Index())
foreach (var (index, embedding) in embeddings.Index())
{
logger.LogDebug("Storing a paragraph of {TokenCount} tokens.", tokenizerService.CountChatCompletionTokens(paragraph));
logger.LogDebug("Storing a paragraph of {TokenCount} tokens.", tokenizerService.CountChatCompletionTokens(embedding.Value));
var documentChunk = new Entities.DocumentChunk { Document = document, Index = index, Content = paragraph!, Embedding = embeddings[index].ToArray() };
var documentChunk = new Entities.DocumentChunk { Document = document, Index = index, Content = embedding.Value, Embedding = embedding.Embedding.Vector.ToArray() };
dbContext.DocumentChunks.Add(documentChunk);
}
@@ -108,7 +110,7 @@ public class VectorSearchService(IServiceProvider serviceProvider, ApplicationDb
logger.LogDebug("Embedding Token Count: {EmbeddingTokenCount}", embeddingTokenCount);
// Perform Vector Search on SQL Database.
var questionEmbedding = await textEmbeddingGenerationService.GenerateEmbeddingAsync(reformulatedQuestion.Text!, cancellationToken: cancellationToken);
var questionEmbedding = await embeddingGenerator.GenerateVectorAsync(reformulatedQuestion.Text!, cancellationToken: cancellationToken);
var chunks = await dbContext.DocumentChunks
.OrderBy(c => EF.Functions.VectorDistance("cosine", c.Embedding, questionEmbedding.ToArray()))
SqlDatabaseVectorSearch/SqlDatabaseVectorSearch.csproj
+10 -10
View File
@@ -1,13 +1,13 @@
<Project Sdk="Microsoft.NET.Sdk.Web">
<PropertyGroup>
<TargetFramework>net9.0</TargetFramework>
<ImplicitUsings>enable</ImplicitUsings>
<PropertyGroup>
<TargetFramework>net9.0</TargetFramework>
<ImplicitUsings>enable</ImplicitUsings>
<Nullable>enable</Nullable>
<NoWarn>$(NoWarn);SKEXP0001;SKEXP0010;SKEXP0050;EXTEXP0018</NoWarn>
</PropertyGroup>
<NoWarn>$(NoWarn);SKEXP0010;SKEXP0050</NoWarn>
</PropertyGroup>
<ItemGroup>
<ItemGroup>
<PackageReference Include="Blazor.Bootstrap" Version="3.3.1" />
<PackageReference Include="DocumentFormat.OpenXml" Version="3.3.0" />
<PackageReference Include="EFCore.SqlServer.VectorSearch" Version="9.0.0-preview.2" />
@@ -16,21 +16,21 @@
<PackageReference Include="Microsoft.AspNetCore.OpenApi" Version="9.0.5" />
<PackageReference Include="Microsoft.EntityFrameworkCore.SqlServer" Version="9.0.5" />
<PackageReference Include="Microsoft.EntityFrameworkCore.Tools" Version="9.0.5">
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
<PrivateAssets>all</PrivateAssets>
<IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets>
</PackageReference>
<PackageReference Include="Microsoft.Extensions.Caching.Hybrid" Version="9.5.0" />
<PackageReference Include="Microsoft.Extensions.Http.Resilience" Version="9.5.0" />
<PackageReference Include="Microsoft.ML.Tokenizers" Version="1.0.2" />
<PackageReference Include="Microsoft.ML.Tokenizers.Data.Cl100kBase" Version="1.0.2" />
<PackageReference Include="Microsoft.ML.Tokenizers.Data.O200kBase" Version="1.0.2" />
<PackageReference Include="Microsoft.SemanticKernel" Version="1.50.0" />
<PackageReference Include="Microsoft.SemanticKernel" Version="1.51.0" />
<PackageReference Include="MimeMapping" Version="3.1.0" />
<PackageReference Include="MinimalHelpers.FluentValidation" Version="1.1.3" />
<PackageReference Include="MinimalHelpers.Routing.Analyzers" Version="1.1.3" />
<PackageReference Include="PdfPig" Version="0.1.10" />
<PackageReference Include="Swashbuckle.AspNetCore.SwaggerUI" Version="8.1.1" />
<PackageReference Include="TinyHelpers.AspNetCore" Version="4.0.26" />
</ItemGroup>
</ItemGroup>
</Project>