👁 Image
EasyAppDev.Blazor.AutoComplete.AI.AzureSearch 1.0.7

EasyAppDev.Blazor.AutoComplete.AI.AzureSearch

Azure AI Search integration for semantic search with the Blazor AutoComplete component.

👁 NuGet
👁 License: MIT

Features

• Hybrid Search: Combines vector + keyword search
• Semantic Ranking: AI-powered result re-ranking
• Managed Service: No infrastructure to maintain
• Enterprise Ready: Built-in security, scaling, and SLA

Installation

dotnet add package EasyAppDev.Blazor.AutoComplete.AI.AzureSearch

Quick Start

1. Configure Services

// Program.cs
builder.Services.AddAutoCompleteAzureSearch<Product>(
 endpoint: "https://mysearch.search.windows.net",
 apiKey: "your-admin-key",
 indexName: "products",
 options => {
 options.EnableSemanticRanking = true;
 options.SemanticConfigurationName = "my-semantic-config";
 },
 textSelector: p => $"{p.Name} {p.Description}",
 idSelector: p => p.Id.ToString());

// Register embedding generator
builder.Services.AddAutoCompleteVectorSearch<Product>(
 openAiApiKey: "sk-...");

2. Use the Component

@using EasyAppDev.Blazor.AutoComplete.AI

<VectorAutoComplete TItem="Product"
 TextField="@(p => p.Name)"
 @bind-Value="@selectedProduct"
 Placeholder="Semantic search..." />

Configuration Options

Hybrid Search

Azure AI Search combines vector similarity with traditional keyword matching:

options.EnableHybridSearch = true;
options.HybridSearchWeight = 0.5f; // 50% vector, 50% keyword

Creating an Index

Use Azure Portal or SDK to create an index with a vector field:

{
 "name": "products",
 "fields": [
 { "name": "id", "type": "Edm.String", "key": true },
 { "name": "name", "type": "Edm.String", "searchable": true },
 { "name": "embedding", "type": "Collection(Edm.Single)", "dimensions": 1536, "vectorSearchProfile": "default" }
 ]
}

License

MIT