Add streaming support and improve JSON serialization

- Updated `Response` record class to allow nullable `Question` and `Answer` properties; moved `StreamState` enum to a new file.
- Added `JsonStringEnumConverter` in `Program.cs` for better enum serialization.
- Corrected terminology in document upload endpoint description.
- Introduced `/api/ask-streaming` endpoint for streaming question responses.
- Added `AskStreamingAsync` method in `VectorSearchService` for handling streaming logic.
- Created `StreamState.cs` to define `StreamState` enum with `Start`, `Append`, and `End` values.

SqlDatabaseVectorSearch/Models/Response.cs

@@ -1,10 +1,4 @@
 namespace SqlDatabaseVectorSearch.Models;
 
-public record class Response(string Question, string Answer, StreamState? StreamState = null);
-
-public enum StreamState
-{
-    Start,
-    Append,
-    End
-}
+// Question and Asnwer can be null when using response streaming.
+public record class Response(string? Question, string? Answer, StreamState? StreamState = null);

SqlDatabaseVectorSearch/Models/StreamState.cs

@@ -0,0 +1,8 @@
+namespace SqlDatabaseVectorSearch.Models;
+
+public enum StreamState
+{
+    Start,
+    Append,
+    End
+}

SqlDatabaseVectorSearch/Program.cs

@@ -1,4 +1,5 @@
 using System.ComponentModel;
+using System.Text.Json.Serialization;
 using Microsoft.AspNetCore.Http.HttpResults;
 using Microsoft.EntityFrameworkCore;
 using Microsoft.SemanticKernel;
@@ -49,6 +50,11 @@ builder.Services.AddSingleton<TokenizerService>();
 builder.Services.AddSingleton<ChatService>();
 builder.Services.AddScoped<VectorSearchService>();
 
+builder.Services.ConfigureHttpJsonOptions(options =>
+{
+    options.SerializerOptions.Converters.Add(new JsonStringEnumConverter());
+});
+
 builder.Services.AddOpenApi(options =>
 {
     options.RemoveServerList();
@@ -114,7 +120,7 @@ documentsApiGroup.MapPost(string.Empty, async (IFormFile file, VectorSearchServi
 .DisableAntiforgery()
 .ProducesProblem(StatusCodes.Status400BadRequest)
 .WithSummary("Uploads a document")
-.WithDescription("Uploads a document to SQL Database and saves its embedding using the new native Vector type. The document will be indexed and used to answer questions. Currently, only PDF files are supported.");
+.WithDescription("Uploads a document to SQL Database and saves its embedding using the native VECTOR type. The document will be indexed and used to answer questions. Currently, only PDF files are supported.");
 
 documentsApiGroup.MapDelete("{documentId:guid}", async (Guid documentId, VectorSearchService vectorSearchService) =>
 {
@@ -134,4 +140,25 @@ app.MapPost("/api/ask", async (Question question, VectorSearchService vectorSear
 .WithDescription("The question will be reformulated taking into account the context of the chat identified by the given ConversationId.")
 .WithTags("Ask");
 
+app.MapPost("/api/ask-streaming", (Question question, VectorSearchService vectorSearchService,
+    [Description("If true, the question will be reformulated taking into account the context of the chat identified by the given ConversationId.")] bool reformulate = true) =>
+{
+    async IAsyncEnumerable<Response> Stream()
+    {
+        // Requests a streaming response.
+        var responseStream = vectorSearchService.AskStreamingAsync(question, reformulate);
+
+        await foreach (var delta in responseStream)
+        {
+            yield return delta;
+            await Task.Delay(50);
+        }
+    }
+
+    return Stream();
+})
+.WithSummary("Asks a question and gets the response as streaming")
+.WithDescription("The question will be reformulated taking into account the context of the chat identified by the given ConversationId.")
+.WithTags("Ask");
+
 app.Run();

SqlDatabaseVectorSearch/Services/VectorSearchService.cs

@@ -88,6 +88,25 @@ public class VectorSearchService(ApplicationDbContext dbContext, ITextEmbeddingG
         return new Response(reformulatedQuestion, answer);
     }
 
+    public async IAsyncEnumerable<Response> AskStreamingAsync(Question question, bool reformulate = true)
+    {
+        var (reformulatedQuestion, chunks) = await CreateContextAsync(question, reformulate);
+
+        var answerStream = chatService.AskStreamingAsync(question.ConversationId, chunks, reformulatedQuestion);
+
+        // The first message contains the original question.
+        yield return new Response(reformulatedQuestion, null, StreamState.Start);
+
+        // Return each token as a partial response.
+        await foreach (var token in answerStream)
+        {
+            yield return new Response(null, token, StreamState.Append);
+        }
+
+        // The last message tells the client that the stream has ended.
+        yield return new Response(null, null, StreamState.End);
+    }
+
     private async Task<(string Question, IEnumerable<string> Chunks)> CreateContextAsync(Question question, bool reformulate = true)
     {
         // Reformulate the following question taking into account the context of the chat to perform keyword search and embeddings: