Add streaming and refactor chat/question handling

Updated `Response` record in `Response.cs` to include an optional `StreamState` property, which can be `Start`, `Append`, or `End`. Added a new `StreamState` enum to `Response.cs`.

In `ChatService.cs`, added new methods `AskQuestionAsync` and `AskStreamingAsync` to handle asking questions and streaming responses, respectively. Refactored `CreateChatAsync` to return a `ChatHistory` object.

In `VectorSearchService.cs`, added a new `AskQuestionAsync` method to handle questions using `ChatService`. Updated `CreateContextAsync` to return a tuple with the reformulated question and chunks. Removed the previous implementation of `AskQuestionAsync` and replaced it with the new method utilizing `ChatService`.

SqlDatabaseVectorSearch/Models/Response.cs

@@ -1,3 +1,10 @@
 namespace SqlDatabaseVectorSearch.Models;
 
-public record class Response(string Question, string Answer);
+public record class Response(string Question, string Answer, StreamState? StreamState = null);
+
+public enum StreamState
+{
+    Start,
+    Append,
+    End
+}

SqlDatabaseVectorSearch/Services/ChatService.cs

@@ -35,6 +35,42 @@ public class ChatService(IChatCompletionService chatCompletionService, Tokenizer
     }
 
     public async Task<string> AskQuestionAsync(Guid conversationId, IEnumerable<string> chunks, string question)
+    {
+        var chat = CreateChatAsync(chunks, question);
+
+        var answer = await chatCompletionService.GetChatMessageContentAsync(chat, new AzureOpenAIPromptExecutionSettings
+        {
+            MaxTokens = appSettings.MaxOutputTokens
+        });
+
+        // Add question and answer to the chat history.
+        await SetChatHistoryAsync(conversationId, question, answer.Content!);
+
+        return answer.Content!;
+    }
+
+    public async IAsyncEnumerable<string> AskStreamingAsync(Guid conversationId, IEnumerable<string> chunks, string question)
+    {
+        var chat = CreateChatAsync(chunks, question);
+
+        var answer = new StringBuilder();
+        await foreach (var token in chatCompletionService.GetStreamingChatMessageContentsAsync(chat, new AzureOpenAIPromptExecutionSettings
+        {
+            MaxTokens = appSettings.MaxOutputTokens
+        }))
+        {
+            if (!string.IsNullOrEmpty(token.Content))
+            {
+                yield return token.Content;
+                answer.Append(token.Content);
+            }
+        }
+
+        // Add question and answer to the chat history.
+        await SetChatHistoryAsync(conversationId, question, answer.ToString());
+    }
+
+    private ChatHistory CreateChatAsync(IEnumerable<string> chunks, string question)
     {
         var chat = new ChatHistory("""
             You can use only the information provided in this chat to answer questions. If you don't know the answer, reply suggesting to refine the question.
@@ -79,16 +115,7 @@ public class ChatService(IChatCompletionService chatCompletionService, Tokenizer
         }
 
         chat.AddUserMessage(prompt.ToString());
-
+        return chat;
-        var answer = await chatCompletionService.GetChatMessageContentAsync(chat, new AzureOpenAIPromptExecutionSettings
-        {
-            MaxTokens = appSettings.MaxOutputTokens
-        });
-
-        // Add question and answer to the chat history.
-        await SetChatHistoryAsync(conversationId, question, answer.Content!);
-
-        return answer.Content!;
     }
 
     private async Task UpdateCacheAsync(Guid conversationId, ChatHistory chat)

SqlDatabaseVectorSearch/Services/VectorSearchService.cs

@@ -81,6 +81,14 @@ public class VectorSearchService(ApplicationDbContext dbContext, ITextEmbeddingG
             => dbContext.Documents.Where(d => d.Id == documentId).ExecuteDeleteAsync();
 
     public async Task<Response> AskQuestionAsync(Question question, bool reformulate = true)
+    {
+        var (reformulatedQuestion, chunks) = await CreateContextAsync(question, reformulate);
+
+        var answer = await chatService.AskQuestionAsync(question.ConversationId, chunks, reformulatedQuestion);
+        return new Response(reformulatedQuestion, answer);
+    }
+
+    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:
         var reformulatedQuestion = reformulate ? await chatService.CreateQuestionAsync(question.ConversationId, question.Text) : question.Text;
@@ -94,8 +102,7 @@ public class VectorSearchService(ApplicationDbContext dbContext, ITextEmbeddingG
                     .Take(appSettings.MaxRelevantChunks)
                     .ToListAsync();
 
-        var answer = await chatService.AskQuestionAsync(question.ConversationId, chunks, reformulatedQuestion);
+        return (reformulatedQuestion, chunks);
-        return new Response(reformulatedQuestion, answer);
     }
 
     private static Task<string> GetContentAsync(Stream stream)