Merge branch 'master' into ui

README.md

@@ -6,7 +6,7 @@ The application is a Minimal API that exposes endpoints to load documents, gener
 > [!NOTE]
 > If you prefer to use straight SQL, check out the [sql branch](https://github.com/marcominerva/SqlDatabaseVectorSearch/tree/sql).
 
-![SQL Database Vector Search](https://github.com/marcominerva/SqlDatabaseVectorSearch/blob/master/SqlDatabaseVectorSearch.png)
+![SQL Database Vector Search](https://raw.githubusercontent.com/marcominerva/SqlDatabaseVectorSearch/refs/heads/master/SqlDatabaseVectorSearch.png)
 
 ## Setup
 
@@ -143,4 +143,4 @@ When using the `/api/ask-streaming` endpoint, answers will be streamed as happen
   - each one contains a token
   - The *streamState* property is set to `Append`
   - *origianlQuestion*, *reformulatedQuestion* and *tokenUsage* are always `null`
-- The stream ends when an element with *streamState* equals to `End` is received. This element contains token usage information for the question and the whole answer.
+- The stream ends when an element with *streamState* equals to `End` is received. This element contains token usage information for the question and the whole answer.

SqlDatabaseVectorSearch/Services/ChatService.cs

@@ -156,7 +156,14 @@ public class ChatService(IChatCompletionService chatCompletionService, Tokenizer
     }
 
     private async Task UpdateCacheAsync(Guid conversationId, ChatHistory chat, CancellationToken cancellationToken)
-        => await cache.SetAsync(conversationId.ToString(), chat, cancellationToken: cancellationToken);
+    {
+        if (chat.Count > appSettings.MessageLimit)
+        {
+            chat.RemoveRange(0, chat.Count - appSettings.MessageLimit);
+        }
+
+        await cache.SetAsync(conversationId.ToString(), chat, cancellationToken: cancellationToken);
+    }
 
     private async Task<ChatHistory> GetChatHistoryAsync(Guid conversationId, CancellationToken cancellationToken)
     {

SqlDatabaseVectorSearch/Settings/AppSettings.cs

@@ -15,4 +15,6 @@ public class AppSettings
     public int MaxOutputTokens { get; init; } = 800;
 
     public TimeSpan MessageExpiration { get; init; }
+
+    public int MessageLimit { get; set; } = 20;
 }

SqlDatabaseVectorSearch/appsettings.json

@@ -24,9 +24,10 @@
         "MaxTokensPerParagraph": 1000,
         "OverlapTokens": 100,
         "MaxRelevantChunks": 10,
-        "MaxInputTokens": 16385,
+        "MaxInputTokens": 16384,
         "MaxOutputTokens": 800,
-        "MessageExpiration": "00:05:00"
+        "MessageExpiration": "00:05:00",
+        "MessageLimit": 20
     },
     "Logging": {
         "LogLevel": {