Finished the function for importing arbitrary documents (#516)

app/MindWork AI Studio/Components/ReadFileContent.razor.cs

@@ -38,8 +38,7 @@ public partial class ReadFileContent : MSGComponentBase
             return;
         }
         
-        var streamId = Guid.NewGuid().ToString();
-        var fileContent = await this.RustService.ReadArbitraryFileData(selectedFile.SelectedFilePath, streamId, int.MaxValue);
+        var fileContent = await this.RustService.ReadArbitraryFileData(selectedFile.SelectedFilePath, int.MaxValue);
         await this.FileContentChanged.InvokeAsync(fileContent);
     }
 }

app/MindWork AI Studio/Tools/ContentStreamSseHandler.cs

@@ -8,7 +8,7 @@ public static class ContentStreamSseHandler
     private static readonly ConcurrentDictionary<string, List<ContentStreamPptxImageData>> CHUNKED_IMAGES = new();
     private static readonly ConcurrentDictionary<string, int> CURRENT_SLIDE_NUMBERS = new();
 
-    public static string ProcessEvent(ContentStreamSseEvent? sseEvent, bool extractImages = true)
+    public static string? ProcessEvent(ContentStreamSseEvent? sseEvent, bool extractImages = true)
     {
         switch (sseEvent)
         {
@@ -16,40 +16,50 @@ public static class ContentStreamSseHandler
                 switch (sseEvent.Metadata)
                 {
                     case ContentStreamTextMetadata:
-                        return $"{sseEvent.Content}\n";
+                        return sseEvent.Content;
                 
                     case ContentStreamPdfMetadata pdfMetadata:
                         var pageNumber = pdfMetadata.Pdf?.PageNumber ?? 0;
-                        return $"# Page {pageNumber}\n{sseEvent.Content}";
+                        return $"""
+                                # Page {pageNumber}
+                                {sseEvent.Content}
+                                
+                                """;
                     
                     case ContentStreamSpreadsheetMetadata spreadsheetMetadata:
                         var sheetName = spreadsheetMetadata.Spreadsheet?.SheetName;
                         var rowNumber = spreadsheetMetadata.Spreadsheet?.RowNumber;
                         var spreadSheetResult = new StringBuilder();
-                        if (rowNumber == 1)
-                            spreadSheetResult.AppendLine($"\n# {sheetName}");
-                
-                        spreadSheetResult.AppendLine($"{sseEvent.Content}");
+                        if (rowNumber == 0)
+                        {
+                            spreadSheetResult.AppendLine();
+                            spreadSheetResult.AppendLine($"# {sheetName}");
+                        }
+
+                        spreadSheetResult.Append(sseEvent.Content);
                         return spreadSheetResult.ToString();
                 
                     case ContentStreamDocumentMetadata:
                     case ContentStreamImageMetadata:
-                        return $"{sseEvent.Content}";
+                        return sseEvent.Content;
 
                     case ContentStreamPresentationMetadata presentationMetadata:
                         var slideNumber = presentationMetadata.Presentation?.SlideNumber ?? 0;
                         var image = presentationMetadata.Presentation?.Image ?? null;
                         var presentationResult = new StringBuilder();
                         var streamId = sseEvent.StreamId;
-
+                        
                         CURRENT_SLIDE_NUMBERS.TryGetValue(streamId!, out var currentSlideNumber);
-
                         if (slideNumber != currentSlideNumber)
+                        {
+                            presentationResult.AppendLine();
                             presentationResult.AppendLine($"# Slide {slideNumber}");
+                        }
 
-                        presentationResult.Append($"{sseEvent.Content}");
-
-                        if (image is not null)
+                        if(!string.IsNullOrWhiteSpace(sseEvent.Content))
+                            presentationResult.AppendLine(sseEvent.Content);
+                        
+                        if (extractImages && image is not null)
                         {
                             var imageId = $"{streamId}-{image.Id!}";
                             var isEnd = ProcessImageSegment(imageId, image);
@@ -58,8 +68,8 @@ public static class ContentStreamSseHandler
                         }
 
                         CURRENT_SLIDE_NUMBERS[streamId!] = slideNumber;
-
-                        return presentationResult.ToString();
+                        return presentationResult.Length is 0 ? null : presentationResult.ToString();
+                    
                     default:
                         return sseEvent.Content;
                 }
@@ -68,7 +78,7 @@ public static class ContentStreamSseHandler
                 return sseEvent.Content;
             
             default:
-                return string.Empty;
+                return null;
         }
     }
     

app/MindWork AI Studio/Tools/Services/RustService.Retrieval.cs

@@ -5,9 +5,10 @@ namespace AIStudio.Tools.Services;
 
 public sealed partial class RustService
 {
-    public async Task<string> ReadArbitraryFileData(string path, string streamId, int maxChunks)
+    public async Task<string> ReadArbitraryFileData(string path, int maxChunks, bool extractImages = false)
     {
-        var requestUri = $"/retrieval/fs/extract?path={Uri.EscapeDataString(path)}&stream_id={streamId}";
+        var streamId = Guid.NewGuid().ToString();
+        var requestUri = $"/retrieval/fs/extract?path={Uri.EscapeDataString(path)}&stream_id={streamId}&extract_images={extractImages}";
         var request = new HttpRequestMessage(HttpMethod.Get, requestUri);
         var response = await this.http.SendAsync(request, HttpCompletionOption.ResponseHeadersRead);
 
@@ -36,8 +37,10 @@ public sealed partial class RustService
                 var sseEvent = JsonSerializer.Deserialize<ContentStreamSseEvent>(jsonContent);
                 if (sseEvent is not null)
                 {
-                    var content = ContentStreamSseHandler.ProcessEvent(sseEvent, false);
-                    resultBuilder.Append(content);
+                    var content = ContentStreamSseHandler.ProcessEvent(sseEvent, extractImages);
+                    if(content is not null)
+                        resultBuilder.AppendLine(content);
+                    
                     chunkCount++;
                 }
             }

app/MindWork AI Studio/wwwroot/changelog/v0.9.49.md

@@ -1,5 +1,6 @@
 # v0.9.49, build 224 (2025-06-xx xx:xx UTC)
-- Added a library by Nils Kruthoff (`nilskruthoff`) that allows AI Studio to read PowerPoint files. This feature is not yet available in the UI, but it will soon be available. Thanks, Nils, for that great contribution.
+- Added a library by Nils Kruthoff (`nilskruthoff`) that allows AI Studio to read PowerPoint files. Thanks, Nils, for that great contribution.
+- Added support for loading arbitrary document data into some assistants. This functionality replaces the previous PDF reading function and was contributed by Nils as well.
 - Improved the loading of some components that require data fetching, resulting in a more responsive UI.
 - Improved some awkward phrasings in English and German.
 - Improved the implementation of configuration plugins to enhance long-term maintainability.