improved code and made sure components are reused if possible

app/MindWork AI Studio/Tools/Services/DataSourceEmbeddingService.Files.cs

@@ -17,11 +17,6 @@ public sealed partial class DataSourceEmbeddingService
     private const int DEFAULT_CHUNK_OVERLAP_TOKEN_LENGTH = 300;
     private const bool IMAGE_EMBEDDING_ENABLED = false;
 
-    private static readonly string[] RAG_DELIMITED_TABLE_FILE_EXTENSIONS = ["csv", "tsv"];
-    private static readonly string[] RAG_SPREADSHEET_FILE_EXTENSIONS = ["ods", "xlsm", "xlsb"];
-    private static readonly string[] RAG_SPREADSHEET_ADD_IN_FILE_EXTENSIONS = ["xla", "xlam"];
-    private static readonly string[] SKIPPED_RAG_FILE_EXTENSIONS = ["lnk"];
-
     private enum RagFileIndexingDecision
     {
         INDEXABLE,
@@ -575,7 +570,7 @@ public sealed partial class DataSourceEmbeddingService
             ]);
 
         if (this.IsSourceCodeFilePath(filePath))
-            return GetSourceCodeChunkingStrategy(filePath);
+            return GetSourceCodeChunkingStrategy();
 
         return new("document", [
             new("Page or extracted section", SplitBySourceSegments, true),
@@ -587,24 +582,13 @@ public sealed partial class DataSourceEmbeddingService
         ]);
     }
 
-    private static ChunkingStrategy GetSourceCodeChunkingStrategy(string filePath)
-    {
-        var rules = new List<ChunkingRule>
-        {
+    private static ChunkingStrategy GetSourceCodeChunkingStrategy() =>
+        new("source-code", [
             new("Extracted section", SplitBySourceSegments, true),
-        };
-        rules.AddRange(GetSourceCodeDelimiterRules(filePath));
-        rules.Add(new("Line break", SplitByLineBreaks));
-        rules.Add(new("Whitespace", SplitByWhitespace));
-        rules.Add(new("Hard cut", null));
-
-        return new("source-code", rules);
-    }
-
-    private static IReadOnlyList<ChunkingRule> GetSourceCodeDelimiterRules(string filePath) => Path.GetExtension(filePath).TrimStart('.') switch
-    {
-        _ => [],
-    };
+            new("Line break", SplitByLineBreaks),
+            new("Whitespace", SplitByWhitespace),
+            new("Hard cut", null),
+        ]);
 
     private static List<string> NormalizeSplitUnits(IReadOnlyList<string> units, string fallbackText)
     {
@@ -875,16 +859,12 @@ public sealed partial class DataSourceEmbeddingService
 
     private bool IsDelimitedTableFilePath(string filePath)
     {
-        var extension = Path.GetExtension(filePath).TrimStart('.');
-        return RAG_DELIMITED_TABLE_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase);
+        return FileTypes.IsAllowedPath(filePath, FileTypes.DELIMITED_TABLE);
     }
 
     private bool IsSpreadsheetFilePath(string filePath)
     {
-        var extension = Path.GetExtension(filePath).TrimStart('.');
-        return FileTypes.IsAllowedPath(filePath, FileTypes.EXCEL)
-               || RAG_SPREADSHEET_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase)
-               || RAG_SPREADSHEET_ADD_IN_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase);
+        return FileTypes.IsAllowedPath(filePath, FileTypes.SPREADSHEET);
     }
 
     private bool IsSourceCodeFilePath(string filePath)
@@ -894,18 +874,12 @@ public sealed partial class DataSourceEmbeddingService
 
     private bool IsHtmlFilePath(string filePath)
     {
-        var extension = Path.GetExtension(filePath).TrimStart('.');
-        return extension.Equals("html", StringComparison.OrdinalIgnoreCase)
-               || extension.Equals("htm", StringComparison.OrdinalIgnoreCase);
+        return FileTypes.IsAllowedPath(filePath, FileTypes.HTML);
     }
 
     private bool IsSupportedRagFilePath(string filePath)
     {
-        var extension = Path.GetExtension(filePath).TrimStart('.');
-        return FileTypes.IsAllowedPath(filePath, FileTypes.DOCUMENT)
-               || RAG_DELIMITED_TABLE_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase)
-               || RAG_SPREADSHEET_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase)
-               || RAG_SPREADSHEET_ADD_IN_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase);
+        return FileTypes.IsAllowedPath(filePath, FileTypes.DOCUMENT);
     }
 
     private RagFileIndexingDecision GetRagFileIndexingDecision(FileInfo file)
@@ -942,8 +916,7 @@ public sealed partial class DataSourceEmbeddingService
 
     private static bool IsSkippedRagFileName(string fileName)
     {
-        var extension = Path.GetExtension(fileName).TrimStart('.');
-        return SKIPPED_RAG_FILE_EXTENSIONS.Contains(extension, StringComparer.OrdinalIgnoreCase)
+        return FileTypes.IsAllowedPath(fileName, FileTypes.SHORTCUT)
                || fileName.StartsWith(OFFICE_LOCK_FILE_PREFIX, StringComparison.Ordinal);
     }
 
@@ -1126,9 +1099,6 @@ public sealed partial class DataSourceEmbeddingService
             : null;
     }
 
-    private string GetCollectionName(string dataSourceId) =>
-        DataSourceEmbeddingNames.GetCollectionName(dataSourceId);
-
     private string CreatePointId(string dataSourceId, string fingerprint, int chunkIndex) =>
         CreateStableGuid($"{dataSourceId}:chunk:{fingerprint}:{chunkIndex}");
 

app/MindWork AI Studio/Tools/Services/DataSourceEmbeddingService.State.cs

@@ -11,7 +11,7 @@ public sealed partial class DataSourceEmbeddingService
         EmbeddingStateClient? embeddingState,
         CancellationToken token)
     {
-        await this.DeleteCollectionAsync(this.GetCollectionName(dataSourceId), vectorStore, token);
+        await this.DeleteCollectionAsync(DataSourceEmbeddingNames.GetCollectionName(dataSourceId), vectorStore, token);
 
         embeddingState ??= await databaseClientProvider.GetEmbeddingStateAsync(token);
         if (!embeddingState.IsAvailable)

app/MindWork AI Studio/Tools/Services/DataSourceEmbeddingService.cs

@@ -428,11 +428,11 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
             return;
         }
 
-        var collectionName = this.GetCollectionName(dataSource.Id);
+        var collectionName = DataSourceEmbeddingNames.GetCollectionName(dataSource.Id);
         var persistedManifest = await embeddingState.GetManifestAsync(dataSource.Id, token);
         if (persistedManifest.VectorSize > 0)
         {
-            var ensureResult = await this.EnsureCollectionExistsAsync(vectorStore, collectionName, dataSource.Name, persistedManifest.VectorSize, token);
+            var ensureResult = await vectorStore.EnsureVectorStoreExists(collectionName, dataSource.Name, persistedManifest.VectorSize, token);
             if (ensureResult.Created)
             {
                 logger.LogWarning(
@@ -685,7 +685,7 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
         VectorStoreOptimizationTracker optimizationTracker,
         CancellationToken token)
     {
-        var collectionName = this.GetCollectionName(dataSource.Id);
+        var collectionName = DataSourceEmbeddingNames.GetCollectionName(dataSource.Id);
         logger.LogDebug(
             "Resetting stored embeddings for file '{FilePath}' in collection '{CollectionName}' before re-indexing.",
             file.FullName,
@@ -783,7 +783,7 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
         if (manifest.VectorSize == 0)
         {
             token.ThrowIfCancellationRequested();
-            var ensureResult = await this.EnsureCollectionExistsAsync(vectorStore, collectionName, dataSource.Name, vectorSize, token);
+            var ensureResult = await vectorStore.EnsureVectorStoreExists(collectionName, dataSource.Name, vectorSize, token);
             if (!ensureResult.Created)
             {
                 logger.LogWarning(
@@ -792,7 +792,7 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
                     dataSource.Name,
                     dataSource.Id);
                 await vectorStore.DeleteVectorStore(collectionName, token);
-                ensureResult = await this.EnsureCollectionExistsAsync(vectorStore, collectionName, dataSource.Name, vectorSize, token);
+                ensureResult = await vectorStore.EnsureVectorStoreExists(collectionName, dataSource.Name, vectorSize, token);
                 if (!ensureResult.Created)
                     throw new InvalidOperationException($"Vector store '{collectionName}' could not be recreated cleanly.");
             }
@@ -845,11 +845,6 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
         batch.Clear();
     }
 
-    private async Task<VectorStoreEnsureResult> EnsureCollectionExistsAsync(VectorStoreClient vectorStore, string collectionName, string dataSourceName, int vectorSize, CancellationToken token)
-    {
-        return await vectorStore.EnsureVectorStoreExists(collectionName, dataSourceName, vectorSize, token);
-    }
-
     private async Task UpsertPointsAsync(
         VectorStoreClient vectorStore,
         string collectionName,

app/MindWork AI Studio/Tools/Services/DataSourceLocalRetrievalService.cs

@@ -6,6 +6,7 @@ using AIStudio.Tools.Databases;
 using AIStudio.Tools.Databases.EmbeddingState;
 using AIStudio.Tools.Databases.VectorStore;
 using AIStudio.Tools.RAG;
+using AIStudio.Tools.Rust;
 
 namespace AIStudio.Tools.Services;
 
@@ -371,13 +372,18 @@ public sealed class DataSourceLocalRetrievalService(
         }
     }
 
-    private static RetrievalContentType GetRetrievalContentType(string fileType) => fileType.TrimStart('.').ToLowerInvariant() switch
+    private static RetrievalContentType GetRetrievalContentType(string fileType)
     {
-        "csv" or "tsv" or "ods" or "xls" or "xlsx" or "xlsm" or "xlsb" => RetrievalContentType.TEXT_SPREADSHEET,
-        "odp" or "ppt" or "pptx" => RetrievalContentType.TEXT_PRESENTATION,
-        "htm" or "html" => RetrievalContentType.TEXT_WEBSITE,
-        _ => RetrievalContentType.TEXT_DOCUMENT
-    };
+        if (FileTypes.IsAllowedExtension(fileType, FileTypes.DELIMITED_TABLE, FileTypes.SPREADSHEET))
+            return RetrievalContentType.TEXT_SPREADSHEET;
+
+        if (FileTypes.IsAllowedExtension(fileType, FileTypes.POWER_POINT))
+            return RetrievalContentType.TEXT_PRESENTATION;
+
+        return FileTypes.IsAllowedExtension(fileType, FileTypes.HTML)
+            ? RetrievalContentType.TEXT_WEBSITE
+            : RetrievalContentType.TEXT_DOCUMENT;
+    }
 
     private static string GetQueryText(IContent lastUserPrompt) => lastUserPrompt switch
     {