MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-10-09 07:49:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Carry the extraction failure code into the indexer

Browse Source
This commit is contained in:
Thorsten Sommer committed 2026-09-09 10:42:02 +02:00
1 parent 4c69434c47
commit 6dd2389a99
4 files changed
+129 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/MindWork AI Studio/Tools/Services/DataSourceEmbeddingService.cs
+6 -1
View File
@@ -769,8 +769,13 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
if (batch.Count > 0)
await this.FlushBatchAsync(indexStore, vectorStore, dataSource, file, fingerprint, parentFile, embeddingProvider, provider, manifest, optimizationTracker, collectionName, batch, token);
//
// The extraction itself did not report a failure, but nothing usable came out of it. For
// the index this is the same case as a scanned page without a text layer, which is why it
// carries a code of its own instead of an unclassified exception:
//
if (totalChunkCount == 0)
throw new InvalidOperationException(string.Format(TB("No text could be read from the file '{0}'."), file.Name));
throw new FileExtractionException(FileExtractionErrorCode.NO_CONTENT, string.Format(TB("No text could be read from the file '{0}'."), file.Name));
logger.LogDebug(
"Generated {ChunkCount} chunks for file '{FilePath}' in data source '{DataSourceName}' ({DataSourceId}).",