Fixed page numbers being guessed from the text instead of read from the metadata

This commit is contained in:
Thorsten Sommer committed 2026-09-15 13:05:20 +02:00
1 parent 6ce7d856a3
commit 01e09804f6
9 files changed
+285 -49

No files matched your search

@@ -843,7 +843,7 @@ public sealed partial class DataSourceEmbeddingService(SettingsManager settingsM
await foreach (var chunk in this.StreamEmbeddingChunksAsync(file.FullName, dataSource, embeddingProvider, token))
{
batch.Add(new(this.CreatePointId(dataSource.Id, fingerprint, totalChunkCount), chunk, totalChunkCount, TryExtractPageNumber(chunk)));
batch.Add(new(this.CreatePointId(dataSource.Id, fingerprint, totalChunkCount), chunk.Text, totalChunkCount, chunk.PageNumber));
totalChunkCount++;
if (batch.Count >= embeddingBatchSize)