feat(server): increase embedding jobs concurrency & handle empty content after trim (#12574)

<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit

- **Improvements**
  - Increased the default concurrency for background tasks, enhancing processing efficiency.
  - Improved handling of empty or unsupported documents to ensure consistent processing.
  - Optimized document filtering to exclude certain documents from processing, improving performance.

- **Bug Fixes**
  - Enhanced detection of empty document summaries, reducing errors during processing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
darkskygit
2025-05-27 14:28:34 +00:00
parent 7eb6b268a6
commit 9220b973c7
6 changed files with 54 additions and 23 deletions
@@ -199,6 +199,21 @@ test('should insert and search embedding', async t => {
);
t.snapshot(afterAddIgnoreDocs.length, 'should not find docs to embed');
}
{
const docId = `foo$bar`;
await t.context.doc.upsert({
spaceId: workspace.id,
docId: docId,
blob: Uint8Array.from([1, 2, 3]),
timestamp: Date.now(),
editorId: user.id,
});
const results = await t.context.copilotWorkspace.findDocsToEmbed(
workspace.id
);
t.false(results.includes(docId), 'docs containing `$` should be excluded');
}
});
test('should check need to be embedded', async t => {