Batch embedding requests to respect model's max batch size of 32

FixRAGService
Shipped
March 30, 2026 at 10:34 PM UTC
Author
Kamo
Commit
e0cd2aa

The embedding model rejects requests with more than 32 inputs, but articles with large content produce 46-198 chunks. All embedding attempts were failing with 413 errors, leaving Qdrant empty.

All changes

Like what you see shipping?

Every one of these updates lands in your workspace automatically. Start free and watch it grow week after week.

Start Free ForeverView Pricing