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

Name

lúc 22:34 30 tháng 3, 2026 UTC

Tác giả

Kamo

Cam kết

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.