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

Порезанный

30 марта 2026 г. в 22:34 UTC

Автор

Kamo

Обещать

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.