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

FixRAGService
已装运
2026年3月30日 22:34 UTC
作者
Kamo
提交
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.

所有更改

就像你看到的运输?

每一个都自动更新您工作空间的地盘。 开始自由,看它成长 一周又一周.

永远开始自由查看定价