mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-30 04:29:24 +08:00
## Summary - Parse chat, embedding, and rerank usage from provider responses - Record usage with the correct model type even when no usage sink is provided - Cover SiliconFlow, Aliyun, Huawei Cloud, Qiniu, and VolcEngine response formats
25 KiB
25 KiB