online recall

iQIYI Technical Product Team

Aug 20, 2021 · Artificial Intelligence

Engineering Practice of Online Vector Recall Service at iQIYI

iQIYI’s engineering team built an online vector‑recall service on Milvus, wrapping it with a Dubbo‑gRPC interface to serve 6 M 64‑dimensional embeddings at roughly 3 k QPS and 20 ms p99 latency, integrating query‑embedding generation, simplifying recommendation pipelines, and demonstrating the performance and operational advantages of a platformized ANN‑based recall layer.