The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query. Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.
This text-video retrieval example mainly consists of two notebooks, and I think everyone can learn the basic operations of Towhee and Milvus through the getting started notebook. And the deep dive notebook will make the engine more feasible in production.
In this notebook, you will learn how to reduce resource usage, speed up system, and ensure stability.