Deep learning models has been proven to be an effective method to extract content from unstructured data like image, video, sound and text. When using pre-trained DL models in production, people will need to handle huge amount of feature vectors.
Milvus is an open source vector similarity search engine, which could help users to perform efficient similarity search over billions of vectors.
Jun will introduce the design and architecture of Milvus, and share the scenarios of Milvus to the audience.