angela.hashnode.devData Insertion and Data Persistence in a Vector DatabaseMilvus architecture recap SDK sends data requests to proxy, the portal, via load balancer. Then the proxy interacts with coordinator service to write DDL (data definition language) and DML (data manipulation language) requests into message storage. ...Apr 6, 2022·9 min read
angela.hashnode.dev7 Basic NLP Models to Empower Your ML ApplicationAn overview of the 7 NLP models. In the previous post, we have explained what is NLP and its real-world applications. In this post, we will continue to introduce some of the main deep-learning models used in NLP applications. BERT Bidirectional Enco...Mar 24, 2022·3 min read
angela.hashnode.devAccelerating Similarity Search on Really Big Data with Vector Indexing (Part II)From computer vision to new drug discovery, many popular artificial intelligence (AI) applications are powered by vector databases. Indexing, a process of organizing data that drastically accelerates big data search, enables us to efficiently query m...Mar 22, 2022·9 min read
angela.hashnode.devAn Introduction to Milvus Python SDK and APIBackground The following illustration depicts the interaction between SDKs and Milvus through gRPC. Imagine that Milvus is a black box. Protocol Buffers are used to define the interfaces of the server, and the structure of the information they carry....Mar 22, 2022·3 min read
angela.hashnode.devBuilding a Vector Database for Scalable Similarity SearchAccording to statistics, about 80%-90% of the world's data is unstructured. Fueled by the rapid growth of the Internet, an explosion of unstructured data is expected in the coming years. Consequently, companies are in urgent need of a powerful databa...Mar 22, 2022·11 min read
