Open Source Summit + Embedded Linux Conference + OSPOCon 2021

Most of the data around us is unstructured and stored without relation to the real world. This means that this data is difficult to index, classify and search through. While this is often solved by manual effort or expensive machine learning models, Weaviate takes another approach. Weaviate is a vector search engine, which stores data as vectors and automatically adds context and meaning to new data. This enables to search through the data without using exact matching keywords. Moreover, data can be automatically classified. Weaviate is completely open source, has a built-in machine learning model, has a graph-like data model, completely API-based and is cloud-native. Weaviate uses GraphQL to interact with the data in an intuitive manner. This talk is an introduction to the vector search engine Weaviate. You will learn how pre-trained language models and storing data using vectors enables semantic search and classification. There will be live demos to show Weaviate and how you can get started with your own datasets. No prior technical knowledge is required; all concepts are illustrated with real use case examples and live demos. Different from previous talks are the latest feature developments to store images and connect to language transformer models.