Data Pipelines in Generative AI
摘要
Data is a fundamental block of all applications. Data is to a molecule as an application is to an object. Data pipelines are necessary to engineer data coming from various sources in various formats, as data powers the intelligence in an intelligent application. This chapter discusses data. Covering all the aspects of data is difficult to do in one chapter. In fact, it is difficult to do in a single book. This chapter attempts to cover some of the aspects of data engineering that explain how data engineering pipelines fit into an intelligent Generative AI application.