The Free Lunch is Over: Dealing with Unstructured Data in the Era of LLMs

Explore the evolving landscape of unstructured data processing in this 37-minute conference talk from The Apache Software Foundation. Delve into the challenges and opportunities presented by recent advancements in Machine Learning and Large Language Models (LLMs) for Data Engineers. Learn how to process audio, images, and text using vector embeddings, and discover the requirements for building unstructured data-based pipelines. Gain insights into leveraging open-source tools and the Apache data engineering stack, including Apache Spark, Lucene, and Tika, to meet the growing demand for natural language processing of unstructured data sources. Speaker Ismaël Mejía, a Senior Cloud Advocate at Microsoft and Apache Software Foundation member, shares his expertise on adapting to these changes and maintaining unstructured data sources effectively.