🎥 Wrangle PDFs from start to finish with custom User Defined Functions (UDFs) in Daft Software Engineer @Malcolm Greaves walks you through every step of a PDF processing pipeline. By the end of the video, you will have a fully functional pipeline that: • Starts with downloading PDFs from an S3 bucket • Extracts text boxes using OCR or by reading the file format • Performs spatial layout analysis to group text boxes into lines or paragraphs • Computes embeddings using a lightweight LLM, running locally • Saves everything to Parquet We've broken up the full 20-minute tutorial into small chapters, so feel free to jump around! Here's the notebook to follow along: https://docs.daft.ai/en/stable/resources/tutorials/#document-processing