DatabricksPDF is a proof-of-concept repo showing how to extract structured data from unstructured PDF documents (e.g., a resume) into a Delta table using Databricks SQL’s ai_parse_document. It then demonstrates curating that extracted content into “gold” fields using ai_query/LLMs, with example notebooks and a reference architecture diagram

Step-by-step starter project demonstrating how to build, test, and operationalize a Mosaic AI Agent on Databricks using MLflow, Foundation Models, and tool execution.