M02 Data Pipeline, CI/CD setup

Students will establish a foundational data pipeline by ingesting a subset of the corpus, extracting and structuring text data, and initially storing it across PostgreSQL, a vector store, and a minimal Neo4j graph, while continuously refining the systems architecture.

• Basic ingestion of PDFs/text (subset of corpus).
• Text extraction, chunking, basic metadata extraction.
• First data written to PostgreSQL, vector store, and (at least) a minimal Neo4j graph.
• Updated architecture diagram.