Why does a RAG ingestion pipeline need its own ETL process instead of just embedding raw files directly?

Raw documents (PDFs, HTML, Word docs) need to be parsed into clean text, split into appropriately-sized chunks, and have metadata attached (source, page number) before embedding — skipping this means embedding messy formatting artifacts or chunks with no traceability back to their source, which hurts both retrieval quality and the ability to cite where an answer came from.