Q1
A data engineer is building the ingestion pipeline for a RAG system. The source consists of thousands of large PDF documents stored in an OCI Object Storage bucket. Which sequence of steps, using a framework like LangChain, correctly describes the data preparation process before the data can be stored in a vector database? ```mermaid flowchart LR A[OCI Object Storage] --> B{Load Documents} B --> C{Split into Chunks} C --> D{Generate Embeddings} D --> E[(Vector Database)] ```