Retrieval-augmented generation (RAG) fundamentals

This section introduces the key components and principles behind developing RAG applications over unstructured data.

Diagram of RAG application components.

In particular:

  • Data pipeline: Transforming unstructured documents, such as collections of PDFs, into a format suitable for retrieval using the RAG application’s data pipeline.

  • Retrieval, Augmentation, and Generation (RAG chain): A series (or chain) of steps is called to:

    • Understand the user’s question.

    • Retrieve the supporting data.

    • Call an LLM to generate a response based on the user’s question and supporting data.

  • Evaluation: Assessing the RAG application to determine its quality, cost, and latency to ensure it meets your business requirements.

  • Governance and LLMOps: Tracking and managing the lifecycle of each component, including data lineage and governance (access controls).