Skip to content
Module
Module 2 of 6Lesson 2 of 2~16 min

Inventory sources and metadata

An assistant that cites a draft or an outdated version quickly loses user trust, and the problem often starts with source selection. You learn to inventory a RAG system's content based on real needs, decide what stays out, and settle early the metadata everything downstream will rely on.

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to build a RAG source inventory from real user questions, decide what is excluded, and list the metadata to capture at ingestion.

Questions this lesson answers

  • How do you build a source inventory for a RAG system?
  • What metadata should you capture before indexing documents for RAG?
  • Should you index every available document in a RAG system?

Topics covered

  • RAG data sources
  • metadata
  • document ingestion
  • knowledge base
  • content governance

Where it fits

Do you need RAG, and on which sources?

Does my need justify RAG, and which sources should go into it?

Lessons in this module

  1. Choose between RAG, long context, injected data and fine-tuning
  2. Inventory sources and metadata (this lesson)

What you will learn in this module

This lesson is part of the course Design a RAG architecture that fits your product

  • Choose, for an information need, between long context, data injected by the application, RAG and fine-tuning, and justify the choice by volume, update frequency, access rights and cost.
  • Specify the source inventory, exclusions, the metadata to capture and the document chunking strategy.

Related courses