Module 5 of 6Lesson 2 of 2~16 min
Keep the index up to date
An answer that was correct last week can turn wrong without anyone noticing if the index does not keep up with its sources. You learn to set a freshness target suited to each source, choose how to meet it, remember content that has been removed, and make sync failures visible.
Lesson objective
By the end of this lesson, you will be able to set a freshness target per source and specify the mechanisms that meet it: resync, deletion propagation, versions and an alert on failure.
Topics covered
- index freshness
- reindexing
- source synchronization
- stale data
Where it fits
Access rights and freshness
How do you guarantee that each user only reads what they are allowed to see, in its current version?
Lessons in this module
- Filter by access rights before the model
- Keep the index up to date (this lesson)
What you will learn in the course
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.
- Design retrieval: semantic, keyword or hybrid search, reranking, contextual retrieval, number of passages and relevance threshold.
- Specify the answer grounded in sources, how citations are displayed, how conflicting sources are handled and what happens when nothing is found.
- Specify access filtering before the model reads any passage, and index freshness (resync, deletions, versions).
- Build a set of 30 test questions that covers RAG failure modes and diagnose which stage caused a wrong answer.
- Estimate the cost items of a RAG system and choose between a hosted tool, a managed knowledge base, a vector database and a custom build.
Related courses
- Build an AI assistant for your productAdvanced · ~3 hr
- Evaluate an AI feature: test sets, metrics and LLM judgesAdvanced · ~3 hr
- Ship and monitor an AI feature in productionExpert · ~3 hr