Skip to content
StackUnseen
Subscribe

Five-day tracks

5 Days of Production RAG

Retrieval as a system you operate: trusted sources and freshness, ingestion as a data product, retrieval as its own subsystem, chunking for the question, and citations you can evaluate.
10 min in total
  1. 01

    Part 1 · Explainer · 2 min read

    Your vector index does not know who is allowed to read it

    Embeddings carry no access control lists. Ownership, permissions, freshness and lineage have to be designed before anything is indexed.

    On the map: Sources, Ingestion
  2. 02

    Part 2 · Explainer · 2 min read

    Ingestion is a data product, not a loader script

    Parsing sets your quality ceiling, failures need a destination, and the update and delete paths are the half nobody tests.

    On the map: Ingestion
  3. 03

    Part 3 · Explainer · 2 min read

    Test retrieval on its own or you will tune the wrong thing

    Most "the model is wrong" problems are recall problems. Hybrid search, query rewriting and versioned indexes are where they get fixed.

    On the map: Retrieval
  4. 04

    Part 4 · Explainer · 2 min read

    Chunk for the question, not for the token limit

    Chunk size is a decision about what a complete answer looks like. Reranking, context budgets and refusal thresholds finish the job.

    On the map: Ingestion, Retrieval
  5. 05

    Part 5 · Explainer · 2 min read

    You cannot run RAG on user complaints

    Groundedness scores, per-claim citations and an operations dashboard are what tell you quality is drifting before your users do.

    On the map: Retrieval, Observability