Deploy a RAG app
Measure smoke goldens and readiness correctness
Executable checks prove readyz fails if index digest ≠ pinned digest; rollback restores previous digest in < 2 min on fixtures — including the known misshape behind DEPLOY-EMPTY-INDEX-5.
1Learn the idea
Read
Schema and policy checks
Add executable validation at the trust boundaries of containerized café FAQ RAG with readiness probes and versioned index pin. Reject unknown fields where they matter, bound string sizes, and coerce only after auth/signature checks when raw bytes are security-relevant. Invariant under test: readyz fails if index digest ≠ pinned digest; rollback restores previous digest in < 2 min. A TypeScript type or Python annotation is not runtime validation — pair them with parsers.
Read
Golden and adversarial fixtures
Automate the fixtures from setup, including a recreation of DEPLOY-EMPTY-INDEX-5. Assert both the visible error and the absence of side effects (no provider call, no queue write, no flag flip). Where metrics matter, assert label enums stay bounded.
Read
Implementation artifact
assert client.get("/readyz").status_code == 200
assert client.get("/answer?q=hours").json()["citation"] == "doc:hours"
Read
Gate semantics
Document which failures are client mistakes (4xx) versus operator/config mistakes (5xx/503). Oracle still stands: kubectl rollout status shows ready; /readyz 200 only when index pin matches. Validation should make accidental “success with empty body” impossible for platform engineer shipping faq-index@sha256:a1b2 to staging.
Read
Stage depth
Property ideas: shuffled field order, Unicode edges, maximum-length strings, and replayed timestamps. Where money, identity, or citations matter, assertion messages should cite the field name. Do not snapshot entire provider payloads in tests; assert semantically. If validation fails open “to keep the demo working,” you have inverted the lab. Tie at least one CI job to the DEPLOY-EMPTY-INDEX-5 fixture so main cannot regress silently. Re-read readyz fails if index digest ≠ pinned digest; rollback restores previous digest in < 2 min after each new parser — convenience helpers love to bypass it.
Read
Field notes for `deploy-rag-app` / `validation`
Table-drive status codes and error codes so reviewers see coverage at a glance. Include a Unicode normalization case if user text is accepted. Verify that oversized bodies fail before CPU-heavy work. Where digests or versions are pinned, assert mismatch behavior. Keep golden files small enough to read in review. CI should fail on skipped tests that mark the incident fixture as xfail without a ticket link. In this chapter the product is containerized café FAQ RAG with readiness probes and versioned index pin, the human stakeholder is platform engineer shipping faq-index@sha256:a1b2 to staging, and the incident id you design against is DEPLOY-EMPTY-INDEX-5. Re-state the oracle in your notes — kubectl rollout status shows ready; /readyz 200 only when index pin matches — and keep the invariant visible: readyz fails if index digest ≠ pinned digest; rollback restores previous digest in < 2 min. Track ready_ratio == 1 and citation_miss_rate ≤ 0.02 during rollout as the scoreboard. Surface under change control: GET /readyz. If you only have forty minutes, finish the fixture for new pods serve empty index while old pods terminate — citation miss spike before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.
Go deeper
Before you start
Why this matters
List three fixtures: one golden success, one schema/auth reject, and one regression for DEPLOY-EMPTY-INDEX-5. For each, write the exact assertion (status, code, metric, or citation) that must turn red if broken.
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.