Define the café FAQ retriever input contract

The accepted input remains: five short documents with stable IDs plus one normalized user question. Keep parsing and normalization in functions that do not score, train, or call a model. That split lets a test fail the boundary without blaming the core logic. The user-facing decision stays: answer a café question only when a relevant local note is retrieved and cite its ID.

import re
def tokens(s): return set(re.findall(r'[a-z0-9]+',s.lower()))
assert tokens('Wi-Fi!')=={'wi','fi'}
print(tokens('When is the cafe open?'))

Expected evidence: normalized token sets. If the contract is silent on a bad value, later debugging will look like an algorithm bug when it is really a data bug.

Write one assertion for a neighboring valid input to the café FAQ retriever so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of build-mini-rag—not as comments you plan to delete.

List every field in café notes: hours, wifi, pets, allergens, parking and mark each as required, optional, or forbidden. Required fields must fail loudly when missing; optional fields need defaults you can quote in a test; forbidden fields (secrets, raw PII, path escapes) must never be accepted silently. This list is the contract for the café FAQ retriever.

Add one sentence about encoding, units, or timezones if relevant to five short documents with stable IDs plus one normalized user question. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to answer a café question only when a relevant local note is retrieved and cite its ID.

Write the error string you want for the most likely bad input. Prefer ValueError('threshold out of range')-style messages over generic invalid input. The contract’s job is to make retrieval miss or ungrounded fluent answer harder to confuse with a model or algorithm bug later.

At the data contract stage for build-mini-rag, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about café notes: hours, wifi, pets, allergens, parking that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: always-answer-from-largest-document heuristic.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to answer a café question only when a relevant local note is retrieved and cite its ID. If you cannot point to a file, command, or assertion that proves that for the café FAQ retriever, stay on this page instead of advancing.

How-to: build a 5-document RAG app · Glossary: RAG

Previous · Next