Define the article embedding search input contract

The accepted input remains: article texts, embedding function (fake or API), query string. 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: rank articles by cosine similarity to an embedded query.

function assertDim(vec, n=3){ if(!Array.isArray(vec)||vec.length!==n) throw new Error('dim'); return vec; }
console.log(assertDim([0.1,0.2,0.3]));

Expected evidence: embedding dim contract. 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 article embedding search so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of embedding-api-lab—not as comments you plan to delete.

List every field in three short support articles + one gold query 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 article embedding search.

Add one sentence about encoding, units, or timezones if relevant to article texts, embedding function (fake or API), query string. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to rank articles by cosine similarity to an embedded query.

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 comparing raw tokens without vectors, or dimension mismatch harder to confuse with a model or algorithm bug later.

At the data contract stage for embedding-api-lab, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about three short support articles + one gold query 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: keyword overlap ranking on the same articles.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to rank articles by cosine similarity to an embedded query. If you cannot point to a file, command, or assertion that proves that for the article embedding search, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next