Build the first working article embedding search

Build only what the claim requires: query embedding + article embeddings produce a stable top-1 for the fixture question. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

export async function run(input: unknown, deps: Dependencies) {
  const started = performance.now();
  const validated = deps.parseInput(input);
  const raw = await deps.execute(validated); // POST `${AI_BASE_URL}/embeddings` with `{ model: EMBEDDING_MODEL, input: texts }`
  const value = deps.parseOutput(raw);
  return { value, durationMs: Math.round(performance.now() - started) };
}

Expected evidence: The query “reset password” returns the password-reset article first with a finite score.. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from three short support articles + one gold query. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the article embedding search, print or log at least three intermediates that map to the claim (query embedding + article embeddings produce a stable top-1 for the fixture question). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with three short support articles + one gold query twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports rank articles by cosine similarity to an embedded query. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation 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 a deterministic path with printed intermediates 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