extract-person

Typed extraction of a nested object — the “hello world” of Nola. The JSON Schema is derived from the Person interface at compile time and the extraction is one typed expression: no runtime type-to-schema library, no re-declared model class. src/format.ts is plain TypeScript, value-imported from the .tsi with the standard NodeNext ./format.js specifier — existing TS code mixes into a nola module with no extra setup.

src/person.tsi

import { normalizePerson } from "./format.js";

export interface Person {
  name: string;
  age: number;
  employer: string;
  job: string;
}

export infer function extractPerson(.message: string) {
  const person = ask ..`the person described in the text`<Person>;
  return normalizePerson(person);
}

src/format.ts

// Plain TypeScript, imported from person.tsi with the standard NodeNext
// `./format.js` specifier — mixing existing TS code into a nola module
// needs no special setup.
import type { Person } from "./person.tsi";

export function normalizePerson(person: Person): Person {
  return { ...person, name: person.name.trim(), employer: person.employer.trim() };
}

Run it

npx nola run src/main.ts                      # mock provider (deterministic)
# real provider: edit nola.config.ts to openai({ model: "gpt-5-mini" }) (needs OPENAI_API_KEY)

Prints {"name":"Alice Smith","age":32,"employer":"Acme Corp","job":"staff engineer"}.

Scaffold: npm create nola my-app — the starter template is this example (without the format.ts helper). Source: examples/extract-person on GitHub.

Next: extract-resume