Skip to content

extract-resume

The industry-canonical structured-extraction demo — every LLM framework has a resume example; this is Nola’s. The types are plain same-file interfaces (nested Education[] included; JSDoc comments become schema descriptions) and the function is imported directly — no schema DSL, no codegen step, no generated client directory, no second language.

src/resume.tsi
export interface Education {
  school: string;
  degree: string;
  /** graduation year */
  year: number;
}


export interface Resume {
  name: string;
  email: string;
  /** one entry per position, most recent first */
  experience: string[];
  skills: string[];
  education: Education[];
}


export infer function extractResume(.message: string) {
  return ask ..`the candidate's resume data`<Resume>;
}

Run it

Section titled “Run it”
Terminal window
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)

Scaffold: npm create nola my-app -- --template extract-resume Source: examples/extract-resume on GitHub.

Next: classify-message