Anvia Docs

Extractors are the easiest path when you have text and want validated data back. Internally, Anvia builds an agent with a required submit tool from your schema.

1. Create the Schema

import { ExtractorBuilder } from "@anvia/core";
import { OpenAIClient } from "@anvia/openai";
import { z } from "zod";

const model = new OpenAIClient({ apiKey }).completionModel("gpt-5");

const ticketSchema = z.object({
  customer: z.string(),
  priority: z.enum(["low", "medium", "high"]),
  summary: z.string(),
});

2. Build the Extractor

const extractor = new ExtractorBuilder(model, ticketSchema)
  .instructions("Extract support ticket fields.")
  .retries(1)
  .build();

Use retries(...) when invalid or missing structured data should be retried before failing.

3. Extract Data

const ticket = await extractor.extract(`
  Acme Co. reports checkout failures for all enterprise users.
  The issue is urgent and blocking revenue.
`);

console.log(ticket.priority);

4. Keep Usage and Messages When Needed

const result = await extractor.extractWithUsage("Ada reports a billing issue.");

console.log(result.data);
console.log(result.usage.totalTokens);
console.log(result.messages);

Use extractWithHistory(...) when extraction should consider previous messages.

Next, read Output Validation to understand where validation happens.