Skip to main content

Documentation Index

Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Turn unstructured text into typed JSON objects using the Vercel AI SDK’s generateObject function. Define a Zod schema, pass the text, and get back validated, type-safe data — no regex, no prompt engineering for JSON formatting.

​
How it works

Unstructured text → AI model + Zod schema → Typed JSON object
The Vercel AI SDK handles JSON mode, schema enforcement, and validation automatically. You define the shape, the model fills it in.

​
Extract contact information

import { runcrate } from '@runcrate/ai';
import { generateObject } from 'ai';
import { z } from 'zod';

const contactSchema = z.object({
  name: z.string().describe('Full name'),
  email: z.string().email().optional().describe('Email address'),
  phone: z.string().optional().describe('Phone number'),
  company: z.string().optional().describe('Company name'),
  role: z.string().optional().describe('Job title or role'),
});

const { object: contact } = await generateObject({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  schema: contactSchema,
  prompt: `Extract contact info from this email signature:

    Best regards,
    Sarah Chen
    Senior Product Manager, Acme Corp
    sarah.chen@acme.com | (415) 555-0192`,
});

console.log(contact.name);    // "Sarah Chen"
console.log(contact.company); // "Acme Corp"
console.log(contact.email);   // "sarah.chen@acme.com"

​
Parse invoices

import { runcrate } from '@runcrate/ai';
import { generateObject } from 'ai';
import { z } from 'zod';

const invoiceSchema = z.object({
  invoiceNumber: z.string().describe('Invoice or receipt number'),
  date: z.string().describe('Invoice date in ISO 8601 format'),
  vendor: z.string().describe('Vendor or merchant name'),
  items: z.array(z.object({
    description: z.string(),
    quantity: z.number(),
    unitPrice: z.number(),
    total: z.number(),
  })),
  subtotal: z.number(),
  tax: z.number(),
  total: z.number(),
  currency: z.string().default('USD'),
});

const invoiceText = `
INVOICE #INV-2024-0847
Date: March 15, 2025
From: Cloud Hardware Co.

2x NVIDIA A100 80GB rental (30 days) — $4,800.00 each
1x 10TB NVMe storage — $120.00

Subtotal: $9,720.00
Tax (8.5%): $826.20
Total: $10,546.20
`;

const { object: invoice } = await generateObject({
  model: runcrate('deepseek-ai/DeepSeek-V3'),
  schema: invoiceSchema,
  prompt: `Extract all invoice data from this text:\n\n${invoiceText}`,
});

console.log(`Invoice ${invoice.invoiceNumber}: $${invoice.total}`);
for (const item of invoice.items) {
  console.log(`  ${item.quantity}x ${item.description}: $${item.total}`);
}
The same pattern works for any structured data: product catalogs, support tickets, medical records, job postings. Define a Zod schema, call generateObject, and get typed results.

​
Next steps