> ## Documentation Index
> Fetch the complete documentation index at: https://docs.thedrive.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Extract structured data from a document in under 5 minutes
## 1. Get an API key
Sign up at [dev.thedrive.ai](https://dev.thedrive.ai) and create an API key from the dashboard. Free tier includes 100 credits/month.
## 2. Install the SDK
```bash Python theme={null}
pip install thedriveai
```
```bash TypeScript theme={null}
npm install @thedriveai/sdk
```
## 3. Extract data
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(
file="invoice.pdf",
schema={
"invoice_number": {"type": "string", "description": "The invoice number"},
"vendor": {"type": "string", "description": "Company name"},
"total": {"type": "number", "description": "Total amount due"},
"is_paid": {"type": "boolean", "description": "Whether the invoice is marked as paid"},
},
)
print(result.data)
# {"invoice_number": "INV-2024-0042", "vendor": "Acme Corp", "total": 1234.56, "is_paid": false}
print(result.confidence)
# {"invoice_number": 0.96, "vendor": 0.94, "total": 0.91, "is_paid": 0.85}
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
import { readFileSync } from "fs";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: {
invoice_number: { type: "string", description: "The invoice number" },
vendor: { type: "string", description: "Company name" },
total: { type: "number", description: "Total amount due" },
is_paid: { type: "boolean", description: "Whether the invoice is marked as paid" },
},
});
console.log(result.data);
// { invoice_number: "INV-2024-0042", vendor: "Acme Corp", total: 1234.56, is_paid: false }
```
```bash cURL theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/extract \
-H "X-API-Key: tda_live_..." \
-F file=@invoice.pdf \
-F 'schema={
"invoice_number": {"type": "string", "description": "The invoice number"},
"vendor": {"type": "string", "description": "Company name"},
"total": {"type": "number", "description": "Total amount due"}
}'
```
## 4. Or use Pydantic / Zod
Instead of writing raw JSON schemas, use the tools you already know.
```python Pydantic theme={null}
from pydantic import BaseModel, Field
from thedriveai import TheDriveAI
class Invoice(BaseModel):
invoice_number: str = Field(description="The invoice number")
vendor: str = Field(description="Company name")
total: float = Field(description="Total amount due")
is_paid: bool = Field(description="Whether the invoice is marked as paid")
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(file="invoice.pdf", schema=Invoice)
print(result.data["vendor"]) # "Acme Corp"
print(result.data["total"]) # 1234.56
```
```typescript Zod theme={null}
import { TheDriveAI, fromZod } from "@thedriveai/sdk";
import { readFileSync } from "fs";
import { z } from "zod";
const Invoice = z.object({
invoice_number: z.string().describe("The invoice number"),
vendor: z.string().describe("Company name"),
total: z.number().describe("Total amount due"),
is_paid: z.boolean().describe("Whether the invoice is marked as paid"),
});
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: fromZod(Invoice),
});
console.log(result.data.vendor); // "Acme Corp"
console.log(result.data.total); // 1234.56
```
Both approaches support nested objects, arrays, enums, and optional fields. See [Schemas](/developer/schemas) for the full reference.
## 5. Extract from a URL
You can pass a URL instead of uploading a file. Works with any public URL — the API renders JavaScript-heavy pages with a headless browser.
```python Python theme={null}
result = client.extract(
url="https://example.com/pricing",
schema={
"plans": {
"type": "array",
"description": "Available pricing plans",
"items": {
"type": "object",
"properties": {
"name": {"type": "string", "description": "Plan name"},
"price": {"type": "number", "description": "Monthly price"},
}
}
}
},
)
```
```typescript TypeScript theme={null}
const result = await client.extract({
url: "https://example.com/pricing",
schema: {
plans: {
type: "array",
description: "Available pricing plans",
items: {
type: "object",
properties: {
name: { type: "string", description: "Plan name" },
price: { type: "number", description: "Monthly price" },
},
},
},
},
});
```
## What's in the response
Every extraction returns:
| Field | Description |
| -------------- | ---------------------------------------------------- |
| `data` | Extracted values, type-enforced to match your schema |
| `confidence` | Per-field confidence scores (0.0 - 1.0) |
| `citations` | Per-field source text snippets from the document |
| `field_status` | Per-field found/not\_found status with type info |
| `credits_used` | Credits consumed for this request |
## Error handling
```python Python theme={null}
from thedriveai import TheDriveAI, TheDriveAIError
try:
result = client.extract(file="doc.pdf", schema={...})
except TheDriveAIError as e:
print(e.status_code) # 400, 413, 503, etc.
print(e.detail) # Error detail from the API
```
```typescript TypeScript theme={null}
import { TheDriveAI, TheDriveAIError } from "@thedriveai/sdk";
try {
const result = await client.extract({...});
} catch (e) {
if (e instanceof TheDriveAIError) {
console.log(e.statusCode); // 400, 413, 503, etc.
console.log(e.detail); // Error detail from the API
}
}
```
| Status | Meaning |
| ------ | ------------------------------------------------ |
| `400` | Invalid schema, missing file/URL, or bad request |
| `401` | Missing or invalid API key |
| `413` | File too large (max 50 MB) |
| `503` | AI service temporarily unavailable |
## What's next
Compute and reason over documents — sums, comparisons, risk assessments.
Validate an invoice against a contract, reconcile spreadsheets, compare agreements.
Full type reference — arrays, nested objects, enums, required fields, Pydantic, Zod.
Process documents asynchronously with webhook notifications.