Structured Extraction

import json
from datalab_sdk import DatalabClient, ExtractOptions

client = DatalabClient()

# Define a JSON schema for extraction
page_schema = json.dumps({
    "invoice_number": {"type": "string", "description": "Invoice number"},
    "total": {"type": "number", "description": "Total amount due"},
    "vendor": {"type": "string", "description": "Vendor or company name"},
    "items": {
        "type": "array",
        "items": {
            "type": "object",
            "properties": {
                "description": {"type": "string"},
                "amount": {"type": "number"}
            }
        }
    }
})

options = ExtractOptions(page_schema=page_schema)
result = client.extract("invoice.pdf", options=options)

# Access the extracted data
extracted = json.loads(result.extraction_schema_json)
print(extracted)

import json
from datalab_sdk import DatalabClient, ConvertOptions, ExtractOptions

client = DatalabClient()

# Step 1: Convert and save a checkpoint
convert_options = ConvertOptions(
    mode="accurate",
    save_checkpoint=True,
)
convert_result = client.convert("report.pdf", options=convert_options)
print(convert_result.markdown)

# Step 2: Extract using the checkpoint (no re-parsing needed)
page_schema = json.dumps({
    "title": {"type": "string", "description": "Document title"},
    "author": {"type": "string", "description": "Author name"},
    "date": {"type": "string", "description": "Publication date"},
    "summary": {"type": "string", "description": "Brief summary of the document"},
})

extract_options = ExtractOptions(
    page_schema=page_schema,
    checkpoint_id=convert_result.checkpoint_id,
)
extract_result = client.extract("report.pdf", options=extract_options)
extracted = json.loads(extract_result.extraction_schema_json)
print(extracted)

result = client.extract("invoice.pdf", options=options)

# Extracted structured data (JSON string)
extracted = json.loads(result.extraction_schema_json)
print(extracted["invoice_number"])
print(extracted["total"])

# Standard conversion fields are also available
print(result.success)
print(result.markdown)
print(result.page_count)
print(result.cost_breakdown)

import asyncio
import json
from datalab_sdk import AsyncDatalabClient, ExtractOptions

async def extract_data():
    async with AsyncDatalabClient() as client:
        page_schema = json.dumps({
            "title": {"type": "string", "description": "Document title"},
            "author": {"type": "string", "description": "Author name"},
        })
        options = ExtractOptions(page_schema=page_schema)
        result = await client.extract("document.pdf", options=options)
        return json.loads(result.extraction_schema_json)

extracted = asyncio.run(extract_data())
print(extracted)