Balanced and Accurate Extraction Modes

import json
from datalab_sdk import DatalabClient, ExtractOptions

client = DatalabClient()

schema = {
    "type": "object",
    "properties": {
        "company_name": {"type": "string", "description": "Full legal name of the company"},
        "fiscal_year_end": {"type": "string", "description": "End date of the fiscal year (YYYY-MM-DD)"},
        "total_revenue": {"type": "number", "description": "Total revenue in the reporting currency"},
        "auditor_name": {"type": "string", "description": "Name of the external audit firm"}
    },
    "required": ["company_name", "fiscal_year_end"]
}

options = ExtractOptions(
    page_schema=json.dumps(schema),
    extraction_mode="balanced",
    mode="accurate",
)

result = client.extract("annual_report.pdf", options=options)
extracted = json.loads(result.extraction_schema_json)

# Each field comes with citations and metadata
print(f"Company: {extracted['company_name']}")
print(f"Citations: {extracted['company_name_citations']}")
print(f"Status: {extracted['company_name_meta']['extraction_status']}")
verification = extracted["company_name_meta"].get("verification") or {}
print(f"Verified: {verification.get('status', 'UNAVAILABLE')}")

curl -X POST https://www.datalab.to/api/v1/extract \
  -H "X-API-Key: $DATALAB_API_KEY" \
  -F "file=@annual_report.pdf" \
  -F "extraction_mode=balanced" \
  -F 'page_schema={"type":"object","properties":{"company_name":{"type":"string","description":"Full legal name"},"total_revenue":{"type":"number","description":"Total revenue"}}}'

# Poll request_check_url from response until status is "complete"

import requests, json, time, os

headers = {"X-API-Key": os.getenv("DATALAB_API_KEY")}

schema = {
    "type": "object",
    "properties": {
        "company_name": {"type": "string", "description": "Full legal name"},
        "total_revenue": {"type": "number", "description": "Total revenue"}
    }
}

with open("annual_report.pdf", "rb") as f:
    response = requests.post(
        "https://www.datalab.to/api/v1/extract",
        files={"file": ("annual_report.pdf", f, "application/pdf")},
        data={
            "page_schema": json.dumps(schema),
            "extraction_mode": "balanced"
        },
        headers=headers
    )

check_url = response.json()["request_check_url"]

while True:
    result = requests.get(check_url, headers=headers).json()
    if result.get("success") is False or result.get("status") == "failed":
        raise RuntimeError(result.get("error") or "Document processing failed")
    if result["status"] == "complete":
        if result.get("result_url"):
            download = requests.get(result["result_url"], timeout=60)
            download.raise_for_status()
            result = {**download.json(), **{k: v for k, v in result.items() if v is not None}}
        if result.get("success") is False:
            raise RuntimeError(result.get("error") or "Document processing failed")
        extracted = result["extraction_schema_json"]
        if isinstance(extracted, str):
            extracted = json.loads(extracted)
        print(json.dumps(extracted, indent=2))
        break
    time.sleep(2)