In this guide, you’ll go from zero to structured output in under 5 minutes using the Tensorlake SDK.

We’ll walk through uploading a PDF document, enabling signature detection, and printing structured JSON output.

​
Prerequisites

​
Step 1: Install the SDK

pip install tensorlake

​
Step 2: Set Your API Key

Create a .env file or export the variable:

export TENSORLAKE_API_KEY=your-api-key-here

Or in your Python script:

import os
os.environ["TENSORLAKE_API_KEY"] = "your-api-key-here"

​
Step 3: Upload and Parse a Document

Create a file called quickstart.py:

quickstart.py
from tensorlake.documentai import DocumentAI
from tensorlake.documentai.parse import ParsingOptions, SignatureDetectionMode
import os, json

api_key = os.getenv("TENSORLAKE_API_KEY")
doc_ai = DocumentAI(api_key=api_key)

# Upload the document
file_id = doc_ai.upload(path="Residential-Real-Estate-Purchase-Agreement-All-Signed.pdf")

# Configure parsing options
options = ParsingOptions(
    page_number=1,
    chunk_strategy=ChunkingStrategy.NONE,
    table_parsing_strategy=TableParsingStrategy.TSR,
    table_output_mode=TableOutputMode.MARKDOWN,
    detect_signature=True,
    extraction_options=ExtractionOptions(
        schema="""{"properties":{"buyer":{"properties":{"buyer_name":{"type":"string"},"buyer_signature_date":{"description":"Date and time (if both are available) that the buyer signed.","type":"string"},"buyer_signed":{"description":"Determine if the buyer signed the agreement","type":"boolean"}},"type":"object"},"seller":{"properties":{"seller_name":{"type":"string"},"seller_signature_date":{"description":"Date and time (if both are available) that the seller signed.","type":"string"},"seller_signed":{"description":"Determine if the seller signed the agreement","type":"boolean"}},"type":"object"}},"title":"leasing_agreement","type":"object"}""",
        skip_ocr=True,
    ),
)

# Parse
job = doc_ai.parse(file_id=file_id, options=options)
result = doc_ai.wait_for(job)

# Save + print result
with open("output.json", "w") as f:
    json.dump(result.model_dump(), f, indent=2)

print("✅ Output saved to output.json")

Run it:

python quickstart.py

​
What You’ll See

  • A file called output.json with structured data like:
{
  "pages": [
    {
      "page_number": 1,
      "json_result": {
        "buyer": {
          "buyer_name": "Nova Ellison",
          "buyer_signature_date": "September 10, 2025",
          "buyer_signed": true
        },
        "seller": {
          "seller_name": "Juno Vega",
          "seller_signature_date": "September 10, 2025",
          "seller_signed": true
        }
      }
    }
  ]
}

​
Next Steps

Need help? Join our Slack and say hi!