Skip to main content

Documentation Index

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

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

This example demonstrates how to build a Tensorlake application that extracts structured data from driver’s license images using OpenAI’s vision model. What you’ll learn:
  • Processing multimodal data (images) in Tensorlake
  • Using custom dependencies with Docker images
  • Managing API secrets securely
  • Extracting structured data with Pydantic models
structured_extraction.py
import os
import base64

import requests
from pydantic import BaseModel
from tensorlake.applications import application, function, Image, RequestError

# Install dependencies for your application
image = Image().run("pip install openai pydantic requests")
# List of secrets required by the application.
# The application expects to find these secrets in the environment.
secrets = ["OPENAI_API_KEY"]

class DrivingLicense(BaseModel):
    name: str
    date_of_birth: str
    address: str
    license_number: str
    license_expiration_date: str

@application()
@function(image=image, secrets=secrets)
def extract_driving_license_data(url: str) -> DrivingLicense:
    from openai import OpenAI

    # Download image from URL
    http_response = requests.get(url)
    http_response.raise_for_status()

    # Encode image as base64
    image_base64 = base64.b64encode(http_response.content).decode("utf-8")

    # Determine image format from content type or URL
    content_type = http_response.headers.get("content-type", "")
    if "jpeg" in content_type or "jpg" in content_type:
        image_format = "jpeg"
    elif "png" in content_type:
        image_format = "png"
    else:
        # Default to jpeg if can't determine
        image_format = "jpeg"

    # Extract structured data using OpenAI's vision model
    openai = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

    completion = openai.beta.chat.completions.parse(
        model="gpt-4o-mini",
        messages=[
            {
                "role": "system",
                "content": "Extract the personal information from the driving license image.",
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/{image_format};base64,{image_base64}"
                        },
                    }
                ],
            },
        ],
        response_format=DrivingLicense,
    )

    license_data: DrivingLicense = completion.choices[0].message.parsed
    return license_data
Building custom images allows you to install pretty much anything you want in your function’s environment. Take a look at the Dependency management guide to learn more about it. Before we deploy this application on Tensorlake, we need to make sure the function can access the secret api key. You can do this by running the tl secrets command in your terminal: 
tl secrets set OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
If you want to learn more about how we manage secrets, take a look at the Secrets management guide.
Now that you’ve defined your custom image, and set the secret api key, you can deploy the application: 
tl deploy structured_extraction.py
You should see the tensorlake stream build logs as your image is being built. Once the image is built, you can invoke the application as before. 
curl -N -X POST https://api.tensorlake.ai/applications/extract_driving_license_data \
  -H "Authorization: Bearer $TENSORLAKE_API_KEY" \
  --json '"https://tlake.link/dl"'
The response will contain the extracted structured data: 
{
  "name": "John Doe",
  "date_of_birth": "1990-01-15",
  "address": "123 Main St, City, State 12345",
  "license_number": "D1234567",
  "license_expiration_date": "2025-01-15"
}