Getting Started

pip install vlmrun --upgrade

# For video processing
pip install "vlmrun[video]"

# For document processing
pip install "vlmrun[doc]"

# For all features
pip install "vlmrun[all]"

# On Linux/macOS
export VLMRUN_API_KEY="your-api-key"

# On Windows
set VLMRUN_API_KEY=your-api-key

from vlmrun.client import VLMRun

# Initialize the client
client = VLMRun()

# Process an image from a URL
response = client.image.generate(
    urls=["https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.invoice/invoice_1.jpg"],
    domain="document.invoice"
)

# Check if processing completed
if response.status == "completed":
    # `response.response` is returned as a dictionary by default,
    # so access fields with `.get()` or `[ ]` indexing.
    invoice = response.response
    print(f"Invoice #: {invoice.get('invoice_number')}")
    print(f"Total: ${invoice.get('total_amount')}")

# Extract data from a PDF
response = client.document.generate(
    url="https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.invoice/invoice_1.jpg",
    domain="document.invoice"
)

# Transcribe an audio file
response = client.audio.generate(
    url="https://storage.googleapis.com/vlm-data-public-prod/examples/audio/sample.mp3",
    domain="audio.transcription"
)

# Using a local file
from PIL import Image
image = Image.open("invoice.jpg")

response = client.image.generate(
    images=[image],
    domain="document.invoice"
)