VLMRun Client
│
├── Content APIs
│   ├── client.image     # Image processing
│   ├── client.document  # Document processing
│   ├── client.audio     # Audio processing
│   └── client.video     # Video processing
│
├── Resource APIs
│   ├── client.files     # File management
│   ├── client.hub       # Domain & schema access
│   ├── client.models    # Model information
│   └── client.gateway   # OpenAI-compatible OCR / VLM gateway
│
└── Utility APIs
    ├── client.predictions # Prediction management
    └── client.fine_tuning # Model customization

# Process an image from a file
response = client.image.generate(
    images=[image],
    domain="document.invoice"
)

# From a URL
response = client.image.generate(
    urls=["https://example.com/invoice.jpg"],
    domain="document.invoice"
)

# Process a document
response = client.document.generate(
    file="document.pdf",
    domain="document.invoice"
)

# Process audio
response = client.audio.generate(
    file="recording.mp3",
    domain="audio.transcription"
)

# Process video
response = client.video.generate(
    file="clip.mp4",
    domain="video.dashcam-analytics",
    batch=True
)

# Key fields of a prediction response
prediction = client.image.generate(...)

prediction.id          # Unique identifier
prediction.status      # Processing status
prediction.created_at  # Creation timestamp
prediction.response    # Structured results (when complete)
prediction.usage       # Resource usage information

# Start processing
prediction = client.document.generate(
    file="large-document.pdf",
    domain="document.invoice"
)

# Wait for processing to complete
if prediction.status != "completed":
    prediction = client.predictions.wait(prediction.id)

# Now work with the results
result = prediction.response

# Get structured data from a domain schema
response = client.image.generate(
    images=[image],
    domain="document.invoice"
)

# Access fields in the response
invoice_data = response.response
print(f"Invoice #: {invoice_data.invoice_number}")
print(f"Amount: ${invoice_data.total_amount}")

from pydantic import BaseModel, Field

# Define a custom schema
class ProductInfo(BaseModel):
    name: str = Field(..., description="Product name")
    price: float = Field(..., description="Product price")
    category: str = Field(..., description="Product category")

# Use the custom schema
response = client.image.generate(
    images=[product_image],
    domain="image.product",
    config={"json_schema": ProductInfo.model_json_schema()}
)

# Upload a file
file = client.files.upload("document.pdf")

# Use the file in a prediction
prediction = client.document.generate(
    file=file.id,
    domain="document.invoice"
)

# List available domains
domains = client.hub.list_domains()

# Get details about a domain
schema = client.hub.get_schema("document.invoice")

# List available models
models = client.models.list()

# Process and extract in one step
response = client.image.generate(
    images=[image],
    domain="document.invoice",
    autocast=True  # Get a type-safe model
)

# Work with the structured data
invoice = response.response
total_with_tax = invoice.total_amount * 1.1

# 1. Upload file
file = client.files.upload("invoice.jpg")

# 2. Process the file
prediction = client.image.generate(
    file=file.id,
    domain="document.invoice"
)

# 3. Get the results
if prediction.status == "completed":
    invoice_data = prediction.response

# Process multiple files
results = []
for file_path in file_paths:
    response = client.document.generate(
        file=file_path,
        domain="document.invoice",
        batch=True  # Process asynchronously
    )
    results.append(response.id)

# Wait for all results
completed = [client.predictions.wait(id) for id in results]