Document processing

from typing import List, Optional

from agno.agent import Agent
from agno.media import File
from agno.models.openai import OpenAIResponses
from pydantic import BaseModel, Field


class LineItem(BaseModel):
    description: str
    quantity: Optional[float] = None
    unit_price: Optional[float] = None
    amount: Optional[float] = None


class Invoice(BaseModel):
    invoice_number: Optional[str] = Field(None, description="As printed on the invoice")
    vendor: Optional[str] = None
    invoice_date: Optional[str] = None
    due_date: Optional[str] = None
    subtotal: Optional[float] = None
    tax: Optional[float] = None
    total: Optional[float] = None
    currency: Optional[str] = Field(None, description="ISO 4217, e.g. USD, EUR")
    lines: List[LineItem] = Field(default_factory=list)


agent = Agent(
    model=OpenAIResponses(id="gpt-5.5"),
    instructions=(
        "Extract invoice fields and line items from the attached PDF. "
        "Use exactly what the document shows. If a field is missing, "
        "leave it null. Do not guess."
    ),
    output_schema=Invoice,
)

result = agent.run(
    "Extract the invoice.",
    files=[File(url="https://example.com/invoice-1042.pdf")],
).content
# Invoice(invoice_number='1042', vendor='Acme Corp', invoice_date='2026-04-12',
#         due_date='2026-05-12', subtotal=1200.0, tax=96.0, total=1296.0,
#         currency='USD', lines=[LineItem(...), LineItem(...)])