請求書データ抽出：ディープラーニング、機械学習、LLMの比較（2026年ガイド）

from openai import OpenAI
import base64, json

client = OpenAI(
    base_url="https://api.kunavo.com/v1",
    api_key="sk-kn-...",
)

SCHEMA = {
    "name": "invoice",
    "schema": {
        "type": "object",
        "properties": {
            "vendor_name":    {"type": "string"},
            "vendor_tax_id":  {"type": ["string", "null"]},
            "invoice_number": {"type": "string"},
            "invoice_date":   {"type": "string", "description": "ISO 8601"},
            "due_date":       {"type": ["string", "null"]},
            "currency":       {"type": "string", "description": "ISO 4217"},
            "line_items": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "description": {"type": "string"},
                        "quantity":    {"type": "number"},
                        "unit_price":  {"type": "number"},
                        "amount":      {"type": "number"},
                    },
                    "required": ["description", "amount"],
                },
            },
            "subtotal":  {"type": ["number", "null"]},
            "tax":       {"type": ["number", "null"]},
            "total":     {"type": "number"},
        },
        "required": ["vendor_name", "invoice_number", "invoice_date",
                     "currency", "line_items", "total"],
    },
}

def extract(path: str) -> dict:
    image_b64 = base64.b64encode(open(path, "rb").read()).decode()
    resp = client.chat.completions.create(
        model="claude-haiku-4-5",   # the cheapest capable model for clean invoices
        response_format={"type": "json_schema", "json_schema": SCHEMA},
        messages=[
            {"role": "system", "content":
                "Extract the invoice into the schema. Copy values exactly as "
                "printed; use null when a field is absent. Never invent data."},
            {"role": "user", "content": [
                {"type": "image_url",
                 "image_url": {"url": f"data:image/png;base64,{image_b64}"}},
            ]},
        ],
    )
    return json.loads(resp.choices[0].message.content)

inv = extract("invoice_0231.png")

# Cheap arithmetic guardrail: reject when the line items don't add up.
delta = abs(sum(li["amount"] for li in inv["line_items"])
            + (inv.get("tax") or 0) - inv["total"])
if delta > 0.02:
    raise ValueError(f"line items disagree with total by {delta:.2f}")

print(inv["vendor_name"], inv["total"], inv["currency"])

from pydantic import BaseModel, Field
from typing import Literal
from openai import OpenAI

client = OpenAI(base_url="https://api.kunavo.com/v1", api_key=KEY)

class LineItem(BaseModel):
    description: str
    quantity: float | None = None
    unit_price: float | None = None
    amount: float

class Invoice(BaseModel):
    vendor_name: str
    vendor_tax_id: str | None = None
    invoice_number: str
    invoice_date: str = Field(description="ISO 8601")
    currency: str = Field(description="ISO 4217")
    line_items: list[LineItem]
    tax: float | None = None
    total: float
    # A confidence field the model fills in itself is a cheap, surprisingly
    # reliable router: low self-reported confidence correlates well with the
    # documents a human should see.
    confidence: Literal["high", "medium", "low"]

resp = client.chat.completions.create(
    model="claude-haiku-4-5",
    response_format={
        "type": "json_schema",
        "json_schema": {"name": "invoice", "schema": Invoice.model_json_schema()},
    },
    messages=[...],
)

invoice = Invoice.model_validate_json(resp.choices[0].message.content)

CHEAP, STRONG = "claude-haiku-4-5", "claude-sonnet-5"

def valid(inv: dict) -> bool:
    """Arithmetic is the guardrail no confidence score replaces."""
    items = sum(li["amount"] for li in inv["line_items"])
    return abs(items + (inv.get("tax") or 0) - inv["total"]) <= 0.02

def extract_routed(path: str) -> tuple[dict, str]:
    inv = extract(path, model=CHEAP)
    if valid(inv) and inv.get("confidence") != "low":
        return inv, CHEAP

    # Escalate: same prompt, same schema, stronger model. Only the failures
    # pay the higher rate, which is what keeps the blended cost near the
    # cheap tier's.
    inv = extract(path, model=STRONG)
    if not valid(inv):
        raise NeedsHumanReview(path, inv)
    return inv, STRONG

# Blended cost at a 90/10 split, per 10,000 invoices:
#   9,000 x $0.00248 + 1,000 x $0.00497
#   = $27.29