"""The LLM extraction call: one scanned invoice in, its fields out, each with word scores."""
import json

from google import genai
from google.genai import types

MODEL = "gemini-2.5-flash"
FIELDS = {  # field name -> mandatory
    "Invoice number": True,
    "Invoice date": True,
    "Vendor": True,
    "PO number": False,
    "Due date": True,
    "Total": True,
}
PROMPT = (
    "Read this invoice. Return JSON: a list of {field, value, word_scores}, one per field in "
    + ", ".join(FIELDS)
    + ". word_scores is your 0-1 legibility score for each word of the value. Use an empty "
    "value and no scores when a field isn't on the page."
)


def extract_invoice(document: bytes, mime_type: str) -> list[dict]:
    client = genai.Client()  # credentials come from the environment
    response = client.models.generate_content(
        model=MODEL,
        contents=[types.Part.from_bytes(data=document, mime_type=mime_type), PROMPT],
        config=types.GenerateContentConfig(response_mime_type="application/json"),
    )
    rows = json.loads(response.text)
    for row in rows:
        row["mandatory"] = FIELDS.get(row["field"], False)
    return rows