文档解析与信息抽取

import base64
import json
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"])

FIELDS = ["invoice_number", "issue_date", "seller_name", "buyer_name", "total_amount", "currency"]
PROMPT = (
    "Extract these fields from the invoice image and reply with one JSON object only: "
    + ", ".join(FIELDS)
    + ". Use null for anything you cannot read. Dates as YYYY-MM-DD, amounts as numbers."
)


def parse_json(text):
    """Some models add text around the JSON; keep the outermost object."""
    return json.loads(text[text.find("{"): text.rfind("}") + 1])


def extract(path):
    with open(path, "rb") as f:
        data_url = "data:image/png;base64," + base64.b64encode(f.read()).decode()
    resp = client.chat.completions.create(
        model="gemini-3.8-flash",
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": PROMPT},
                {"type": "image_url", "image_url": {"url": data_url}},
            ],
        }],
        response_format={"type": "json_object"},
        temperature=0,
    )
    record = parse_json(resp.choices[0].message.content)
    missing = [k for k in FIELDS if k not in record]
    if missing:
        raise ValueError("missing fields: " + ", ".join(missing))
    return record


print(extract("invoice.png"))
# Text-layer PDFs and Word files: extract the text yourself and send it to deepseek-v4.1-flash with the same field list.