Reading an Invoice

This example extracts information from an invoice — the value of the service and the CNPJ (a Brazilian tax identification number).

File uploads belong in a Page: the uploaded bytes arrive in-memory as file["content"] and you persist them with get_persistent_dir(). The AI extracts more reliably from text than from a raw document, so we extract_text first and prompt on the resulting string.

from pathlib import Path

from abstra.pages import register_function
from abstra.common import get_persistent_dir
from abstra.ai import extract_text, prompt


@register_function
def analyze(file: dict):
    # The upload arrives as {"filename", "content_type", "content"}; persist the bytes.
    dest = get_persistent_dir() / "uploads" / Path(file["filename"]).name
    dest.parent.mkdir(parents=True, exist_ok=True)
    dest.write_bytes(file["content"])

    # Extract the text first, then prompt on the text
    text = extract_text(dest)
    answer = prompt(
        ["Here is an invoice", text],
        format={
            "value": {"type": "number", "description": "Value of the service in dollars"},
            "CNPJ": {"type": "string"},
        },
    )
    return {"value": answer["value"], "cnpj": answer["CNPJ"]}


@register_function
def __render__():
    return """
    <input type="file" id="invoice" accept=".pdf,.jpg,.jpeg,.png">
    <button onclick="go()">Read invoice</button>
    <pre id="out"></pre>
    <script>
      async function go() {
        const file = document.getElementById('invoice').files[0];
        const result = await analyze(file);   // pass the File directly
        document.getElementById('out').textContent = JSON.stringify(result, null, 2);
      }
    </script>
    """