document-parser / app.py
segovia
document rename
a154425
Raw History Blame
3.87 kB
from __future__ import annotations
import os
import csv
import tempfile
from pathlib import Path
import gradio as gr
from document_processing import extract_text, is_image_document, to_data_uri
from receipt_ai import extract_receipt_json, extract_receipt_json_from_image
from receipt_results import build_empty_result
RESULT_COLUMNS = [
"source_file",
"document_type",
"fecha",
"fecha_vencimiento",
"cuit_proveedor",
"description_proveedor",
"moneda",
"subtotal",
"taxes",
"total",
"confidence",
]
def parse_uploaded_file(client, model: str, file_path: str) -> dict:
path = Path(file_path)
if is_image_document(path):
result = extract_receipt_json_from_image(client, model, path, to_data_uri(path))
else:
text = extract_text(path)
if not text.strip():
return build_empty_result(path.name)
result = extract_receipt_json(client, model, path, text)
result["source_file"] = path.name
return result
def rows_to_table(rows: list[dict]) -> list[list[object]]:
return [[row.get(column) for column in RESULT_COLUMNS] for row in rows]
def build_csv_download(rows: list[dict]) -> str:
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".csv", mode="w", newline="", encoding="utf-8")
with temp_file as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=RESULT_COLUMNS)
writer.writeheader()
for row in rows:
writer.writerow({column: row.get(column) for column in RESULT_COLUMNS})
return temp_file.name
def process_files(files: list[str] | None, existing_rows: list[dict] | None, model: str):
from dotenv import load_dotenv
from openai import OpenAI
load_dotenv()
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
rows = list(existing_rows or [])
if not files:
return rows, gr.update(value=rows_to_table(rows)), "No files selected."
for file_path in files:
rows.append(parse_uploaded_file(client, model, file_path))
return rows, gr.update(value=rows_to_table(rows)), f"Parsed {len(files)} file(s). Total rows: {len(rows)}."
def clear_results():
return [], gr.update(value=[]), "Results cleared."
def build_app() -> gr.Blocks:
default_model = os.getenv("OPENAI_MODEL", "gpt-4o")
with gr.Blocks(title="Document Parser", theme=gr.themes.Soft()) as demo:
gr.Markdown("# Purchase Receipt Parser\nUpload one or more files and append the extracted receipt data into the grid.")
with gr.Row():
files = gr.File(label="Upload files", file_count="multiple", type="filepath")
model = gr.Textbox(label="Model", value=default_model)
status = gr.Markdown("Ready.")
results_state = gr.State([])
results_grid = gr.Dataframe(
label="Parsed documents",
headers=RESULT_COLUMNS,
value=[],
interactive=False,
wrap=True,
)
with gr.Row():
parse_button = gr.Button("Parse documents", variant="primary")
clear_button = gr.Button("Clear grid")
download_button = gr.DownloadButton(label="Download CSV", variant="secondary", value=build_csv_download, inputs=[results_state])
parse_button.click(
process_files,
inputs=[files, results_state, model],
outputs=[results_state, results_grid, status],
)
clear_button.click(
clear_results,
inputs=[],
outputs=[results_state, results_grid, status],
)
return demo
if __name__ == "__main__":
share_enabled = True
try:
build_app().launch(share=True)
except Exception as exc:
print(f"Share link unavailable ({exc}). Starting local-only Gradio app instead.")
build_app().launch(share=False)