gradio-pdf 0.0.2

Python library for easily interacting with trained machine learning models

gradio_pdf

Display PDFs in Gradio!

Example usage

import gradio as gr
from gradio_pdf import PDF
from pdf2image import convert_from_path
from transformers import pipeline
from pathlib import Path

dir_ = Path(__file__).parent

p = pipeline(
    "document-question-answering",
    model="impira/layoutlm-document-qa",
)

def qa(question: str, doc: str) -> str:
    img = convert_from_path(doc)[0]
    output = p(img, question)
    return sorted(output, key=lambda x: x["score"], reverse=True)[0]['answer']


demo = gr.Interface(
    qa,
    [gr.Textbox(label="Question"), PDF(label="Document")],
    gr.Textbox(),
    examples=[["What is the total gross worth?", str(dir_ / "invoice_2.pdf")],
              ["Whos is being invoiced?", str(dir_ / "sample_invoice.pdf")]]
)

demo.launch()

Demo