gradio_chatwithpdf.py

from openai import OpenAI
import gradio
import pdfplumber
import os
from io import BytesIO

def read_PDF_2(fileobj):
    print("readPDF called")
    pdf_text = ""
    
    pdf_file = BytesIO(fileobj)
    
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            pdf_text += page.extract_text()

    return pdf_text


def askPDF(upload_PDF, prompt):
    print("askPDF called")
    client = OpenAI()

    pdf_text = read_PDF_2(upload_PDF)
    systemMessage = '"""' + pdf_text + '"""' + \
        '\nAnswer all questions according to the text delimited in tripple quotes above'
    completion = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": systemMessage},
            {"role": "user", "content": prompt}
        ]
    )

    return (completion.choices[0].message).content


# gradio deployment
demo = gradio.Interface(fn=askPDF,
                        inputs=[gradio.File(type = "binary",file_types=['.pdf']), 'text'],
                        outputs="text",
                        title = "Ask questions from pdf",
                        description = "Limitations: it works for small files, breaks for long PDFs."
                        )

demo.launch()