app.py

import os
import openai
import sys

import gradio as gr
from langchain import OpenAI, PromptTemplate
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains.summarize import load_summarize_chain
from langchain.document_loaders import PyPDFLoader
from langchain.chains import RetrievalQA

sys.path.append('../..')

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file

openai.api_key  = os.environ['OPENAI_API_KEY']

llm = OpenAI(temperature=0)
text_splitter = CharacterTextSplitter()

def summarize_pdf(pdf_file_path, custom_prompt=""):
    pdf_file_path = pdf_file_path.name
    loader = PyPDFLoader(pdf_file_path)
    docs = loader.load_and_split()
    chain = load_summarize_chain(llm, chain_type="map_reduce")
    summary = chain.run(docs)
    return summary

def main():
    output_summary = gr.Textbox(label="Summary")

    iface = gr.Interface(
        fn=summarize_pdf,
        inputs=["file"],
        outputs=[output_summary],
        title="PDF Summarizer",
        description="Langchain based summarization application that's given a PDF file or a text from a text box can then create a summary of the text content. <br> Enter the PDF file and get its summary.",
    )

    iface.launch()

if __name__ == "__main__":
    main()