app.py

import gradio as gr 
import warnings
import json
#import openai
import os

import tiktoken
import gradio as gr
from langchain import OpenAI, PromptTemplate
from langchain.chains.summarize import load_summarize_chain
from langchain.document_loaders import PyPDFLoader

warnings.filterwarnings('ignore')

#openai.api_key = "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"


def num_tokens_from_string(string: str, encoding_name: str) -> int:
    """Returns the number of tokens in a text string."""
    encoding = tiktoken.get_encoding(encoding_name)
    num_tokens = len(encoding.encode(string))
    return num_tokens

num_tokens_from_string("tiktoken is great!", "cl100k_base")

llm = OpenAI(temperature=0)

def summarize_pdf(pdf_file_path):
    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

#summarize = summarize_pdf("Assignment 1 - AIDI.pdf")
#summarize

input_pdf_path = gr.components.Textbox(label="Provide the PDF file path")
output_summary = gr.components.Textbox(label="Summary")

interface = gr.Interface(
    fn=summarize_pdf,
    inputs=input_pdf_path,
    outputs=output_summary,
    title="PDF Summarizer",
    description="Provide PDF file path to get the summary.",
).launch(share=True)