app.py

import gradio as gr
import PyPDF2
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores.faiss import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain import OpenAI, VectorDBQA

import os
openai_api_key = os.environ["OPENAI_API_KEY"] 


def pdf_to_text(pdf_file, query):
  # Open the PDF file in binary mode
  with open(pdf_file.name, 'rb') as pdf_file:
      # Create a PDF reader object
      pdf_reader = PyPDF2.PdfReader(pdf_file)

      # Create an empty string to store the text
      text = ""

      # Loop through each page of the PDF
      for page_num in range(len(pdf_reader.pages)):
          # Get the page object
          page = pdf_reader.pages[page_num]
          # Extract the texst from the page and add it to the text variable
          text += page.extract_text()
    #embedding step 
  text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
  texts = text_splitter.split_text(text)

  embeddings = OpenAIEmbeddings()
  #vector store
  vectorstore = FAISS.from_texts(texts, embeddings)

    #inference
  qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=vectorstore)
  return qa.run(query)

examples = [
    [os.path.abspath("NASDAQ_AAPL_2020.pdf"), "how much are the outstanding shares ?"],
    [os.path.abspath("NASDAQ_AAPL_2020.pdf"), "what is competitors strategy ?"],
    [os.path.abspath("NASDAQ_AAPL_2020.pdf"), "who is the chief executive officer ?"],
    [os.path.abspath("NASDAQ_MSFT_2020.pdf"), "How much is the guided revenue for next quarter?"],
    [os.path.abspath("example_file.pdf"), "what are the name of all authors?"],
    [os.path.abspath("breast cancer.pdf"), "What Causes Breast Cancer?"],
    [os.path.abspath("v61n3a11.pdf"), "what is MDT?"]
    
]
      


# Define the Gradio interface
#pdf_input = [gr.inputs.File(label="PDF File")]
#query_input = gr.inputs.Textbox(label="Query")
#outputs = gr.outputs.Textbox(label="Chatbot Response")

interface = gr.Interface(fn=pdf_to_text, 
                         inputs= [gr.inputs.File(label="input pdf file"), gr.inputs.Textbox(label="Question:")],
                         outputs =gr.outputs.Textbox(label="Chatbot Response"),
                         examples = examples,
                        )

# Run the interface
interface.launch(enable_queue = True)