app.py

import streamlit as st
from langchain import OpenAI, PromptTemplate, LLMChain
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains.mapreduce import MapReduceChain
from langchain.prompts import PromptTemplate
from langchain.chat_models import AzureChatOpenAI
from langchain.chains.summarize import load_summarize_chain
from langchain.chains import AnalyzeDocumentChain
from PyPDF2 import PdfReader
from langchain.document_loaders import TextLoader
from langchain.indexes import VectorstoreIndexCreator
from langchain.document_loaders import PyPDFLoader



import os
os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_VERSION"] = "2023-05-15"
os.environ["OPENAI_API_BASE"] = "https://cog-mnjbf5r4o6b3e.openai.azure.com/"
os.environ["OPENAI_API_KEY"] = "957f7d98b47a467a98a786f7ca903112"

llm = AzureChatOpenAI(
                       deployment_name="chat",
            openai_api_version="2023-03-15-preview")



st.title("Contract Management System")

# description text
st.write("""Hello! I'm an Al chatbot specifically created to assist vou with any procurement-related questions you may have. My range of capabilities includes providing information on contract expiry dates payment terms, and other relevant details. 

Feel free to ask me anything you need help with!
To get started, just provide me with the contract number and let me know what specitic details you're interested in. Additionally, tee tree to ask me any general questions you may have regardinc procurement. I'm here to assist vou in any way can 😊""")

# pdf file upload
pdf_file = st.file_uploader("Upload file", type=["pdf"])


def extract_text_from_pdf():
    reader = PdfReader(pdf_file)
    # get all pages text
    text = [reader.pages[i].extract_text() for i in range(len(reader.pages))]
    # join all pages text
    text = " ".join(text)
    return text



if st.button("Summerize Contract"):
    with st.spinner("Extracting Text..."):
        summary_chain = load_summarize_chain(llm, chain_type="map_reduce")
        summarize_document_chain = AnalyzeDocumentChain(combine_docs_chain=summary_chain, verbose=True)
        text = extract_text_from_pdf()
    with st.spinner("Summarizing..."):
        result = summarize_document_chain.run(text)
    st.write(result)