import os
from langchain.chains import RetrievalQA
from langchain.llms import AzureOpenAI
from langchain.document_loaders import TextLoader
from langchain.document_loaders import PyPDFLoader
from langchain.indexes import VectorstoreIndexCreator
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.chains.question_answering import load_qa_chain
from langchain.llms import AzureOpenAI
from langchain.chains.question_answering import load_qa_chain
import streamlit as st
from PIL import Image
import time

image = Image.open('Wipro logo.png')
st.image(image)

st.title("Wipro impact | The inquisitive sustainability leader:  Learn some of the best practices in sustainability from success stories of leading companies.. ")


st.header("Welcome!. Today, What company's sustainability story is inspiring you ?.. ")


myurl = st.text_input("Give the URL to find a sustainability or annual report", "Type URL of any company PDF document here")

index = None

if st.button("Load this report "):
    loader1 = PyPDFLoader(myurl)
    langchainembeddings = OpenAIEmbeddings(deployment="textembedding", chunk_size=1)

index = VectorstoreIndexCreator(
        # split the documents into chunks
        text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0),
        # select which embeddings we want to use
        embedding=langchainembeddings,
        # use Chroma as the vectorestore to index and search embeddings
        vectorstore_cls=Chroma
    ).from_loaders([loader1])
    
st.write("loaded")





yourquestion = st.text_input('Ask your question on best practices', 'What is Wipro plans for Biodiversity in 2024?')
st.write('Your input is ', yourquestion)

aimethod = st.radio(
    "Choose a AI brain",
    ('GPT3', 'GPT3.5' ), index=1)


os.environ['OPENAI_API_TYPE'] = 'azure'
os.environ['OPENAI_API_VERSION'] = '2023-03-15-preview'

#llmgpt3 = AzureOpenAI(      deployment_name="testdavanci", model_name="text-davinci-003" )
llmchatgpt = AzureOpenAI(     deployment_name="esujnand", model_name="gpt-35-turbo" )

if st.button("Ask Best practices "):
  answer = index.query(llm=llmchatgpt, question=query, chain_type="map_reduce")
  st.write(answer)


aimethod = st.radio(
    "Choose a AI brain or document comprehension method",
    ('2 minutes AI method map_reduce', '4 minutes AI method refine' ), index=0)

mychain_type = "map_reduce"
if aimethod ==  '2 minutes AI method map_reduce':
  mychain_type = "map_reduce"
if aimethod ==  '4 minutes AI method refine':
  mychain_type = "refine"

 


loader1 = PyPDFLoader(url)


def history():
  mycount = 0 
  if 'count' not in st.session_state:
    st.session_state['count'] =  0
  else:
    mycount = st.session_state['count']

  if True:
    st.write(mycount)
    mycount = mycount + 1 
    st.session_state['count'] = mycount
    for i in range(mycount):
      mystatekeyindex = "element" + str(i)
      mystatekeyanswerindex = "elementANS" + str(i)
      if mystatekeyindex not in st.session_state:
        st.session_state[mystatekeyindex] =  yourquestion
        st.session_state[mystatekeyanswerindex] = answer
      if mystatekeyindex in st.session_state:
        with st.expander(st.session_state[mystatekeyindex]):
          st.write( st.session_state[mystatekeyanswerindex] )


def colorizedtext(acolor, astring):
  formattedcolor = ":" + acolor + "[" + astring +  "]"
  return formattedcolor

 

if st.button("Ask QA "):
  documents = loader1.load()
  answer = ""
  with st.spinner(" Finding answer for your question .... AI will get you answer in 2 more minutes... "  ):
    with st.expander( "Employing your choice of AI method ... " + aimethod + "..."):
      st.write(str(chain)[:700])
    st.write("AI is reading this [link](%s)" % url)    
    prgpgress = st.progress(0)
    st.subheader(colorizedtext("red", yourquestion))
    for i in range(100):
        time.sleep(0.9)
        prgpgress.progress(i+1)



    answer = chain.run(input_documents=documents, question=yourquestion)
  st.subheader(colorizedtext("blue", answer))
  history()