app.py

import streamlit as st
import openai
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.embeddings import HuggingFaceEmbeddings, SentenceTransformerEmbeddings
from langchain import HuggingFaceHub
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from htmlTemplates import bot_template, user_template, css
from transformers import pipeline

import pinecone
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Pinecone
from langchain import PromptTemplate
from langchain.chains.question_answering import load_qa_chain
#from langchain.chains.summarize import load_summarize_chain
import nltk
import sys
import os
from dotenv import load_dotenv
load_dotenv()

HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
repo_id=os.getenv("repo_id")

OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
openai_api_key = os.environ.get('openai_api_key')
embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)

#*******************************************#Pinecone Account: b***liu@gmail.com
#pinecone_index_name=os.environ.get('pinecone_index_name')
#pinecone_namespace=os.environ.get('pinecone_namespace')
#pinecone_api_key=os.environ.get('pinecone_api_key')
#pinecone_environment=os.environ.get('pinecone_environment')
#pinecone.init(      
#	api_key=pinecone_api_key,      
#	environment=pinecone_environment      
#)      
#index = pinecone.Index(pinecone_index_name)
#loaded_v_db_500_wt_metadata = Pinecone.from_existing_index(index_name=pinecone_index_name, embedding=embeddings, namespace=pinecone_namespace)
#*******************************************#

#*******************************************#Pinecone Account: ij***.l**@hotmail.com
pinecone_index_name_1=os.environ.get('pinecone_index_name_1')
#pinecone_namespace_1=os.environ.get('pinecone_namespace_1') #no namespace under this Pinecone account
pinecone_api_key_1=os.environ.get('pinecone_api_key_1')
pinecone_environment_1=os.environ.get('pinecone_environment_1')
pinecone.init(      
	api_key=pinecone_api_key_1,      
	environment=pinecone_environment_1      
)      
index = pinecone.Index(pinecone_index_name_1)
#vectorstore = Pinecone.from_existing_index(index_name=pinecone_index_name_1, embedding=embeddings)
#*******************************************#

hf_token = os.environ.get('HUGGINGFACEHUB_API_TOKEN')
HUGGINGFACEHUB_API_TOKEN = os.environ.get('HUGGINGFACEHUB_API_TOKEN')
huggingfacehub_api_token= os.environ.get('huggingfacehub_api_token')
repo_id = os.environ.get('repo_id')

def get_vector_store():   
    #vectorstore = FAISS.from_texts(texts = text_chunks, embedding = embeddings)
    vector_store = Pinecone.from_existing_index(index_name=pinecone_index_name_1, embedding=embeddings)
    return vector_store

def get_conversation_chain(vector_store):   
    # OpenAI Model
    #llm = ChatOpenAI()
    #HuggingFace Model
    #llm = HuggingFaceHub(repo_id="google/flan-t5-xxl")
    #llm = HuggingFaceHub(repo_id="tiiuae/falcon-40b-instruct", model_kwargs={"temperature":0.5, "max_length":512}) #出现超时timed out错误
    #llm = HuggingFaceHub(repo_id="meta-llama/Llama-2-70b-hf", model_kwargs={"min_length":100, "max_length":1024,"temperature":0.1})
    #repo_id="HuggingFaceH4/starchat-beta"
    llm = HuggingFaceHub(repo_id=repo_id,
                         model_kwargs={"min_length":1024,
                                       #"max_new_tokens":5632, "do_sample":True,
                                       "max_new_tokens":3072, "do_sample":True,
                                       "temperature":0.1,
                                       "top_k":50,
                                       "top_p":0.95, "eos_token_id":49155}) 
    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm = llm,
        retriever = vector_store.as_retriever(),
        memory = memory
    )
    print("***Start of printing Conversation_Chain***")
    print(conversation_chain)
    print("***End of printing Conversation_Chain***")
    st.write("***Start of printing Conversation_Chain***")
    st.write(conversation_chain)
    st.write("***End of printing Conversation_Chain***")    
    return conversation_chain

def handle_user_input(question):
    response = st.session_state.conversation({'question':question})    
    st.session_state.chat_history = response['chat_history']
    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
            
def main():
    load_dotenv()
    st.set_page_config(page_title='Chat with Your own PDFs', page_icon=':books:')
    st.write(css, unsafe_allow_html=True)    
    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None
    st.header('Chat with Your own PDFs :books:')
    
    #if question:
    vector_store = get_vector_store()
    st.session_state.conversation =  get_conversation_chain(vector_store)
    question = st.text_input("Ask anything to your PDF: ")
    if question !="" and not question.strip().isspace() and not question == "" and not question.strip() == "" and not question.isspace():
        handle_user_input(question)  
#    with st.sidebar:
#        st.subheader("Upload your Documents Here: ")
#        pdf_files = st.file_uploader("Choose your PDF Files and Press OK", type=['pdf'], accept_multiple_files=True)
#        if st.button("OK"):
#            with st.spinner("Preparation under process..."):          
#                # Create Vector Store                
#                vector_store = get_vector_store()
#                st.write("DONE")
#                # Create conversation chain
#                st.session_state.conversation =  get_conversation_chain(vector_store)

if __name__ == '__main__':
    main()