File size: 3,580 Bytes
015bbbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
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

def get_pdf_text(pdf_files):
    
    text = ""
    for pdf_file in pdf_files:
        reader = PdfReader(pdf_file)
        for page in reader.pages:
            text += page.extract_text()
    return text

def get_chunk_text(text):
    
    text_splitter = CharacterTextSplitter(
    separator = "\n",
    chunk_size = 1000,
    chunk_overlap = 200,
    length_function = len
    )

    chunks = text_splitter.split_text(text)

    return chunks


def get_vector_store(text_chunks):
    
    # For OpenAI Embeddings
    
    embeddings = OpenAIEmbeddings()
    
    # For Huggingface Embeddings

    # embeddings = HuggingFaceInstructEmbeddings(model_name = "hkunlp/instructor-xl")

    vectorstore = FAISS.from_texts(texts = text_chunks, embedding = embeddings)
    
    return vectorstore

def get_conversation_chain(vector_store):
    
    # OpenAI Model

    llm = ChatOpenAI()

    # HuggingFace Model

    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})

    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)

    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm = llm,
        retriever = vector_store.as_retriever(),
        memory = memory
    )

    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:')
    question = st.text_input("Ask anything to your PDF: ")

    if question:
        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("Processing your PDFs..."):

                # Get PDF Text
                raw_text = get_pdf_text(pdf_files)

                # Get Text Chunks
                text_chunks = get_chunk_text(raw_text)
                

                # Create Vector Store
                
                vector_store = get_vector_store(text_chunks)
                st.write("DONE")

                # Create conversation chain

                st.session_state.conversation =  get_conversation_chain(vector_store)


if __name__ == '__main__':
    main()