File size: 6,448 Bytes
6ee1ffa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3651b15
6ee1ffa
 
 
 
 
3651b15
6ee1ffa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
import os
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceInstructEmbeddings, OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template
from langchain.llms import HuggingFaceHub
from langchain.chat_models import ChatOpenAI

load_dotenv()

def update_api_token(model_choice, api_token):
    dotenv_file = '.env'
    if model_choice == "OpenAI":
        with open(dotenv_file, 'r') as file:
            lines = file.readlines()
        with open(dotenv_file, 'w') as file:
            for line in lines:
                if line.startswith("OPENAI_API_KEY"):
                    file.write(f"OPENAI_API_KEY={api_token}\n")
                else:
                    file.write(line)
        os.environ['OPENAI_API_KEY'] = api_token
    elif model_choice == "HuggingFace":
        with open(dotenv_file, 'r') as file:
            lines = file.readlines()
        with open(dotenv_file, 'w') as file:
            for line in lines:
                if line.startswith("HUGGINGFACEHUB_API_TOKEN"):
                    file.write(f"HUGGINGFACEHUB_API_TOKEN={api_token}\n")
                else:
                    file.write(line)
        os.environ['HUGGINGFACEHUB_API_TOKEN'] = api_token

def validate_token(model_choice):
    if 'validation_done' not in st.session_state:
        try:
            if model_choice == "OpenAI":
                st.session_state.EMBEDDINGS = OpenAIEmbeddings()
                st.session_state.LLM = ChatOpenAI()
            else:
                st.session_state.EMBEDDINGS = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
                st.session_state.LLM = HuggingFaceHub(repo_id="google/flan-t5-base", model_kwargs={"temperature": 0.5, "max_length": 512})
            st.session_state.validation_done = True
            return True
        except Exception as e:
            return False
    else:
        return True

def get_pdf_text(pdf_docs):
    text = ""
    if pdf_docs:
        for pdf in pdf_docs:
            pdf_reader = PdfReader(pdf)
            for page in pdf_reader.pages:
                text += page.extract_text()
    return text

def get_text_chunks(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_vectorstore(text_chunks, embeddings):
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(llm, embeddings, vectorstore=None):
    if llm is None or embeddings is None:
        raise ValueError("LLM or EMBEDDINGS is not initialized.")
    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)

    if vectorstore is None:
        dummy_text = [""]
        vectorstore = FAISS.from_texts(texts=dummy_text, embedding=embeddings)

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

def handle_userinput(user_question):
    response = st.session_state.conversation({'question': user_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():
    global LLM, EMBEDDINGS
    LLM = None
    EMBEDDINGS = None

    st.set_page_config(page_title="MultiDoc_ChatBot", page_icon=":mag:")
    st.write(css, unsafe_allow_html=True)

    st.header("Chat with multiple PDFs :mag:")

    # User options for LLM and Embeddings
    model_choice = st.radio("Choose your model source", ("OpenAI", "HuggingFace"))
    api_token = st.text_input("Enter your API token", type="password")

    if st.button("Save API Token"):
        update_api_token(model_choice, api_token)
        with st.spinner("Validating API Token..."):
            if validate_token(model_choice):
                st.success(f"{model_choice} API token saved and model uploaded!")
            else:
                st.error("Invalid API token. Please try again.")
            
            print("LLM : ", st.session_state.LLM)
            print("EMBEDDINGS : ", st.session_state.EMBEDDINGS)

    if 'LLM' in st.session_state:
        LLM = st.session_state.LLM
    if 'EMBEDDINGS' in st.session_state:
        EMBEDDINGS = st.session_state.EMBEDDINGS

    if "user_question" not in st.session_state:
        st.session_state.user_question = ""

    user_question = st.text_input("Ask a question about your documents:", key="question_input", value=st.session_state.user_question)
    submit_button = st.button("Submit")

    if submit_button and user_question:
        if LLM is None or EMBEDDINGS is None:
            st.error("LLM or EMBEDDINGS is not initialized.")
        else:
            if "conversation" not in st.session_state:
                st.session_state.conversation = get_conversation_chain(LLM, EMBEDDINGS)
            if "chat_history" not in st.session_state:
                st.session_state.chat_history = []
            handle_userinput(user_question)
            st.session_state.user_question = ""

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            if LLM is None or EMBEDDINGS is None:
                st.error("LLM or EMBEDDINGS is not initialized.")
            else:
                with st.spinner("Processing"):
                    raw_text = get_pdf_text(pdf_docs)
                    text_chunks = get_text_chunks(raw_text)
                    vectorstore = get_vectorstore(text_chunks, EMBEDDINGS)
                    st.session_state.conversation = get_conversation_chain(LLM, EMBEDDINGS, vectorstore=vectorstore)

if __name__ == '__main__':
    main()