moveworkshackathonchatbot/app2.py at main · ViditJain123/moveworkshackathonchatbot · GitHub

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
import os
import pickle
import streamlit as st
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template
from langchain.llms import HuggingFaceHub

# os.environ['HUGGINGFACEHUB_API_TOKEN'] = "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"
os.environ["OPENAI_API_KEY"] = "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"

# def get_pdf_text(pdf_docs):
#     text = ""
#     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 = OpenAIEmbeddings()
#     # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
#     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
#     return vectorstore

with open("C:/Users/vidit/OneDrive/Desktop/Embedding_store/faiss_instructEmbeddings.pkl", "rb") as f:
    vectorstore = pickle.load(f)


def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    # llm = HuggingFaceHub(repo_id="nomic-ai/gpt4all-j", model_kwargs={"temperature":0.7, "max_length":512})

    memory = ConversationBufferMemory(
        memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_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():
    # load_dotenv()
    st.set_page_config(page_title="Chat with your website",
                       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 website :books:")
    user_question = st.text_input("Ask a question about your website:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your website")
        if st.button("Process"):
            with st.spinner("Processing"):
                # create conversation chain
                st.session_state.conversation = get_conversation_chain(
                    vectorstore)


if __name__ == '__main__':
    main()