File size: 5,534 Bytes
7bb34c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
165
166
167
168
169
##############################################################
#   PDF Chat
#
#   Mike Pastor  February 2024


import streamlit as st
from dotenv import load_dotenv

from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter

from InstructorEmbedding import INSTRUCTOR
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

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

#  Chunk size and overlap must not exceed the models capacity!
#
def get_text_chunks(text):
    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=800,    #  1000
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks


def get_vectorstore(text_chunks):
    # embeddings = OpenAIEmbeddings()

    #  pip install InstructorEmbedding
    #  pip install sentence-transformers==2.2.2
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")

    #  from InstructorEmbedding import INSTRUCTOR
    # model = INSTRUCTOR('hkunlp/instructor-xl')
    # sentence = "3D ActionSLAM: wearable person tracking in multi-floor environments"
    # instruction = "Represent the Science title:"
    # embeddings = model.encode([[instruction, sentence]])

    # embeddings = model.encode(text_chunks)
    print('have Embeddings:   ')

    # text_chunks="this is a test"
    #   FAISS,  Chroma and other vector databases
    #
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    print('FAISS succeeds:   ')

    return vectorstore

def get_conversation_chain(vectorstore):
    # llm = ChatOpenAI()
    #  llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
    #  google/bigbird-roberta-base     facebook/bart-large
    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=vectorstore.as_retriever(),
        memory=memory,
    )
    return conversation_chain

def handle_userinput(user_question):

    response = st.session_state.conversation({'question': user_question})
    # response = st.session_state.conversation({'summarization': user_question})
    st.session_state.chat_history = response['chat_history']


    # st.empty()

    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="MLP Chat with multiple 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("Mike's PDF Chat :books:")

    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    # st.write( user_template, unsafe_allow_html=True)
    # st.write(user_template.replace( "{{MSG}}", "Hello robot!"), unsafe_allow_html=True)
    # st.write(bot_template.replace( "{{MSG}}", "Hello human!"), unsafe_allow_html=True)


    with st.sidebar:

        st.subheader("Your documents")
        pdf_docs = st.file_uploader(
            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)

        # Upon button press
        if st.button("Process these files"):
            with st.spinner("Processing..."):

                #################################################################
                #  Track the overall time for file processing into Vectors
                # #
                from datetime import datetime
                global_now = datetime.now()
                global_current_time = global_now.strftime("%H:%M:%S")
                st.write("Vectorizing Files - Current Time =", global_current_time)

                # get pdf text
                raw_text = get_pdf_text(pdf_docs)
                #  st.write(raw_text)

                # # get the text chunks
                text_chunks = get_text_chunks(raw_text)
                # st.write(text_chunks)

                # # create vector store
                vectorstore = get_vectorstore(text_chunks)

                # # create conversation chain
                st.session_state.conversation = get_conversation_chain(vectorstore)

                # Mission Complete!
                global_later = datetime.now()
                st.write("Files Vectorized - Total EXECUTION Time =",
                         (global_later - global_now), global_later)


if __name__ == '__main__':
    main()