File size: 6,518 Bytes
ec9e166
 
 
621c159
ec9e166
 
 
 
 
 
 
 
5838c96
907eaa3
3e1c3a5
 
8e8ccf4
9c39b4d
8c29218
ec9e166
 
 
 
 
 
3e466e9
 
 
 
 
 
8c29218
ec9e166
52933e7
ec9e166
 
 
 
 
8c29218
c24dee1
ec9e166
 
 
 
 
 
 
 
 
 
8c29218
 
ec9e166
d815c47
75201e2
6b53f9c
52933e7
ec9e166
 
 
 
 
 
 
 
 
8c29218
ec9e166
 
 
 
 
7e3de88
 
 
 
ec9e166
d8dabbe
5838c96
 
7e3de88
9c39b4d
e5c0906
b0dd4a4
8f8e7b3
 
b0dd4a4
 
 
 
 
 
 
 
8f8e7b3
 
 
 
f0cd778
b0dd4a4
5b48ab1
2d3a987
 
 
 
 
989668b
2b48b3a
2d3a987
989668b
2d3a987
8f8e7b3
ec9e166
 
33ac479
ec9e166
 
 
9ff8dae
 
ec9e166
 
 
8c29218
ec9e166
 
 
 
 
8c29218
33ac479
7e3de88
a392478
7e3de88
446feac
 
 
03d0aa3
 
 
ec9e166
8c29218
ec9e166
aca1efc
f2c89bd
1ee0e49
681f3fb
1ee0e49
f2c89bd
ec9e166
be124ff
70dfddf
ec9e166
c0361e2
ec9e166
 
 
 
 
 
 
 
 
 
 
bc361ee
 
 
ec9e166
907eaa3
ec9e166
1d9366f
9f78fda
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
170
171
172
173
174
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 HuggingFaceBgeEmbeddings
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
from deep_translator import GoogleTranslator
import pandas as pd
# set this key as an environment variable
os.environ["HUGGINGFACEHUB_API_TOKEN"] = st.secrets['huggingface_token']
###########################################################################################

def get_pdf_text(pdf_docs : list) -> str:
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text
###########################################
def load_file(): 
    loader = TextLoader('d2.txt')
    documents = loader.load()
    return documents 
######################################
def get_text_chunks(text:str) ->list:
    text_splitter = CharacterTextSplitter(
        separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks


def get_vectorstore(text_chunks : list) -> FAISS:
    model = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
    encode_kwargs = {
        "normalize_embeddings": True
    }  # set True to compute cosine similarity
    embeddings = HuggingFaceBgeEmbeddings(
        model_name=model, encode_kwargs=encode_kwargs, model_kwargs={"device": "cpu"}
    )
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


def get_conversation_chain(vectorstore:FAISS) -> ConversationalRetrievalChain:
    # llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
    llm = HuggingFaceHub(
        repo_id="mistralai/Mistral-7B-Instruct-v0.2",
        #repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1"
        #repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF"
        model_kwargs={"temperature": 0.9, "max_length": 2048},
    )

    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:str):
    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:
            text2=message.content 
            translator = GoogleTranslator(source='english', target='persian')
            result = translator.translate(text2)
            st.write("سوال کاربر: "+result)
        else:
            text1=message.content 
            translator = GoogleTranslator(source='english', target='persian')
            result = translator.translate(text1)
            st.write("پاسخ ربات: "+result)

#############################################################################################################
def read_pdf_pr_en(pdf_file_path):
  from deep_translator import GoogleTranslator
  import PyPDF2
  # مسیر فایل PDF را تعیین کنید
  #pdf_file_path = '/content/d2en.pdf'
  # باز کردن فایل PDF
  with open(pdf_file_path, 'rb') as pdf_file:
    pdf_reader = PyPDF2.PdfReader(pdf_file)
    # خواندن محتوای صفحه‌ها
    full_text = ''
    for page in pdf_reader.pages:
        page_pdf=page.extract_text()
        translator = GoogleTranslator(source='persian', target='english')
        result = translator.translate(page_pdf)
        full_text +=result
    st.write(full_text)
    return(full_text)
#################################################################################################################
def get_pdf_text(pdf_docs): 
    text = "" 
    for pdf in pdf_docs: 
        pdf_reader = PdfReader(pdf) 
    for page in pdf_reader.pages: 
        txt_page=page.extract_text() 
        text += txt_page
    return text
        

################################33333333333333333333333333333333333333333333333333333333
def main():
    st.set_page_config(
        page_title="Chat Bot PDFs",
        page_icon=":books:",
    )

    #st.markdown("# Chat with a Bot")
    #st.markdown("This bot tries to answer questions about multiple PDFs. Let the processing of the PDF finish before adding your question. 🙏🏾")

    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 Bot PDFs :books:")
    user_question1 = st.text_input("Ask a question about your documents:")
    translator = GoogleTranslator(source='persian', target='english')
    user_question = translator.translate(user_question1)
    if st.button("Answer"):
            with st.spinner("Answering"):
              handle_userinput(user_question)
    if st.button("CLEAR"):
            with st.spinner("CLEARING"):
              st.cache_data.clear()

    
    with st.sidebar:
        import pandas as pd
        st.subheader("Your excel file")
        xls_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True,type=['csv'])
        if xls_docs is not None:
            df = pd.read_csv(xls_docs)
        
        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"):
            with st.spinner("Processing"):
                # get pdf text
                raw_text = get_pdf_text(pdf_docs)

                # get the text chunks
                text_chunks = get_text_chunks(raw_text)

                # create vector store
                vectorstore = get_vectorstore(text_chunks)

                # create conversation chain
                st.session_state.conversation = get_conversation_chain(vectorstore)
                
                #compelete build model
                st.write("compelete build model")


if __name__ == "__main__":
    main()