File size: 9,591 Bytes
7b38ee1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b850f8
 
 
 
 
 
7b38ee1
 
7b850f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b38ee1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b850f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b38ee1
7b850f8
 
 
 
 
 
7b38ee1
 
7b850f8
7b38ee1
7b850f8
 
 
 
 
7b38ee1
7b850f8
7b38ee1
 
 
 
 
 
 
 
 
7b850f8
7b38ee1
7b850f8
 
7b38ee1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b850f8
 
7b38ee1
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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306

# import os
# import logging
# from dotenv import load_dotenv
# import streamlit as st
# from PyPDF2 import PdfReader
# from langchain.text_splitter import CharacterTextSplitter
# # from langchain.embeddings import HuggingFaceInstructEmbeddings
# from langchain_cohere import CohereEmbeddings
# from langchain.vectorstores import FAISS
# from langchain.memory import ConversationBufferMemory
# from langchain.chains import ConversationalRetrievalChain
# # from langchain.llms import Ollama
# from langchain_groq import ChatGroq

# # Load environment variables
# load_dotenv()

# # Set up logging
# logging.basicConfig(
#     level=logging.INFO,
#     format='%(asctime)s - %(levelname)s - %(message)s'
# )

# # Function to extract text from PDF files
# 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

# # Function to split the extracted text into chunks
# 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

# # Function to create a FAISS vectorstore
# # def get_vectorstore(text_chunks):
# #     embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
# #     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
# #     return vectorstore

# def get_vectorstore(text_chunks):
#     cohere_api_key = os.getenv("COHERE_API_KEY")
#     embeddings = CohereEmbeddings(model="embed-english-v3.0", cohere_api_key=cohere_api_key)
#     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
#     return vectorstore

# # Function to set up the conversational retrieval chain
# def get_conversation_chain(vectorstore):
#     try:
#         # llm = Ollama(model="llama3.2:1b")
#         llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0.5)
#         memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
        
#         conversation_chain = ConversationalRetrievalChain.from_llm(
#             llm=llm,
#             retriever=vectorstore.as_retriever(),
#             memory=memory
#         )
        
#         logging.info("Conversation chain created successfully.")
#         return conversation_chain
#     except Exception as e:
#         logging.error(f"Error creating conversation chain: {e}")
#         st.error("An error occurred while setting up the conversation chain.")

# # Handle user input
# def handle_userinput(user_question):
#     if st.session_state.conversation is not None:
#         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(f"*User:* {message.content}")
#             else:
#                 st.write(f"*Bot:* {message.content}")
#     else:
#         st.warning("Please process the documents first.")

# # Main function to run the Streamlit app
# def main():
#     load_dotenv()
#     st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")

#     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 multiple PDFs :books:")
#     user_question = st.text_input("Ask a question about your documents:")
#     if user_question:
#         handle_userinput(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"):
#             with st.spinner("Processing..."):
#                 raw_text = get_pdf_text(pdf_docs)
#                 text_chunks = get_text_chunks(raw_text)
#                 vectorstore = get_vectorstore(text_chunks)
#                 st.session_state.conversation = get_conversation_chain(vectorstore)

# if __name__ == '__main__':
#     main()




































import os
import logging
from dotenv import load_dotenv
import streamlit as st
from PyPDF2 import PdfReader
from docx import Document  # Import for handling Word files
import io  # Import for handling byte streams
from langchain.text_splitter import CharacterTextSplitter
from langchain_cohere import CohereEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_groq import ChatGroq

# Load environment variables
load_dotenv()

# Set up logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)

# Function to extract text from PDF files
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

# Function to extract text from Word files
def get_word_text(word_docs):
    text = ""
    for word in word_docs:
        doc = Document(io.BytesIO(word.read()))  # Read the Word document from bytes
        for para in doc.paragraphs:
            text += para.text + "\n"  # Append each paragraph followed by a newline
    return text

# Function to extract text from TXT files
def get_txt_text(txt_docs):
    text = ""
    for txt in txt_docs:
        text += txt.read().decode("utf-8") + "\n"  # Read and decode the text file content
    return text

# Function to split the extracted text into chunks
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):
    cohere_api_key = os.getenv("COHERE_API_KEY")
    embeddings = CohereEmbeddings(model="embed-english-v3.0", cohere_api_key=cohere_api_key)
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

# Function to set up the conversational retrieval chain
def get_conversation_chain(vectorstore):
    try:
        llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0.5)
        memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
        
        conversation_chain = ConversationalRetrievalChain.from_llm(
            llm=llm,
            retriever=vectorstore.as_retriever(),
            memory=memory
        )
        
        logging.info("Conversation chain created successfully.")
        return conversation_chain
    except Exception as e:
        logging.error(f"Error creating conversation chain: {e}")
        st.error("An error occurred while setting up the conversation chain.")

# Handle user input
def handle_userinput(user_question):
    if st.session_state.conversation is not None:
        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(f"*User:* {message.content}")
            else:
                st.write(f"*Bot:* {message.content}")
    else:
        st.warning("Please process the documents first.")

# Main function to run the Streamlit app
def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple documents", page_icon=":books:")

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

    with st.sidebar:
        st.subheader("Your documents")
        
        pdf_docs = st.file_uploader(
            "Upload your PDFs here", accept_multiple_files=True, type=["pdf"]
        )
        
        word_docs = st.file_uploader(
            "Upload your Word documents here", accept_multiple_files=True, type=["docx"]
        )
        
        txt_docs = st.file_uploader(
            "Upload your TXT files here", accept_multiple_files=True, type=["txt"]
        )
        
        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = ""
                
                if pdf_docs:
                    raw_text += get_pdf_text(pdf_docs)
                
                if word_docs:
                    raw_text += get_word_text(word_docs)
                
                if txt_docs:
                    raw_text += get_txt_text(txt_docs)
                
                if raw_text:  # Only process if there is any raw text extracted.
                    text_chunks = get_text_chunks(raw_text)
                    vectorstore = get_vectorstore(text_chunks)
                    st.session_state.conversation = get_conversation_chain(vectorstore)
                else:
                    st.warning("No documents were uploaded or processed.")

if __name__ == '__main__':
    main()