File size: 11,761 Bytes
d31ac17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
464fb2b
 
d31ac17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
# # # import streamlit as st
# # # from dotenv import load_dotenv
# # # from PyPDF2 import PdfReader
# # # 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

# # # 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


# # # def get_conversation_chain(vectorstore):
# # #     llm = ChatOpenAI()
# # #     # 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})
# # #     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="Mental Health Support",
# # #                        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("Mental Health Support :brain:")
# # #     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"):
# # #                 # 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)
                


# # # if __name__ == '__main__':
# # #     main()
# # # import streamlit as st
# # # from dotenv import load_dotenv
# # # from PyPDF2 import PdfReader
# # # from langchain.text_splitter import CharacterTextSplitter
# # # from langchain.embeddings import OpenAIEmbeddings
# # # # from langchain.embeddings import 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
# # # # from streamlit_option_menu import option_menu
# # # import pyttsx3

# # # def get_pdf_text(pdf_paths):
# # #     text = ""
# # #     for pdf_path in pdf_paths:
# # #         with open(pdf_path, 'rb') as pdf_file:
# # #             pdf_reader = PdfReader(pdf_file)
# # #             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="nomic-ai/gpt4all-j")
# # #     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
# # #     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})
# # #     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)
            
# # #     engine = pyttsx3.init()
# # #     engine.say(response['answer'])
# # #     engine.runAndWait()

# # # def main():
# # #     load_dotenv()
# # #     st.set_page_config(page_title="Mental Health Support", page_icon=":brain:")
# # #     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("Mental Health Support :brain:")
# # #     pdf_paths = [
# # #         'C:/Users/sharm/Downloads/ask-multiple-pdfs-main/ask-multiple-pdfs-main/Chat_data.pdf',
# # #         'C:/Users/sharm/Downloads/ask-multiple-pdfs-main/ask-multiple-pdfs-main/class 10 history ch 3.pdf'
# # #     ]
    
    
# # #         # get pdf text
# # #     raw_text = get_pdf_text(pdf_paths)

# # #         # 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)

# # #     user_question = st.text_input("Your therapist is there for you!:")
# # #     if user_question and st.session_state.conversation:
# # #         handle_userinput(user_question)

# # # if __name__ == '__main__':
# # #     main()
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
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 langchain.llms import HuggingFaceHub
from htmlTemplates import css, bot_template, user_template
#from InstructorEmbedding import INSTRUCTOR
import tempfile
import ttsmms
import soundfile as sf
from streamlit.components.v1 import html

def get_pdf_text(pdf_paths):
    text = ""
    for pdf_path in pdf_paths:
        with open(pdf_path, 'rb') as pdf_file:
            pdf_reader = PdfReader(pdf_file)
            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-base")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    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)

    audio_path = tempfile.NamedTemporaryFile(delete=False, suffix=".wav").name
    tts = ttsmms.TTS("data/eng")  # Update with the correct path
    wav = tts.synthesis(response['answer'])
    sf.write(audio_path, wav["x"], wav["sampling_rate"])
    
    st.audio(audio_path, format="audio/wav", start_time=0, sample_rate=wav["sampling_rate"])

def main():
    load_dotenv()
    st.set_page_config(page_title="Mental Health Support", page_icon=":brain:")
    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("Mental Health Support :brain:")
    pdf_paths = [
        'Chat_data.pdf'
        
    ]
    
    raw_text = get_pdf_text(pdf_paths)
    text_chunks = get_text_chunks(raw_text)
    vectorstore = get_vectorstore(text_chunks)
    st.session_state.conversation = get_conversation_chain(vectorstore)

    user_question = st.text_input("Your therapist is there for you!:")
    if user_question and st.session_state.conversation:
        handle_userinput(user_question)

if __name__ == '__main__':
    main()
# my_js = """
# alert("Please don't forget to enter you daily details!!!");
# """

# # Wrapt the javascript as html code
# my_html = f"<script>{my_js}</script>"

# # Execute your app

# html(my_html)