File size: 15,965 Bytes
12d891e
8f2ad06
c8ff64a
5a28160
d3a0859
f6250a9
 
 
 
 
 
 
 
 
 
 
ae1d88c
73d7e50
108ee46
 
 
 
ae8729e
b160f83
 
 
 
 
 
 
5a94d35
f6250a9
 
 
 
 
 
 
 
73d7e50
f6250a9
3c5e53e
f6250a9
3591534
de18cf7
3591534
 
884e5c5
 
f6250a9
ae8729e
 
d3a0859
 
ae8729e
b160f83
ae8729e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d3a0859
ae8729e
 
 
 
 
 
 
 
 
1b81bef
 
 
ae8729e
 
 
 
 
d3a0859
f6250a9
c8ff64a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5a94d35
f6250a9
884e5c5
b06fd67
 
 
 
 
 
 
 
 
49d6825
 
7350525
 
e228da0
7350525
 
49d6825
 
 
6b3cf69
ae8729e
b06fd67
 
 
 
 
 
b160f83
 
f42bbe4
b06fd67
 
 
 
 
 
 
e228da0
957dbba
 
5a28160
3465dff
 
 
 
659d932
 
 
 
 
 
 
3465dff
 
9eb733f
 
 
 
 
 
3465dff
b06fd67
 
f42bbe4
f6250a9
b06fd67
 
 
 
 
 
 
 
c8ff64a
 
b06fd67
 
 
 
 
 
 
f6250a9
b06fd67
 
 
f42bbe4
b06fd67
 
 
f42bbe4
b06fd67
f26adcb
b06fd67
 
 
 
 
 
 
b160f83
f6250a9
b06fd67
 
 
f6250a9
884e5c5
f6250a9
 
884e5c5
48235eb
5ea80a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b160f83
5ea80a9
b160f83
5ea80a9
f42bbe4
5ea80a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82aecc1
 
 
 
 
 
5ea80a9
 
 
4ff3a2e
 
82aecc1
 
 
 
5ea80a9
 
 
b160f83
5ea80a9
 
 
 
 
 
 
 
 
c8ff64a
 
5ea80a9
 
 
 
 
 
 
 
 
 
 
b160f83
5ea80a9
 
 
b160f83
5ea80a9
 
 
 
 
 
 
 
 
b160f83
5ea80a9
 
 
 
 
 
 
 
884e5c5
 
1b661bd
884e5c5
 
 
1b661bd
48c275c
1b661bd
884e5c5
b06fd67
1b661bd
48c275c
1b661bd
48c275c
1b661bd
 
48c275c
f6250a9
c8ff64a
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
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
import streamlit as st
from PIL import Image
import random
import time
import streamlit_analytics
from dotenv import load_dotenv
import pickle
from huggingface_hub import Repository
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
import os

import pandas as pd
import pydeck as pdk
from urllib.error import URLError

# Initialize session state variables
if 'chat_history_page1' not in st.session_state:
    st.session_state['chat_history_page1'] = []

if 'chat_history_page2' not in st.session_state:
    st.session_state['chat_history_page2'] = []



# Step 1: Clone the Dataset Repository
repo = Repository(
    local_dir="Private_Book",  # Local directory to clone the repository
    repo_type="dataset",  # Specify that this is a dataset repository
    clone_from="Anne31415/Private_Book",  # Replace with your repository URL
    token=os.environ["HUB_TOKEN"]  # Use the secret token to authenticate
)
repo.git_pull()  # Pull the latest changes (if any)

# Step 2: Load the PDF File
pdf_path = "Private_Book/141123_Kombi.pdf"  # Replace with your PDF file path

# Step 2: Load the PDF File
pdf_path2 = "Private_Book/Deutsche_Kodierrichtlinien_23.pdf"  # Replace with your PDF file path


api_key = os.getenv("OPENAI_API_KEY")
# Retrieve the API key from st.secrets



# Updated caching mechanism using st.cache_data
@st.cache_data(persist="disk")  # Using persist="disk" to save cache across sessions
def load_vector_store(file_path, store_name, force_reload=False):

        # Check if we need to force reload the vector store (e.g., when the PDF changes)
        if force_reload or not os.path.exists(f"{store_name}.pkl"):
            text_splitter = RecursiveCharacterTextSplitter(
                chunk_size=1000,
                chunk_overlap=200,
                length_function=len
            )
            
            text = load_pdf_text(file_path)
            chunks = text_splitter.split_text(text=text)
            
            embeddings = OpenAIEmbeddings()
            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
            with open(f"{store_name}.pkl", "wb") as f:
                pickle.dump(VectorStore, f)
        else:
            with open(f"{store_name}.pkl", "rb") as f:
                VectorStore = pickle.load(f)
    
        return VectorStore

# Utility function to load text from a PDF
def load_pdf_text(file_path):
    pdf_reader = PdfReader(file_path)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text() or ""  # Add fallback for pages where text extraction fails
    return text

def load_chatbot():
    #return load_qa_chain(llm=OpenAI(), chain_type="stuff")
    return load_qa_chain(llm=OpenAI(model_name="gpt-3.5-turbo-instruct"), chain_type="stuff")


def display_chat_history(chat_history):
    for chat in chat_history:
        background_color = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
        st.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)


def handle_no_answer(response):
    no_answer_phrases = [
        "ich weiß es nicht",
        "ich weiß nicht",
        "ich bin mir nicht sicher",
        "es wird nicht erwähnt",
        "Leider kann ich diese Frage nicht beantworten",
        "kann ich diese Frage nicht beantworten",
        "ich kann diese Frage nicht beantworten",
        "ich kann diese Frage leider nicht beantworten",
        "keine information",
        "das ist unklar",
        "da habe ich keine antwort",
        "das kann ich nicht beantworten",
        "i don't know",
        "i am not sure",
        "it is not mentioned",
        "no information",
        "that is unclear",
        "i have no answer",
        "i cannot answer that",
        "unable to provide an answer",
        "not enough context",
    ]

    alternative_responses = [
        "Hmm, das ist eine knifflige Frage. Lass uns das gemeinsam erkunden. Kannst du mehr Details geben?",
        "Interessante Frage! Ich bin mir nicht sicher, aber wir können es herausfinden. Hast du weitere Informationen?",
        "Das ist eine gute Frage. Ich habe momentan keine Antwort darauf, aber vielleicht kannst du sie anders formulieren?",
        "Da bin ich überfragt. Kannst du die Frage anders stellen oder mir mehr Kontext geben?",
        "Ich stehe hier etwas auf dem Schlauch. Gibt es noch andere Aspekte der Frage, die wir betrachten könnten?",
        # Add more alternative responses as needed
    ]

    # Check if response matches any phrase in no_answer_phrases
    if any(phrase in response.lower() for phrase in no_answer_phrases):
        return random.choice(alternative_responses)  # Randomly select a response
    return response




def page1():
    try:
        hide_streamlit_style = """
                <style>
                #MainMenu {visibility: hidden;}
                footer {visibility: hidden;}
                </style>
                """
        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
    
         # Create columns for layout
        col1, col2 = st.columns([3, 1])  # Adjust the ratio to your liking

        with col1:
            st.title("Welcome to BinDocs AI!")

        with col2:
            # Load and display the image in the right column, which will be the top-right corner of the page
            image = Image.open('BinDoc Logo (Quadratisch).png')
            st.image(image, use_column_width='always')

 
        # Start tracking user interactions
        with streamlit_analytics.track():
            if not os.path.exists(pdf_path):
                st.error("File not found. Please check the file path.")
                return
    
            VectorStore = load_vector_store(pdf_path, "vector_store_page1", force_reload=False)

            display_chat_history(st.session_state['chat_history_page1'])
    
            st.write("<!-- Start Spacer -->", unsafe_allow_html=True)
            st.write("<div style='flex: 1;'></div>", unsafe_allow_html=True)
            st.write("<!-- End Spacer -->", unsafe_allow_html=True)
    
            new_messages_placeholder = st.empty()
    
            query = st.text_input("Geben Sie hier Ihre Frage ein / Enter your question here:")

            add_vertical_space(2)  # Adjust as per the desired spacing
            
            # Create two columns for the buttons
            col1, col2 = st.columns(2)
            
            with col1:
                if st.button("Was kann ich mit dem Prognose-Analyse-Tool machen?"):
                    query = "Was kann ich mit dem Prognose-Analyse-Tool machen?"
                if st.button("Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"):
                    query = "Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"
                if st.button("Ich habe mein Meta-Password vergessen, wie kann ich es zurücksetzen?"):
                    query = "Ich habe mein Meta-Password vergessen, wie kann ich es zurücksetzen?"

            
            with col2:
                if st.button("Dies ist eine reine Test Frage, welche aber eine ausreichende Länge hat."):
                    query = "Dies ist eine reine Test Frage, welche aber eine ausreichende Länge hat."
                if st.button("Was sagt mir denn generell die wundervolle Bevölkerungsentwicklung?"):
                    query = "Was sagt mir denn generell die wundervolle Bevölkerungsentwicklung?"
                if st.button("Ob ich hier wohl viel schreibe, dass die Fragen vom Layout her passen?"):
                    query = "Ob ich hier wohl viel schreibe, dass die Fragen vom Layout her passen?"

        
            if query:
                st.session_state['chat_history_page1'].append(("User", query, "new"))

                # Start timing
                start_time = time.time()
                
                with st.spinner('Bot is thinking...'):
                    chain = load_chatbot()
                    docs = VectorStore.similarity_search(query=query, k=3)
                    with get_openai_callback() as cb:
                        response = chain.run(input_documents=docs, question=query)
                        response = handle_no_answer(response)  # Process the response through the new function


                        
                # Stop timing
                end_time = time.time()
                
                # Calculate duration
                duration = end_time - start_time

                # You can use Streamlit's text function to display the timing
                st.text(f"Response time: {duration:.2f} seconds")
    
                st.session_state['chat_history_page1'].append(("Bot", response, "new"))
    
    
                # Display new messages at the bottom
                new_messages = st.session_state['chat_history_page1'][-2:]
                for chat in new_messages:
                    background_color = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
                    new_messages_placeholder.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
    
    
                # Clear the input field after the query is made
                query = ""
    
            # Mark all messages as old after displaying
            st.session_state['chat_history_page1'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history_page1']]

    except Exception as e:
        st.error(f"Upsi, an unexpected error occurred: {e}")
        # Optionally log the exception details to a file or error tracking service




def page2():
    try:
        hide_streamlit_style = """
                <style>
                #MainMenu {visibility: hidden;}
                footer {visibility: hidden;}
                </style>
                """
        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
    
         # Create columns for layout
        col1, col2 = st.columns([3, 1])  # Adjust the ratio to your liking

        with col1:
            st.title("Kodieren statt Frustrieren!")

        with col2:
            # Load and display the image in the right column, which will be the top-right corner of the page
            image = Image.open('BinDoc Logo (Quadratisch).png')
            st.image(image, use_column_width='always')

 
        # Start tracking user interactions
        with streamlit_analytics.track():
            
            if not os.path.exists(pdf_path2):
                st.error("File not found. Please check the file path.")
                return
    
            VectorStore = load_vector_store(pdf_path2, "vector_store_page2", force_reload=False)
    

    
            display_chat_history(st.session_state['chat_history_page2'])
    
            st.write("<!-- Start Spacer -->", unsafe_allow_html=True)
            st.write("<div style='flex: 1;'></div>", unsafe_allow_html=True)
            st.write("<!-- End Spacer -->", unsafe_allow_html=True)
    
            new_messages_placeholder = st.empty()
    
            query = st.text_input("Ask questions about your PDF file (in any preferred language):")

            add_vertical_space(2)  # Adjust as per the desired spacing
            
            # Create two columns for the buttons
            col1, col2 = st.columns(2)
            
            with col1:
                if st.button("Wann kodiere ich etwas als Hauptdiagnose und wann als Nebendiagnose?"):
                    query = "Wann kodiere ich etwas als Hauptdiagnose und wann als Nebendiagnose?"
                if st.button("Ein Patient wird mit Aszites bei bekannter Leberzirrhose stationär aufgenommen. Es wird nur der Aszites durch eine Punktion behandelt.Wie kodiere ich das?"):
                    query = ("Ein Patient wird mit Aszites bei bekannter Leberzirrhose stationär aufgenommen. Es wird nur der Aszites durch eine Punktion behandelt.Wie kodiere ich das?")
                if st.button("Hauptdiagnose: Hirntumor wie kodiere ich das?"):
                    query = "Hauptdiagnose: Hirntumor wie kodiere ich das?"

            
            with col2:
                if st.button("Welche Prozeduren werden normalerweise nicht verschlüsselt?"):
                    query = "Welche Prozeduren werden normalerweise nicht verschlüsselt?"
                if st.button("Was muss ich bei der Kodierung der Folgezusänden von Krankheiten beachten?"):
                    query = "Was muss ich bei der Kodierung der Folgezusänden von Krankheiten beachten?"
                if st.button("Was mache ich bei einer Verdachtsdiagnose, wenn mein Patien nach Hause entlassen wird?"):
                    query = "Was mache ich bei einer Verdachtsdiagnose, wenn mein Patien nach Hause entlassen wird?"

        
            if query:
                st.session_state['chat_history_page2'].append(("User", query, "new"))

                # Start timing
                start_time = time.time()
                
                with st.spinner('Bot is thinking...'):
                    chain = load_chatbot()
                    docs = VectorStore.similarity_search(query=query, k=3)
                    with get_openai_callback() as cb:
                        response = chain.run(input_documents=docs, question=query)
                        response = handle_no_answer(response)  # Process the response through the new function


                        
                # Stop timing
                end_time = time.time()
                
                # Calculate duration
                duration = end_time - start_time

                # You can use Streamlit's text function to display the timing
                st.text(f"Response time: {duration:.2f} seconds")
    
                st.session_state['chat_history_page2'].append(("Bot", response, "new"))
    
    
                # Display new messages at the bottom
                new_messages = st.session_state['chat_history_page2'][-2:]
                for chat in new_messages:
                    background_color = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
                    new_messages_placeholder.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
    
    
                # Clear the input field after the query is made
                query = ""
    
            # Mark all messages as old after displaying
            st.session_state['chat_history_page2'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history_page2']]

    except Exception as e:
        st.error(f"Upsi, an unexpected error occurred: {e}")
        # Optionally log the exception details to a file or error tracking service





def main():
    # Sidebar content
    with st.sidebar:
        st.title('BinDoc GmbH')
        st.markdown("Experience revolutionary interaction with BinDocs Chat App, leveraging state-of-the-art AI technology.")
        add_vertical_space(1)
        page = st.sidebar.selectbox("Choose a page", ["Document Analysis Bot", "Coding Assistance Bot"])
        add_vertical_space(1)
        st.write('Made with ❤️ by BinDoc GmbH')

    # Main area content based on page selection
    if page == "Document Analysis Bot":
        page1()
    elif page == "Coding Assistance Bot":
        page2()


if __name__ == "__main__":
    main()