Spaces:
Running
Running
File size: 9,289 Bytes
12d891e 27dbdfd 7c95914 12d891e 7c95914 27dbdfd 7c95914 27dbdfd d796104 47f6195 32f1f35 a48e7a7 13c5f18 976f538 5f51ac1 744d5b3 4e0fb75 1110c74 902d85a 4e0fb75 1110c74 24ecc54 d2d9c5f a48e7a7 fa02bb5 5efe4f5 902d85a 5efe4f5 a48e7a7 0c906d3 830d649 1c10809 c2af936 5efe4f5 df5dc0d 1c10809 18c4abc 5efe4f5 a48e7a7 18c4abc 5751355 c960b96 24ecc54 3b9357b 744d5b3 24ecc54 744d5b3 5f51ac1 e05d529 5751355 12b43bf 902d85a a3fc68d 12b43bf 18c4abc a48e7a7 1110c74 a48e7a7 89ad1c6 bdde277 27dbdfd 3d69dee 1c10809 403a475 7c95914 12d891e 7c95914 12d891e 8a1f468 7c95914 2df9243 7c95914 8a1f468 a63f1b5 27dbdfd 12d891e c678561 a6d00b1 6755ee0 12d891e 27dbdfd 12d891e 191e71b 27dbdfd 12d891e 27dbdfd b6bac0f 7c95914 27dbdfd 7c95914 a152229 7c95914 b6bac0f 9ca7d21 b6bac0f 27dbdfd 13c5f18 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 27dbdfd a48e7a7 10a642d 27dbdfd 10a642d |
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 |
import streamlit as st
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
def cloud_button(label, key=None, color=None, overlap=30):
button_id = f"cloud-button-{key or label}"
color_class = f"color-{color}" if color else ""
num_circles = max(3, min(35, len(label) // 4))
circle_size = 60
# Create circles with text enclosed
circles_html = ''.join([
f'<div class="circle {color_class}" style="margin-right: -{overlap}px;"></div>'
for _ in range(num_circles)
])
circles_html += f'<div class="circle-text">{label}</div>' # Add the text after the circles
cloud_button_html = f"""
<div class="cloud" id="{button_id}" style="margin-bottom: 20px;">
<div class="wrapper {color_class}">
{circles_html}
</div>
</div>
<style>
.cloud {{
position: relative;
display: inline-flex;
align-items: center;
justify-content: center;
}}
.wrapper {{
display: flex;
align-items: center;
justify-content: center;
position: relative;
padding: 10px 20px;
}}
.circle {{
background-color: #FF6347;
border-radius: 50%;
width: {circle_size}px;
height: {circle_size}px;
position: relative;
}}
.circle-text {{
position: absolute;
top: 50%;
left: 50%;
transform: translate(-50%, -50%);
font-weight: bold;
z-index: 2;
white-space: nowrap; /* Prevent line breaks */
text-align: center; /* Center the text horizontally and vertically */
}}
/* Add this CSS for the hover effect and shadow */
.cloud:hover .circle {{
transform: scale(1.1); /* Scale up the circles on hover */
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); /* Add a shadow on hover */
}}
.color-1 .circle {{ background-color: #FFA07A; }}
.color-2 .circle {{ background-color: #FF7F50; }}
.color-3 .circle {{ background-color: #FF6347; }}
</style>
<script>
document.getElementById("{button_id}").onclick = function() {{
// Your existing JavaScript code for handling button click
}};
</script>
"""
st.markdown(cloud_button_html, unsafe_allow_html=True)
# 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_file_path = "Private_Book/KOMBI_all2.pdf" # Replace with your PDF file path
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) # Adjust as per the desired spacing
st.markdown("""
Hello! I’m here to assist you with:<br><br>
📘 **Glossary Inquiries:**<br>
I can clarify terms like "DiGA", "AOP", or "BfArM", providing clear and concise explanations to help you understand our content better.<br><br>
🆘 **Help Page Navigation:**<br>
Ask me if you forgot your password or want to know more about topics related to the platform.<br><br>
📰 **Latest Whitepapers Insights:**<br>
Curious about our recent publications? Feel free to ask about our latest whitepapers!<br><br>
""", unsafe_allow_html=True)
add_vertical_space(1) # Adjust as per the desired spacing
st.write('Made with ❤️ by BinDoc GmbH')
api_key = os.getenv("OPENAI_API_KEY")
# Retrieve the API key from st.secrets
def load_pdf(file_path):
pdf_reader = PdfReader(file_path)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text=text)
store_name, _ = os.path.splitext(os.path.basename(file_path))
if os.path.exists(f"{store_name}.pkl"):
with open(f"{store_name}.pkl", "rb") as f:
VectorStore = pickle.load(f)
else:
embeddings = OpenAIEmbeddings()
VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
with open(f"{store_name}.pkl", "wb") as f:
pickle.dump(VectorStore, f)
return VectorStore
def load_chatbot():
return load_qa_chain(llm=OpenAI(), chain_type="stuff")
def main():
hide_streamlit_style = """
<style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style>
"""
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
# Main content
st.title("Welcome to BinDocs ChatBot! 🤖")
# Directly specifying the path to the PDF file
pdf_path = pdf_file_path
if not os.path.exists(pdf_path):
st.error("File not found. Please check the file path.")
return
if "chat_history" not in st.session_state:
st.session_state['chat_history'] = []
if "button_clicked" not in st.session_state:
st.session_state['button_clicked'] = None
display_chat_history(st.session_state['chat_history'])
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()
if pdf_path is not None:
query = st.text_input("Ask questions about your PDF file (in any preferred language):")
cloud_button("Was genau ist ein Belegarzt?", key="button1", color="1")
cloud_button("Wofür wird die Alpha-ID verwendet?", key="button2", color="2")
cloud_button("Was sind die Vorteile des ambulanten operierens?", key="button3", color="3")
cloud_button("Was kann ich mit dem Prognose-Analyse Toll machen?", key="button4", color="4")
cloud_button("Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?", key="button5", color="5")
cloud_button("Ich habe mein Meta Password vergessen, wie kann ich es zurücksetzen?", key="button6", color="6")
# Handle button clicks
if st.session_state['button_clicked']:
query = st.session_state['button_clicked']
st.session_state['button_clicked'] = None
if st.button("Ask") or (not st.session_state['chat_history'] and query) or (st.session_state['chat_history'] and query != st.session_state['chat_history'][-1][1]):
st.session_state['chat_history'].append(("User", query, "new"))
loading_message = st.empty()
loading_message.text('Bot is thinking...')
VectorStore = load_pdf(pdf_path)
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)
st.session_state['chat_history'].append(("Bot", response, "new"))
# Display new messages at the bottom
new_messages = st.session_state['chat_history'][-2:]
for chat in new_messages:
background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
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)
# Scroll to the latest response using JavaScript
st.write("<script>document.getElementById('response').scrollIntoView();</script>", unsafe_allow_html=True)
loading_message.empty()
# Clear the input field by setting the query variable to an empty string
query = ""
# Mark all messages as old after displaying
st.session_state['chat_history'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history']]
def display_chat_history(chat_history):
for chat in chat_history:
background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
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)
if __name__ == "__main__":
main() |