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'
'
for _ in range(num_circles)
])
circles_html += f'{label}
' # Add the text after the circles
cloud_button_html = f"""
"""
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:
📘 **Glossary Inquiries:**
I can clarify terms like "DiGA", "AOP", or "BfArM", providing clear and concise explanations to help you understand our content better.
🆘 **Help Page Navigation:**
Ask me if you forgot your password or want to know more about topics related to the platform.
📰 **Latest Whitepapers Insights:**
Curious about our recent publications? Feel free to ask about our latest whitepapers!
""", 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 = """
"""
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("", unsafe_allow_html=True)
st.write("", unsafe_allow_html=True)
st.write("", 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"{chat[0]}: {chat[1]}
", unsafe_allow_html=True)
# Scroll to the latest response using JavaScript
st.write("", 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"{chat[0]}: {chat[1]}
", unsafe_allow_html=True)
if __name__ == "__main__":
main()