Spaces:
Sleeping
Sleeping
import streamlit as st | |
from PIL import Image | |
import time | |
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_compressed.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 | |
# 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") | |
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 page1(): | |
try: | |
hide_streamlit_style = """ | |
<style> | |
#MainMenu {visibility: hidden;} | |
footer {visibility: hidden;} | |
</style> | |
""" | |
st.markdown(hide_streamlit_style, unsafe_allow_html=True) | |
col1, col2 = st.columns([3, 1]) | |
with col1: | |
st.title("Welcome to BinDocs ChatBot!") | |
with col2: | |
image = Image.open('BinDoc Logo (Quadratisch).png') | |
st.image(image, use_column_width='always') | |
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) | |
query = st.text_input("Ask questions about your PDF file (in any preferred language):") | |
add_vertical_space(2) | |
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_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) | |
end_time = time.time() | |
duration = end_time - start_time | |
st.text(f"Response time: {duration:.2f} seconds") | |
st.session_state['chat_history_page1'].append(("Bot", response, "new")) | |
new_messages = st.session_state['chat_history_page1'][-2:] | |
for chat in new_messages: | |
background_color = "#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) | |
query = "" | |
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}") | |
def page2(): | |
try: | |
hide_streamlit_style = """ | |
<style> | |
#MainMenu {visibility: hidden;} | |
footer {visibility: hidden;} | |
</style> | |
""" | |
st.markdown(hide_streamlit_style, unsafe_allow_html=True) | |
col1, col2 = st.columns([3, 1]) | |
with col1: | |
st.title("Kodieren statt Frustrieren!") | |
with col2: | |
image = Image.open('BinDoc Logo (Quadratisch).png') | |
st.image(image, use_column_width='always') | |
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) | |
query = st.text_input("Ask questions about your PDF file (in any preferred language):") | |
add_vertical_space(2) | |
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 Folgezustände von Krankheiten beachten?"): | |
query = "Was muss ich bei der Kodierung der Folgezustände von Krankheiten beachten?" | |
if st.button("Was mache ich bei einer Verdachtsdiagnose, wenn mein Patient nach Hause entlassen wird?"): | |
query = "Was mache ich bei einer Verdachtsdiagnose, wenn mein Patient nach Hause entlassen wird?" | |
if query: | |
st.session_state['chat_history_page2'].append(("User", query, "new")) | |
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) | |
end_time = time.time() | |
duration = end_time - start_time | |
st.text(f"Response time: {duration:.2f} seconds") | |
st.session_state['chat_history_page2'].append(("Bot", response, "new")) | |
new_messages = st.session_state['chat_history_page2'][-2:] | |
for chat in new_messages: | |
background_color = "#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) | |
query = "" | |
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}") | |
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() |