Update app.py

app.py

@@ -1,4 +1,5 @@
 import streamlit as st
+import streamlit_analytics
 from dotenv import load_dotenv
 import pickle
 from huggingface_hub import Repository
@@ -16,15 +17,13 @@ import os
 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
+pdf_path = "Private_Book/KOMBI_all2.pdf"  # Replace with your PDF file path
 
 with st.sidebar:
     st.title('BinDoc GmbH')
@@ -49,40 +48,44 @@ with st.sidebar:
     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:
+# 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")
 
 def main():
-
     hide_streamlit_style = """
             <style>
             #MainMenu {visibility: hidden;}
@@ -91,51 +94,51 @@ def main():
             """
     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'] = []
+    # 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, "my_vector_store", force_reload=False)
 
-    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)
+        if "chat_history" not in st.session_state:
+            st.session_state['chat_history'] = []
 
-    new_messages_placeholder = st.empty()
+        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):")
 
         if st.button("Was genau ist ein Belegarzt?"):
             query = "Was genau ist ein Belegarzt?"
         if st.button("Wofür wird die Alpha-ID verwendet?"):
             query = "Wofür wird die Alpha-ID verwendet?"
-        if st.button("Was sind die Vorteile des ambulanten operierens?"):
-            query = "Was sind die Vorteile des ambulanten operierens?"
-        if st.button("Was kann ich mit dem Prognose-Analyse Toll machen?"):
-            query = "Was kann ich mit dem Prognose-Analyse Toll machen?"
+        if st.button("Was sind die Vorteile des ambulanten Operierens?"):
+            query = "Was sind die Vorteile des ambulanten Operierens?"
+        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?")
+        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?"
 
-            
-        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]):
+        if query:
             st.session_state['chat_history'].append(("User", query, "new"))
 
             loading_message = st.empty()
             loading_message.text('Bot is thinking...')
 
-            VectorStore = load_pdf(pdf_path)
+            # Use the VectorStore loaded at the start from the session state
             chain = load_chatbot()
             docs = VectorStore.similarity_search(query=query, k=3)
             with get_openai_callback() as cb:
@@ -154,18 +157,17 @@ def main():
 
             loading_message.empty()
 
-            # Clear the input field by setting the query variable to an empty string
+            # Clear the input field after the query is made
             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()
+    main()