Update app.py

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 from PIL import Image
+from pinecone import Pinecone
 import random
 import time
 from dotenv import load_dotenv
@@ -38,6 +39,18 @@ if 'session_id' not in st.session_state:
 
 
 
+
+# Initialize Pinecone client
+api_key = os.environ["api_key"]
+
+# Consider securely storing and accessing this
+Pinecone.init(api_key=api_key)
+index_name = "canopy--document-uploader"  # Replace with your chosen index name
+
+index = Pinecone.Index(name=index_name)
+
+
+
 # Step 1: Clone the Dataset Repository
 repo = Repository(
     local_dir="Private_Book",  # Local directory to clone the repository
@@ -235,6 +248,22 @@ def display_session_id():
     st.sidebar.markdown(f"**Ihre Session ID:** `{session_id}`")
     st.sidebar.markdown("Verwenden Sie diese ID als Referenz bei Mitteilungen oder Rückmeldungen.")
 
+    
+def query_pinecone(user_input, index, top_k=5):
+    # Assuming 'user_input' is the text from the user you want to query against the vector database
+    # And 'index' is your initialized Pinecone index
+
+    # Query Pinecone index for similar vectors
+    query_results = index.query(
+        vector=user_input,  # Pinecone automatically handles embedding if set up to do so
+        top_k=top_k,
+        include_metadata=True  # Set to True if you want to include metadata in the response
+    )
+
+    # Process query results
+    matches = query_results["matches"]
+    return matches
+
 
 def page1():
     try:
@@ -480,125 +509,65 @@ def page2():
 
 def page3():
     try:
+        # Hide Streamlit's default UI elements
         hide_streamlit_style = """
-                <style>
-                #MainMenu {visibility: hidden;}
-                footer {visibility: hidden;}
-                </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
+        # Create columns for layout
+        col1, col2 = st.columns([3, 1])
 
         with col1:
             st.title("Kosten- und Strukturdaten der Krankenhäuser")
 
         with col2:
-            # Load and display the image in the right column, which will be the top-right corner of the page
+            # Display an image in the right column
             image = Image.open('BinDoc Logo (Quadratisch).png')
             st.image(image, use_column_width='always')
 
-            
-        if not os.path.exists(pdf_path2):
+        # Check if the PDF file exists
+        pdf_path3 = "Private_Book/Kosten_Strukturdaten_RAG_vorbereited.pdf"
+        if not os.path.exists(pdf_path3):
             st.error("File not found. Please check the file path.")
             return
 
-        VectorStore = load_vector_store(pdf_path3, "Kosten_Str_2301", force_reload=True)
-
-
-
         display_chat_history(st.session_state['chat_history_page3'])
 
+        # Spacer
         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
         new_messages_placeholder = st.empty()
 
+        # User query input
         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
+        # Query buttons
         col1, col2 = st.columns(2)
-        
-        with col1:
-            if st.button("Wie hat sich die Bettenanzahl in den letzten 10 Jahren entwickelt?"):
-                query = "Wie hat sich die Bettenanzahl in den letzten 10 Jahren entwickelt?"
-            if st.button("Wie viele Patienten wurden im Jahr 2017 vollstationär behandelt?"):
-                query = ("Wie viele Patienten wurden im Jahr 2017 vollstationär behandelt?")
-            if st.button("Wie viele Vollkräfte arbeiten in Summe 2021 in deutschen Krankenhäusern?"):
-                query = "Wie viele Vollkräfte arbeiten in Summe 2021 in deutschen Krankenhäusern? "
-
-        
-        with col2:
-            if st.button("Welche unterschiedlichen Personalkosten gibt es im Krankenhaus?"):
-                query = "Welche unterschiedlichen Personalkosten gibt es im Krankenhaus?"
-            if st.button("Welche Sachkosten werden in Krankenhäusern unterschieden?"):
-                query = "Welche Sachkosten werden in Krankenhäusern unterschieden? "
-            if st.button("Wie hoch sind die Gesamtkosten der Krankenhäuser pro Jahr: 2019, 2020, 2021?"):
-                query = "Wie hoch sind die Gesamtkosten der Krankenhäuser pro Jahr: 2019, 2020, 2021?"
-
-    
+        # Define buttons and their queries here as before
 
         if query:
-            full_query = ask_bot(query)
-            st.session_state['chat_history_page3'].append(("User", query, "new"))
-
-            # Start timing
-            start_time = time.time()
-            
-            # Create a placeholder for the response time
-            response_time_placeholder = st.empty()
-            
-            with st.spinner('Eve denkt über Ihre Frage nach...'):
-                chain = load_chatbot()
-                docs = VectorStore.similarity_search(query=query, k=5)
-                with get_openai_callback() as cb:
-                    response = chain.run(input_documents=docs, question=full_query)
-                    response = handle_no_answer(response)  # Process the response through the new function
+            # Query Pinecone index
+            matches = query_pinecone(query, index, top_k=5)
+            # Assuming query_pinecone is a function that sends the query to Pinecone and retrieves matches
 
+            for match in matches:
+                # Display matched texts and their scores
+                matched_text = match["metadata"].get("text", "No text available")
+                similarity_score = match["score"]
+                st.write(f"Matched Text: {matched_text} - Score: {similarity_score}")
 
-                    
-            # Stop timing
-            end_time = time.time()
-            
-            # Calculate duration
-            duration = end_time - start_time
-
-            st.session_state['chat_history_page3'].append(("Eve", response, "new"))
-
-            # Combine chat histories from all pages
-            all_chat_histories = [
-                st.session_state['chat_history_page1'],
-                st.session_state['chat_history_page2'],
-                st.session_state['chat_history_page3']
-            ]
-
-            # Save the combined chat histories
-            save_conversation(all_chat_histories, st.session_state['session_id'])
-
-
-            # Display new messages at the bottom
-            new_messages = st.session_state['chat_history_page3'][-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)
-        
-            # Update the response time placeholder after the messages are displayed
-            response_time_placeholder.text(f"Response time: {duration:.2f} seconds")
-
-
-            # Clear the input field after the query is made
-            query = ""
-
-        # Mark all messages as old after displaying
-        st.session_state['chat_history_page3'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history_page3']]
+            # Append the user query to chat history and process it as before
+            process_and_display_chat_history(query, matches)  # You would need to implement this based on your application logic
 
     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 page4():
     try: