Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from PIL import Image
-from pinecone import Pinecone
+import pinecone
+import pinecone_text
 import random
 import time
 from dotenv import load_dotenv
@@ -17,8 +18,6 @@ from langchain.callbacks import get_openai_callback
 import os
 import uuid
 import json
-
-
 import pandas as pd
 import pydeck as pdk
 from urllib.error import URLError
@@ -50,6 +49,8 @@ index_name = "canopy--document-uploader"  # Replace with your chosen index name
 
 index = pc.Index(name=index_name)
 
+# Initialize Pinecone Text Client for embedding
+encoder = pinecone_text.OpenAIEncoder()
 
 # Step 1: Clone the Dataset Repository
 repo = Repository(
@@ -254,16 +255,11 @@ def query_pinecone(vector, index, top_k=5):
     query_results = index.query(vector=vector, top_k=top_k)
     return query_results["matches"]
 
-    
-from sentence_transformers import SentenceTransformer
-
-# Initialize the model
-model = SentenceTransformer('all-MiniLM-L6-v2')
-
 def text_to_vector(text):
-    # Convert input text to vector
-    embedding = model.encode(text)
-    return embedding.tolist()  # Convert embedding to list
+    # Convert input text to vector using Pinecone Text Client
+    embedding = encoder.encode([text])[0]  # Assume single text input; adjust accordingly
+    return embedding
+
 
 
 def page1():
@@ -510,68 +506,48 @@ def page2():
 
 def page3():
     try:
-        # Hide Streamlit's default UI elements
-        hide_streamlit_style = """
+        st.markdown("""
             <style>
             #MainMenu {visibility: hidden;}
             footer {visibility: hidden;}
             </style>
-            """
-        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+            """, unsafe_allow_html=True)
     
-        # Create columns for layout
         col1, col2 = st.columns([3, 1])
-
         with col1:
             st.title("Kosten- und Strukturdaten der Krankenhäuser")
-
         with col2:
-            # Display an image in the right column
-            image = Image.open('BinDoc Logo (Quadratisch).png')
-            st.image(image, use_column_width='always')
-
-        # 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
+            image_path = 'BinDoc Logo (Quadratisch).png'
+            if os.path.exists(image_path):
+                image = Image.open(image_path)
+                st.image(image, use_column_width='always')
 
         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:")
 
-        # Query buttons
-        col1, col2 = st.columns(2)
-        # Define buttons and their queries here as before
-
-        
         if query:
-            # Convert the query text to a vector
-            query_vector = text_to_vector(query)
-
-            # Query Pinecone with the vector
-            matches = query_pinecone(query_vector, index, top_k=5)
+            # Convert the query text to a vector using Pinecone Text Client
+            query_vector = encoder.encode([query])[0]
+            matches = query_pinecone(query_vector, top_k=5)
 
-            # Assuming query_pinecone is defined elsewhere and connects to Pinecone correctly
-            # Display the results
+            response_messages = []
             for match in matches:
-                matched_text = match["metadata"].get("text", "No text available")
+                matched_text = match["metadata"].get("summary", "Detailed information not available.")
                 similarity_score = match["score"]
-                st.write(f"Matched Text: {matched_text} - Score: {similarity_score}")
+                response_messages.append((f"Pinecone Match - Score: {similarity_score:.2f}", matched_text))
 
-            # Your existing logic to handle chat history and responses...
+            # Update session state with the new chat and response
+            st.session_state['chat_history_page3'].extend([(query, "User Query")] + response_messages)
             
+            # Display the new responses
+            display_chat_history([(query, "User Query")] + response_messages)
+
+            # Save the updated conversation to a file
+            save_conversation(st.session_state['chat_history_page3'], st.session_state['session_id'])
+
     except Exception as e:
-        st.error(f"Upsi, an unexpected error occurred: {e}")
+        st.error(f"An unexpected error occurred: {e}")