Update app.py

app.py

@@ -249,20 +249,21 @@ def display_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
-
+def query_pinecone(vector, index, top_k=5):
     # 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
-    )
+    query_results = index.query(vector=vector, top_k=top_k)
+    return query_results["matches"]
+
+    
+from sentence_transformers import SentenceTransformer
 
-    # Process query results
-    matches = query_results["matches"]
-    return matches
+# 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
 
 
 def page1():
@@ -552,22 +553,27 @@ def page3():
         col1, col2 = st.columns(2)
         # Define buttons and their queries here as before
 
+        
         if query:
-            # 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
+            # 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)
+
+            # Assuming query_pinecone is defined elsewhere and connects to Pinecone correctly
+            # Display the results
             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}")
 
-            # 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
-
+            # Your existing logic to handle chat history and responses...
+            
     except Exception as e:
         st.error(f"Upsi, an unexpected error occurred: {e}")
+    
+
 
 def page4():
     try: