Update app.py

app.py

@@ -1,37 +1,43 @@
 from dotenv import load_dotenv
 import streamlit as st
 from user_utils import *
-
-#Creating session variables
-
-
+from pinecone import PineconeClient
 
 def main():
+    # Load environment variables
     load_dotenv()
 
     st.header("Automatic Ticket Classification Tool")
-    #Capture user input
+    
+    # Capture user input
     st.write("We are here to help you, please ask your question:")
     user_input = st.text_input("🔍")
 
     if user_input:
-
-        #creating embeddings instance...
-        embeddings=create_embeddings()
-
-        #Function to pull index data from Pinecone
-       
-        index=pull_from_pinecone("pcsk_4etRhj_Lc37c2KWzUgdTSPaShQKgxeZvC331qJcVWjK9LfpDARwkG23kXZoN5ZCHVLyYWZ","gcp-starter","ticket",embeddings)
-        
-        #This function will help us in fetching the top relevent documents from our vector store - Pinecone Index
-        relavant_docs=get_similar_docs(index,user_input)
-
-      
-        st.write(relavant_docs)
-
-
-                 
-if __name__ == '__main__':
+        try:
+            # Create embeddings instance
+            embeddings = create_embeddings()
+
+            # Fetch the Pinecone index using the API key and environment info
+            index = pull_from_pinecone(
+                "pcsk_4etRhj_Lc37c2KWzUgdTSPaShQKgxeZvC331qJcVWjK9LfpDARwkG23kXZoN5ZCHVLyYWZ",
+                "gcp-starter",
+                "ticket",
+                embeddings
+            )
+
+            # Fetch the relevant documents based on the user input
+            relevant_docs = get_similar_docs(index, user_input)
+
+            # Display the relevant documents
+            if relevant_docs:
+                st.write("Relevant Documents:")
+                for doc in relevant_docs:
+                    st.write(doc)
+            else:
+                st.write("No relevant documents found.")
+        except Exception as e:
+            st.write(f"An error occurred: {e}")
+
+if __name__ == "__main__":
     main()
-
-