Update app.py

app.py

@@ -4,7 +4,7 @@ from pinecone import Pinecone
 from sentence_transformers import SentenceTransformer
 
 # Title of the Streamlit App
-st.title("Medical Hybrid Search")
+st.title("Pinecone Query Search on 'pubmed-splade' Index")
 
 # Initialize Pinecone globally
 index = None
@@ -14,8 +14,7 @@ def initialize_pinecone():
     api_key = os.getenv('PINECONE_API_KEY')  # Get Pinecone API key from environment variable
     if api_key:
         # Initialize Pinecone client using the new class instance method
-        pc = Pinecone(api_key=api_key)
-        return pc
+        return Pinecone(api_key=api_key)
     else:
         st.error("Pinecone API key not found! Please set the PINECONE_API_KEY environment variable.")
         return None
@@ -23,11 +22,9 @@ def initialize_pinecone():
 # Function to connect to the 'pubmed-splade' index
 def connect_to_index(pc):
     index_name = 'pubmed-splade'  # Hardcoded index name
-    # Connect to the 'pubmed-splade' index
     if index_name in pc.list_indexes().names():
-        #st.info(f"Successfully connected to index '{index_name}'")
-        index = pc.Index(index_name)
-        return index
+        st.info(f"Successfully connected to index '{index_name}'")
+        return pc.Index(index_name)
     else:
         st.error(f"Index '{index_name}' not found!")
         return None
@@ -41,10 +38,9 @@ pc = initialize_pinecone()
 
 # If Pinecone initialized successfully, proceed with index management
 if pc:
-    # Connect directly to 'pubmed-splade' index
     index = connect_to_index(pc)
 
-    # Model for query encoding
+    # Load model for query encoding
     model = SentenceTransformer('msmarco-bert-base-dot-v5')
 
     # Query input
@@ -54,17 +50,25 @@ if pc:
     if st.button("Search Query"):
         if query_text and index:
             dense_vector = encode_query(model, query_text)
-            #st.write(f"Encoded Query Vector: {dense_vector}")
-            
-            # Search the index (sparse values can be added here as well)
+
+            # Search the index
             results = index.query(
                 vector=dense_vector,
-                top_k=3,
+                top_k=5,
                 include_metadata=True
             )
             
-            st.write("Search Results:")
-            for match in results.matches:
-                st.write(f"ID: {match.id}, Score: {match.score}, Metadata: {match.metadata}")
+            st.write("### Search Results:")
+            if results.matches:
+                for match in results.matches:
+                    score = match.score
+                    context = match.metadata.get("context", "No context available")
+                    
+                    # Display score and context in a formatted way
+                    st.markdown(f"**Score**: `{score}`")
+                    st.markdown(f"**Context**: {context}")
+                    st.markdown("---")  # Divider for each result
+            else:
+                st.warning("No results found for this query.")
         else:
             st.error("Please enter a query and ensure the index is initialized.")