Update pages/3_Earnings_Semantic_Search_🔎_.py

pages/3_Earnings_Semantic_Search_🔎_.py

@@ -8,24 +8,36 @@ st.markdown("## Earnings Semantic Search with SBert")
 def gen_sentiment(text):
     '''Generate sentiment of given text'''
     return sent_pipe(text)[0]['label']
+    
+bi_enc_options = ["multi-qa-mpnet-base-dot-v1","all-mpnet-base-v2","multi-qa-MiniLM-L6-cos-v1","neeva/query2query"]
 
 search_input = st.text_input(
         label='Enter Your Search Query',value= "What key challenges did the business face?", key='search')
         
+sbert_model_name = st.sidebar.selectbox("Encoder Model", options=bi_enc_options, key='sbox')
+        
 top_k = st.sidebar.slider("Number of Top Hits Generated",min_value=1,max_value=5,value=2)
 
 window_size = st.sidebar.slider("Number of Sentences Generated in Search Response",min_value=1,max_value=7,value=3)
 
-if search_input:
+if search_input and sbert_model_name:
     
 
     if "sen_df" in st.session_state and "earnings_passages" in st.session_state:
     
+        
+    
         ## Save to a dataframe for ease of visualization
         sen_df = st.session_state['sen_df']
             
         passages = preprocess_plain_text(st.session_state['earnings_passages'],window_size=window_size)
         
+        with st.spinner(
+            text=f"Loading {sbert_model_name} encoder and embedding text into vector space. This might take a few seconds depending on the length of text..."
+        ):
+            sbert = load_sbert(sbert_model_name)
+            
+        
         ##### Sematic Search #####
         # Encode the query using the bi-encoder and find potentially relevant passages
         corpus_embeddings = sbert.encode(passages, convert_to_tensor=True, show_progress_bar=True)