Update app.py

app.py

@@ -12,21 +12,21 @@ corpus = pd.read_pickle("corpus.pkl")
 
 
 def search(query, top_k=100):
-    print("Top 5 Answer by the NSE:")
+    print("Top Answer by the NSE:")
     print()
     ans = []
-    ##### Sematic Search #####
-    # Encode the query using the bi-encoder and find potentially relevant passages
+    
+    # Encode the query using the bi-encoder and find relevant passage
     question_embedding = bi_encoder.encode(query, convert_to_tensor=True)
     hits = util.semantic_search(question_embedding, corpus_embeddings, top_k=top_k)
     hits = hits[0]  # Get the hits for the first query
 
-    ##### Re-Ranking #####
+    
     # Now, score all retrieved passages with the cross_encoder
     cross_inp = [[query, corpus[hit['corpus_id']]] for hit in hits]
     cross_scores = cross_encoder.predict(cross_inp)
 
-    # Sort results by the cross-encoder scores
+    # Sorting results by the cross-encoder scores
     for idx in range(len(cross_scores)):
         hits[idx]['cross-score'] = cross_scores[idx]
 
@@ -37,10 +37,10 @@ def search(query, top_k=100):
     return ans[0]
 
 
-exp = ["Who is steve jobs?", "What is coldplay?", "What is a turing test?",
+exp = ["Who is steve jobs?", "Who is Salman Khan?", "Who is Kevin Hart?",
        "What is the most interesting thing about our universe?", "What are the most beautiful places on earth?"]
 
-desc = "This is a semantic search engine with a retrieval and reranking system on Wikipedia corous. This will return the top 5 results. So Quest on with Transformers."
+desc = "This is a semantic search engine made with sentence transformer."
 
 inp = gr.inputs.Textbox(lines=1, placeholder=None, default="", label="search you query here")
 out = gr.outputs.Textbox(type="auto", label="search results")