Update app.py

app.py

@@ -65,7 +65,7 @@ with open(embedding_cache_path, "rb") as fIn:
 # This function will search all wikipedia articles for passages that
 # answer the query
 def search(query):
-    st.success("Input question:", query)
+    st.write("Input question:", query)
     ##### Sematic Search #####
     # Encode the query using the bi-encoder and find potentially relevant passages
     query_embedding = bi_encoder.encode(query, convert_to_tensor=True)
@@ -82,18 +82,18 @@ def search(query):
         hits[idx]['cross-score'] = cross_scores[idx]
 
     # Output of top-10 hits from bi-encoder
-    st.success("\n-------------------------\n")
-    st.success("Top-10 Bi-Encoder Retrieval hits")
+    st.write("\n-------------------------\n")
+    st.write("Top-10 Bi-Encoder Retrieval hits")
     hits = sorted(hits, key=lambda x: x['score'], reverse=True)
     for hit in hits[0:10]:
-        st.success("\t{:.3f}\t{}".format(hit['score'], passages[hit['corpus_id']].replace("\n", " ")))
+        st.write("\t{:.3f}\t{}".format(hit['score'], passages[hit['corpus_id']].replace("\n", " ")))
 
     # Output of top-10 hits from re-ranker
-    st.success("\n-------------------------\n")
-    st.success("Top-10 Cross-Encoder Re-ranker hits")
+    st.write("\n-------------------------\n")
+    st.write("Top-10 Cross-Encoder Re-ranker hits")
     hits = sorted(hits, key=lambda x: x['cross-score'], reverse=True)
     for hit in hits[0:10]:
-        st.success("\t{:.3f}\t{}".format(hit['cross-score'], passages[hit['corpus_id']].replace("\n", " ")))
+        st.write("\t{:.3f}\t{}".format(hit['cross-score'], passages[hit['corpus_id']].replace("\n", " ")))
 
 st.write("## Results:")
 if st.button('Generate Sentence'):