Update app.py

app.py

@@ -107,9 +107,9 @@ def preprocess_plain_text(text,window_size=3):
             end_idx = min(start_idx+window_size, len(paragraph))
             passages.append(" ".join(paragraph[start_idx:end_idx]))
             
-    print("Paragraphs: ", len(paragraphs))
-    print("Sentences: ", sum([len(p) for p in paragraphs]))
-    print("Passages: ", len(passages))
+    st.write(f"Paragraphs: {len(paragraphs)}")
+    st.write(f"Sentences: {sum([len(p) for p in paragraphs])}")
+    st.write(f"Passages: {len(passages)}")
 
     return passages
 
@@ -121,10 +121,10 @@ def bi_encode(bi_enc,passages):
     bi_encoder = SentenceTransformer(bi_enc)
 
     #Compute the embeddings using the multi-process pool
-    print('encoding passages into a vector space...')
+    st.write('encoding passages into a vector space...')
     corpus_embeddings = bi_encoder.encode(passages, convert_to_tensor=True, show_progress_bar=True)
 
-    print("Embeddings computed. Shape:", corpus_embeddings.shape)
+    st.write(f"Embeddings computed. Shape: {corpus_embeddings.shape}")
     
     return corpus_embeddings
     
@@ -169,7 +169,9 @@ bi_enc_options = ["multi-qa-mpnet-base-dot-v1","all-mpnet-base-v2","multi-qa-Min
 def search_func(query, top_k=2):
     st.write(f"Search Query: {query}")
     
-    st.write("Document Header: ")
+    if url_text:
+        
+        st.write(f"Document Header: {title}")
 
     ##### BM25 search (lexical search) #####
     bm25_scores = bm25.get_scores(bm25_tokenizer(query))