Update app.py

app.py

@@ -189,7 +189,10 @@ if file_text:
         display_context_table(context_words)
 
     with st.expander("📝 Sentence Clustering"):
-        sentences = [sentence.strip() for sentence in text_without_timestamps.split('.') if len(sentence.strip()) > 10]
+        sentences = [line.strip() for line in text_without_timestamps.split('\n') if len(line.strip()) > 10]
+
+        num_sentences = len(sentences)
+        st.write(f"Total Sentences: {num_sentences}")
 
         num_clusters = st.slider("Number of Clusters", min_value=2, max_value=10, value=5)
         clustered_sentences = cluster_sentences(sentences, num_clusters)
@@ -213,4 +216,11 @@ if file_text:
 
             st.text_area("Clustered Sentences", value=clustered_text, height=400)
 
+            # Verify that all sentences are accounted for in the clustered output
+            clustered_sentences_flat = [sentence for cluster in clustered_sentences for sentence in cluster]
+            if set(sentences) == set(clustered_sentences_flat):
+                st.write("✅ All sentences are accounted for in the clustered output.")
+            else:
+                st.write("❌ Some sentences are missing in the clustered output.")
+
 st.markdown("For more information and updates, visit our [help page](https://huggingface.co/awacke1).")