Update app.py

app.py

@@ -26,6 +26,10 @@ if __name__ == "__main__":
         # call the chunk size mehtod that sets the number
         chunk_size = st.number_input('Chunk size:', min_value=100, max_value=2048, value=512, on_change=clear_history)
 
+        # chunk Overlab
+        chunk_overlap = st.number_input('Chunk Overlap:', min_value=0, max_value=200, value=20, on_change=clear_history)
+
+
         # input the top-k number, k increase the search effectiveness, but is more expensive
         k = st.number_input('top-k most salient docs', min_value=1, max_value=20, value=3, on_change=clear_history)
 
@@ -43,7 +47,7 @@ if __name__ == "__main__":
                             f.write(bytes_data)
 
                         data = load_document(file_name)
-                        chunks = chunk_data(data, chunk_size=chunk_size)
+                        chunks = chunk_data(data, chunk_size=chunk_size, chunk_overlap=chunk_overlap)
                         st.write(f'Chunk size: {chunk_size}, Chunks: {len(chunks)}')
 
                         tokens, embedding_cost = calculate_embedding_cost(chunks)