Has anyone faced the problem when using the SentenceWindowNodeParser for document indexing that when setting a window_size of like 6 (default is 3), the LLM responses using that index is very long and unrelated to general questions like "Hey, how are you today?" or "Who is Elon Musk" and responds with the content & window of the top nodes?
node_parser = SentenceWindowNodeParser.from_defaults(
window_size=3,
window_metadata_key="window",
original_text_metadata_key="original_text",
)