I have a question about the use of Settings. Consider the constructor of
SentenceSplitter
, taken from the LlamaIndex repository:
class SentenceSplitter(MetadataAwareTextSplitter):
"""Parse text with a preference for complete sentences.
In general, this class tries to keep sentences and paragraphs together. Therefore
compared to the original TokenTextSplitter, there are less likely to be
hanging sentences or parts of sentences at the end of the node chunk.
"""
chunk_size: int = Field(
default=DEFAULT_CHUNK_SIZE,
description="The token chunk size for each chunk.",
gt=0,
)
...
Clearly, the default chunk size is used if arguments are not specified. For other classes, argument values are taken from Settings. Are there rules that allow us to know when to rely on Settings and when not to? Thanks.