Hi, all. Anyone know if there's a smart way to find the most optimal values for max_input_size, num_outputs, max_chunk_overlap & chunk_size_limit ?

I'm using PromptHelper. It does help autofill if you've defined it beforehand. I'm trying to find a way to set the optimal values while defining it.

Importing the SimpleDirectoryReader from llama_index and then trying to parse certain files throughout a directory as shown in the https://llamahub.ai/l/file-unstructured page gives the following error: 'str' object has no attribute 'parser_config_set' Any ideas? TIA!