The community member who posted the original question is wondering if it is recommended to preprocess data before using it with LlamaIndex. They mention that they have had much better results when parsing everything into a text file and passing it to LlamaIndex.
In the comments, another community member suggests that the preprocessing required depends on the format of the original data. They note that most parsers already have some form of preprocessing, such as chunking and annotating, defined. Another community member asks about the original format of the data, and the original poster responds that it was in PPTX and CSV formats, but some of it also included images, which might make preprocessing more difficult.
There is no explicitly marked answer in the comments.
is it recommended to pre process data before using it with llamaindex ? Seems I have much better results when parsing everything into a text file and passing it to llamaindex
