Reader

No better place to learn than source code

https://github.com/run-llama/llama_index/blob/be76419dd226244a1ad057f77ad822d16fe92df3/llama-index-core/llama_index/core/readers/file/base.py#L117

I had a question along these lines I have a singe pdf file in a directory and it’s being parsed into 17 different documents. This is affecting the chunking process for embedding. I can’t seem to find in the docs why simple directory reader would do this or how to configure it

It's for making citation by page possible.

If you don't want this, just merge all into a single document object