The RAG generation uses the SimpleDirectoryReader class to load the document files, this class supports parallel processing  [0], perhaps we could adapt our scripts to use that and make the RAG generation faster as currently it can take quite a lot of time.

This task depends on https://issues.redhat.com/browse/OSPRH-13114

 [0] https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader/#usage