The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
However, The log messages are confusing because it says that it is loading markdown files instead of text. We should discuss how we would like to fix this.
However, the log messages are confusing because it says that it is loading markdown files instead of text. We should discuss how we would like to fix this.
I see two options but open to more thoughts:
The language should be changed to text and follow the pattern that the jsonLoader.py uses, skipping the from_laguage call.
Continue to use markdown as the argument to from_language and just adjust the log messages.
It doesn't seem right to be using markdown as the language on a txt document but let's discuss the best path forward.
The
textLoader
uses theload_structured_files
function to spilt the documents but providesmarkdown
as the language. Based off the resolved discussion at this PR https://github.com/microsoft/rag-experiment-accelerator/pull/88, this is fine.However, The log messages are confusing because it says that it is loading markdown files instead of text. We should discuss how we would like to fix this.
However, the log messages are confusing because it says that it is loading markdown files instead of text. We should discuss how we would like to fix this.
I see two options but open to more thoughts:
text
and follow the pattern that thejsonLoader.py
uses, skipping thefrom_laguage
call.It doesn't seem right to be using markdown as the language on a txt document but let's discuss the best path forward.