We propose HtmlRAG, which uses HTML instead of plain text as the format of external knowledge in RAG systems. To tackle the long context brought by HTML, we propose Lossless HTML Cleaning and Two-Step ...

For txt, I let it stay similar format to the msg tool. That means one lang one txt file. For csv, I put all the languages into one file, with the msg entry name, its guid, and attributes. I think this ...