I’m considering using Perplexity to ask questions about uploaded research PDFs, but a lot of the material I work with relies on tables, footnotes, and captions rather than plain paragraphs.

Does it pick up those details accurately, or do you find that it misses information when the answer depends on a table cell or a note at the bottom of the page? I’d also like to know whether it’s easy to tell which parts of an answer came from the PDF versus a web search.