@merari42@lemmy.world avatar

merari42

@merari42@lemmy.world

This profile is from a federated server and may be incomplete. For a complete list of posts, browse on the original instance.

LLM queries for personal pdf libraries?

So perplexity can kind of weakly analyze the first few pages of small file size pdfs one at a time, but I'd love to have something that would allow me to upload several hundred research papers and textbooks that could then be analyzed for consensus and contradictions and give me more meaningful search results and summaries than...

merari42 ,
@merari42@lemmy.world avatar

I have used this small R package that allows you to read the text content of a PDF and send it to a local llama model via ollama or one of the large LLM APIs. I could use that to get structured answers in JSON format on a whole folder of papers, but the context length of a typical model is only long enough to hold a single (roughly 40-page) paper in the memory. So I had to get separate structurer answers on each paper and then generate a complete summary from those. Unfortunately that is not user-friendly yet.

merari42 OP ,
@merari42@lemmy.world avatar

A village nearby my hometown got fiber for the church and installed directed wifi antennas on the church tower to solve their internet problems

merari42 OP ,
@merari42@lemmy.world avatar

Technically you do not confess, but the Big5 internet monopolists track your every move like a vengeful god would do.

merari42 ,
@merari42@lemmy.world avatar

I know Python, R, the STATA ado-language (a horrible proprietary progamming language), MATLABs language, Javascript and some minimal C++. What I know really well though is R and Python. So typical profile for a (data) scientist.

merari42 ,
@merari42@lemmy.world avatar

This is a good place to leave this link to a nice folk song about parasites that has a verse on Toxoplasma of course

merari42 ,
@merari42@lemmy.world avatar

Can you at least say how your prior belief distribution has shifted or been reaffirmed given the observed data points?

merari42 ,
@merari42@lemmy.world avatar

How is Pak better than pacman, which is my preferred package management solution for R.

merari42 ,
@merari42@lemmy.world avatar

Wouldn't porn have a clear bias due to selection issues, if fake moaning is more common in porn than in real live? Then again gathering experimental data would have an experimenter demand issue. Just imagine you are a participant in the natural human sex sounds study. Hard to imagine that you do not take that consciously into account.

merari42 OP ,
@merari42@lemmy.world avatar

hbomberguy has a few of these wild rides. I look forward to the video he will make sometimes this year.

What Would Jesus Do? ( lemmy.world )

"Now listen, you rich people, weep and wail because of the misery that is coming on you. Your wealth has rotted, and moths have eaten your clothes. Your gold and silver are corroded. Their corrosion will testify against you and eat your flesh like fire. You have hoarded wealth in the last days. Look! The wages you failed to...

merari42 ,
@merari42@lemmy.world avatar

I hear he has a history of problems with the state. he was literally crucified.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • random
  • test
  • worldmews
  • mews
  • All magazines