Summarize PDF Docs & Extract Information with AI & R | Step-By-Step Tutorial

DESCRIPTION AND CODE
With {tidychatmodels} it's pretty easy to set up a chat flow to use AI for summarizing PDFs and extracting key information from it. In this video, I show you how that works. You can find the corresponding blog post at albert-rapp.de...
📈 CREATE EFFECTIVE CHARTS
Check out my video course to create insightful data visualizations with ggplot at arapp.thinkifi...
MORE VIDEOS
📺 Avoid duplicate R code in 150 seconds • Avoid duplicate code w...
📺 Shiny modules in 100 seconds • Shiny Modules in 100 S...
📺 Fast explainer playlist • Explainer videos
Subscribe at 👉 / @rappa753
MORE CONTENT
- weekly 3-minute newsletter about R, DataViz and webdev at 3mw.albert-rap...
- LinkedIn at / dr-albert-rapp-9a5b9b28b
#rstats #dataviz #ggplot #dplyr

[@rappa753]

If you enjoyed this video and want to level up your R skills even further, check out my latest video courses:
📍Data Cleaning Master Class at data-cleaning.albert-rapp.de/
📍Insightful Data Visualizations for "Uncreative" R Users at arapp.thinkific.com/courses/insightful-data-visualizations-for-uncreative-r-users

[@jysushdz7826]

THANKS Albert for share this amazing tutorial

[@rappa753]

You're very welcome :)

[@AlexLabuda]

Very nice tutorial, thanks for sharing. Excited to check it out!

[@jimmahgee]

This is super, Albert. At work we have a load of complex documents that get human processed each year. For a hackathon we’re going to see if we can pre-process using LLMs. So this is a super useful starting point for my attempt when the time comes!

[@rappa753]

Nice, best if luck with the hackathon! Let me know how it went 🤗

[@jiazhang803]

Excellent! Thanks Albert! May I ask how you pasted different pieces of code so quickly during the tutorial? Looks like magic to me🙈

[@rappa753]

Thank you 😊 Throw in the whole code chunk and remove it in reverse order. Then just do ctrl-z 😀

[@jiazhang803]

Haha good trick! thanks@@rappa753

[@olexiypukhov-KT]

I find it easier to just use httr, call the api, and map myself. But to each their own.

[@rappa753]

I can relate. People who already know how to work with APIs might feel like it's more overhead. How do you feel about the {httr2} package? I feel like it has a much nicer syntax than {httr}.

[@hanshellsmark8430]

Awsome package! Is rate limits handled in the call to the different models? If not, the map function will be difficult to use on larger use cases, right?

[@rappa753]

Glad that you like it. Rate limits are not yet handled. So you might have to go with a classic for loop and put in a bit of pause between iterations

[@listonjohnson3408]

Has anyone set this up using local models and Ollama negating the need for api keys?