New feature: Tiny Jarvis automatically fetches the news from BBC World, chooses the most impactful headline, reads the articles and generates a summary!
This happens in the background, every hour, to ensure that the news is recent.
I discovered smth called RSS feeds, which is basically a tool that feeds website updates back to you in the form of XML files.
Then I learnt about the feedparser python library, as well as trafilatura, for extracting text from HTML (for getting the text from the articles), which made the job ten times easier.
However, this process does take some time:
Step 1: script parses the BBC World feed
Step 2: local AI chooses between the thirteen daily headlines
Step 3: script fetches the associated articles text
Step 4: local AI summarizes ALL THREE articles.
On a Raspberry Pi 5, obviously, this can take at least 5 minutes.
Now for the moment this is a bit biased, because I chose the “Technology” category for the RSS feed 😅 but i’ll add the option to change it later
@Shreyansh tysm! the model i’m using is Llama 3.2 3B (Q4_K_M) ~2GB uncensored, I found it on huggingface and i run it locally on the rpi5 using llama_cpp (a python wrapper for the C library llama.cpp), so its a tiny bit faster than Ollama. (no Hack Club AI, just found out about it btw)
bro I just checked out your project 😭 this isn’t even close yours is crazy af
my model doesn’t actually have access to the computer,… i just check if the user has said a particular keyword, and if so I does an associated action
i dont use AI except for writing bash script (too lazy)
Comments 4
Hey, This looks super cool…
im doing something similar as well, its called “Buddy”
what model are you using, and also are you using Hack AI or your own credits?
@Shreyansh tysm! the model i’m using is Llama 3.2 3B (Q4_K_M) ~2GB uncensored, I found it on huggingface and i run it locally on the rpi5 using llama_cpp (a python wrapper for the C library llama.cpp), so its a tiny bit faster than Ollama. (no Hack Club AI, just found out about it btw)
bro I just checked out your project 😭 this isn’t even close yours is crazy af
my model doesn’t actually have access to the computer,… i just check if the user has said a particular keyword, and if so I does an associated action
i dont use AI except for writing bash script (too lazy)
this is p cool
@Koei thx
Sign in to join the conversation.