Skip to main content

Featured

I built An Offline ChatBot Companion Raspberry Pi Robot

  This post also has a  YouTube version. Meet Katherine my personalized offline conversational companion chatbot, which can answer questions, give facts on anything, and can remember and comprehend.  I made this chatbot without any large language models. So no-GPT essentially. After years of working on my own conversational software as a hobby, I finally have a prototype I can use to demonstrate. This is Katherine my offline chatbot. I named it after Katherine Johnson - A human computer that worked for NASA. Katherine is powered by my own python code , some public libraries, and local files. I’ve spent a few years learning different strategies for closed looped conversational system. Thanks to Katherine here, I think I’m on the right track. Why did I make Katherine?  Well aside from having my own personalized chatbot, l wanted to be able to have a companion robot that I could talk to no matter the situation. Whether it be a Power outage, or a camping trip, my compani...

My Jarvis Ai pt 2

  


What’s up readers, hobbyists and experimenters, it’s been a while since my last post. But I’m back and can get these articles and experimentations back rolling. 


One of the first updates I’m excited to tell you about, was an update to how I use my “Jarvis” program. From the previous article , I told you I was able to use Jarvis casually, and that was true , however not that effective. Although hands free, any help I wanted from the program had to be given near the computer. The microphone was attached and therefore stationary. 


In order to solve this problem I purchased a conference microphone/ speaker. This device would allow me to travel around the house, giving Jarvis a more omnipresent feel. By stationing the conference microphone in the living area I could enjoy a book or movie etc and still have access to basic information. 


This feature has come in handy while I read, providing clear and detailed explanations about things I need to understand. For example, while reading a book I came across a word I didn’t know so I asked the software. As long as the text to speech component can understand me, I can get a pretty good explanation from the software. 


I can also get quick information about people, places and events in movies while watching. Need to brush up on World War One? No problem, want to know about Roman aqueducts? Sure! It’s easy. 


As another enhancement to the program I’ve added the small subset of Wikipedia articles that works offline. I’m using this feature to give a visual representation just in case I’m on the computer and would like to see objects. 


So overall, I’m even more satisfied with this experiment than before but it got me thinking what other features would I possibly need?


Future updates that might be worth while….


Web control

      YouTube 

      Searches


Keeping up with information 

       To do list 

       Calendar

       Weather

       News


Comments

Popular Posts