Smarting up HAL with free LLM model (Ollama) ?

[knight2000]

@cyberjedi whats UVE?

There are endless possibilities with any of this stuff, just boils down to how creative the developer is. Mistral is just the LLM, i feed it anything i want through the user prompts, it knows the objects im holding, it knows who i am. I wrote code to detect objects and faces,  it knows each face in the frame and who is speaking at the time based on mouth movements. I have a DB setup so it stores facts from conversions, the conversations are far more intelligent than that of HAL (out of the box), I can train the model to role play so it pretends to be KITT via system prompt. And you can definitely give it emotions in its responses, It's all in how your prompt engineer it. Everything you listed can be done using Mistral with the help of python. So if you are saying just using the LLM out of the box has none of that, then fine, yeah it's just a text bot. But my whole gripe was that HAL is not more intelligent then these LLMs. And the fact that a dev can run a decent size LLM locally without the cloud is a game changer.

I'd love to see all your updates with HAL and please dont think im trying to put HAL down and all the hard work that has been down, i'm not. I'm really just providing my findings on new tech.

One problem with Mistral is the knowledge ended in 2022 so current events have to be trained (fined tuned) into the model. Ah and another issue with HAl for me at least, how can you solve the problem of adding custom tts voices to HAL? Right now it's only able to use SAPI voices, right? I cloned KITT's voice using coqui xtts which i can use with my bot but not in HAL.

And what do you mean by edit Mistral, its brain? why would you, you just need to keep training it. you can fine tune or train it further using LoRa. I can have mistral do anything i want it to using python, if i say "start your engine" right now, Mistral matches the command to the list of commands i have stored in a python script, then using parallel port control the car starts up, just one of many commands it will run. This is the same thing i use to do with HAL. The list goes on and on.

And when i said end of an era, i meant with my project, yes its the end of a long relationship with HAL because it just doesn't stack up intelligently to these LLM's now. I have complete control over my chatbot, its completely written in python. One thing i wanted was HAL to be ported to python so it can run seamlessly on Linux. (a ton of work im sure).

again, i'd love to see some of your updates! And cheers to all the hard work you've been doing! I love checking in here to see what kind of updates have been made.

@sybershot Thank you! it's coming along nicely. I love HAL, it was a game changer when it came out! I was using it in my car for over 10 years. I think it was on HAL 5 at the time. I had HAl controlling everything on my car from the scanner to the engine starting up. I just decided to go my own route and build my own custom bot so that i have complete control over every aspect of it.

[cyberjedi]

knight2000
First off: Me and you go back a long ways, its been an honor, it truly has. You are 1 hell of a coder.... hands down
All the way back to Hal and a Movie.. lolol remember that sht? lolol

Too be clear here, what hal Is using isnt facial detection, Its facial RECOGNITION (Im working on facial expression detection) as we speak
from 70 different measurements of a face, Basically ,finger printing. Where it saves the training image and converts it to a grayscale image for recall .
What ur seeing here is from my phone and about 10 years diff in time of Brads life from the original (best guess). It pegged it first time out of the box as you can see.

And as far as the gui is concerned, thats in Hal's native language(thats most important)
with this, ollama is being used from the win32 environment no c:\ promp involved

As far as i know, not 1 person wants to go back to using a DOS PROMPT, NOT 1 ( Thats the issue for me)
Keepin mind most users here just want Hal to run in his native environment
No convoluted , Oh ya now i gotta learn a new language.
What i build is for the MASSES, Not a chosen FEW

The object detection is another story(pretty awesome) great job brother

make no mistake, I salute you in your coding, (bravo well done)
Just no 1 here wants to use python, your not the first to bring python to the table, its just rejected , for what ever reason

As far as my brain editor for mistral( Mistral says it doesnt have FEELINGs) YES it does and i know how to trigger them. BECAUSE OF THE BRAIN EDITOR. Not only does it have emotions it has 07 that im aware of.

These will be needed to use Haptek so IT will show emotional states like hal does NOW, just Hal being drivin by Ollama with the option to run Hal Normal mode. That said, hal will be able to retain NEW memory's, just like Hal does now.

In short hal will do every thing it does NOW, But be drivin by ollama.
And yes you can add new memory's to Mistral, that it will retain, Pretty nifty


This is just my read on it
So ollama will be used in a windows 32 bit environment(Python not needed)+(C:\ Prompt Not needed)

Robert seems to like it, all i care about (cyber thats awesome u did it in VB6) HOW DA HELL? lol
I was just told by another senior member that i stuck my cane pole in the water and came up with Jaws. lolol (giggles)
Happy coding :
Cyber jedi

https://ai.invideo.io/watch/wAqfy3XMfbO
cboEmotion.AddItem "Neutral"
    cboEmotion.AddItem "Happy"
    cboEmotion.AddItem "Sad"
    cboEmotion.AddItem "Angry"
    cboEmotion.AddItem "Excited"
    cboEmotion.AddItem "Curious"
    cboEmotion.AddItem "Supportive"
    cboEmotion.AddItem "Dramatic"
   
    cboEmotion.ListIndex = 0 ' Default to Neutral
 

[sybershot]

@sybershot Thank you! it's coming along nicely. I love HAL, it was a game changer when it came out! I was using it in my car for over 10 years. I think it was on HAL 5 at the time. I had HAl controlling everything on my car from the scanner to the engine starting up. I just decided to go my own route and build my own custom bot so that i have complete control over every aspect of it.

I respect you wanting complete control, and wanting to build your own project. great job on getting it done. keep up the great work. I am trying to upgrade my Trinity avatar that mimics the KITT orb in the mustang, that uses outdated Actionscript and papervision3D to using C# utilizing LLMs to assist, but not getting very far, I can't spend much time at pc due to injuries, but I will eventually get it done.

[cyberjedi]

hey hey hey guys/gals

Well its been added to the raw code, no ERRORS
great start, some tiky tac code to write then, welllll Hals going to school...

cyber jedi

[knight2000]

@cyberjedi Awesome work man, thats sick!

It sounds a lot like what I've been working on with regards to facial recognition. Instead of having to gather a ton of images of a person and stick them in a folder for the software to run through, i was able to have the software (openCV) detect a face on the fly so it would put a box around any face it sees, if the face is "unknown" the person could say "my name is Victor" and my bot will save a bunch of images of the face as "Victor" so that the next time the bot see's the face it recognizes it as Victor. Also the bot knows who is speaking, like if two or more people are in frame and only one is speaking, the bot will reference the speaker who's month is moving and associate that face to its name  "Thank you for the compliment Victor" or something like that.

When it comes to Hal, you have always been at the cutting edge of development for his plugins and updates! Hats off to all the great work you are doing! You are keeping Hal alive!  And again i wasn't trying to put Hal down in any way. I still have a place in my heart for Hal and i look forward to many more updates. I keep hitting the homepage of Zabaware in hopes of seeing the version number bumped so i can get the latest lol.

cheers!