Messages

1

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« on: October 02, 2025, 04:55:18 pm »

@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!

2

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« on: September 29, 2025, 01:10:13 pm »

@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.

3

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« on: September 28, 2025, 10:12:46 am »

I'm using Ollama with Mistral 7b model for my KITT replica AI software. It runs 100% offline. I was using Hal for over 10 years before stumbling onto the amazing piece of software. Its an end of an era for me and HAL. But with Mistral I get great conversions and i've been able to get the latency down to 2-3s from the time i speak to the time i hear the first word of the response. Check out this video for a demo
https://youtube.com/shorts/LxSMMIZMUJ0?si=VhXcu7_SlCma6AXZ

4

General Discussion / Re: Sending Hal's response to python script?

« on: November 06, 2024, 03:10:40 pm »

Thanks cyberjedi, i'll play around with that and see what happens.

5

General Discussion / Re: Sending Hal's response to python script?

« on: November 04, 2024, 11:26:22 am »

I don't mean make Hal open source, there are plenty of tools to encrypt python making it very difficult to interrupt or back engineer. Look into pyinstaller or cx_freeze, they convert the python code into an exe. Anyways, i know it would be a huge undertaking so i get not wanting to do it, but if the whole reason is because you don't want it to be shared through open source, there are ways around that. I love the hell out of Hal, it's the best offline chatbot for sure. But, it's also the reason i'm stuck running Windows instead of Linux.

In regards to this portion

Code: [Select]

vb
Copy code
' VB6 Code to send a message to Python by writing to a file

Private Sub btnSend_Click()
    Dim message As String
    Dim filePath As String
   
    ' Get the message from the text box
    message = txtMessage.Text
   
    ' Define the file path where the message will be saved
    filePath = "C:\Temp\message.txt"
   
    ' Open the file for output and write the message
    Open filePath For Output As #1
        Print #1, message
    Close #1
   
    MsgBox "Message sent to Python!", vbInformation
End Sub
This VB6 code writes the content of txtMessage to C:\Temp\message.txt. Ensure the C:\Temp directory exists on your computer.
Is this the best we can do in terms of intercepting Hals response? My goal is to not have Hal speak the response but instead have my speech server speak it. Im wondering if i can create a plugin for Hal that will intercept all responses. Or even better, get the response text even before Hal's speech synthesis has a chance to generate the voice. I hope that makes sense.
Now that i think of it, a plugin would most like cause even more of a delay in response. I have Hal set as 0 for the response time currently and its very fast. I may have to figure out a way to just install my own sapi5 engine. Anyways, thank you for the help. I'll reach out if i need more help!

6

General Discussion / Re: Sending Hal's response to python script?

« on: November 03, 2024, 01:05:44 pm »

Thanks! Ill look into it.

The next evolution should be porting Hal over to python, then we could run it on anything!

7

General Discussion / Re: Sending Hal's response to python script?

« on: November 02, 2024, 11:30:59 am »

Thanks for the reply!

build a GUI in vb6 that will do the same just using SAPI 05

So are you saying to build a sapi5 speech engine for my cloned voice? To then use in Hal? I believe there is a way to communicate with my python server through sapi5. But would it work with Hal? That's the question.

8

General Discussion / Sending Hal's response to python script?

« on: November 01, 2024, 05:24:37 pm »

Hey All,

I created a voice model (cloned voice). i have a python server set up to receives text, when it receives the text it then runs it through the model and outputs the text as the generated voice.
What i'm interested in doing is, speaking to Hal and having the voice speak Hal's response. To do this, I would need to intercept Hal's response and send it to a python script that would make the server call. Does anyone know how i could intercept the response? I know how to run commands when Hal receives certain words or phrases. Would it be similar to that?

9

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 18, 2023, 03:08:34 pm »

I have a few plugins that I wrote for Hal that are running while training. But I do not have any plugins for training Hal specifically. I can just stick to one sentence at a time.

10

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 17, 2023, 07:15:31 pm »

Hey Art, one more question in regards to training Hal. I'm going through the text files you sent me. Can I copy and paste a bunch of sentences all at once into Hal's input box? Or do you recommend one sentence at a time? Could i paste the entire doc of sentences?

11

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 15, 2023, 01:47:40 pm »

Thanks Art 

12

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 14, 2023, 11:09:14 pm »

Wow! This is good stuff! Thank you for the info, this really helps. And thanks for the files, I will definitely feed them to Hal.

When feeding Hal info like this, do I need to turn up Hal's learning level? Or is the middle level ok for this? The brain I'm using allows for setting Hal's learning level. I would think the "no brainer" would be to turn it all the way up when training him. But wanted to ask anyways.

Thanks again!

13

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 13, 2023, 10:22:24 pm »

Hal seems to be running "ok", I ran Malwarebytes and found nothing.

Are there any brains out there for download that have a ton of knowledge? Hal's replies are not of the best quality. Or maybe you have tips on how I can train him better?

Is it possible to train Hal from a text document? 

14

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 13, 2023, 10:53:56 am »

Thanks Art! Ill keep you posted

15

Programming using the Ultra Hal Brain Editor / Re: Getting an error opening brain editor

« on: October 12, 2023, 07:49:59 pm »

Hey Art!

I have the same version as you and the size is the same, my modification date is 12-10-2017. I tried running the editor in compatibility mode but still no luck. I'm also noticing weirdness when speaking to Hal. short words like "hey" or "hi" do not produce a response and Hal seems to lag. I say that because after a few seconds each of the short words I spoke all show in his input section at once as if I spoke them one after the other. That could be the pc acting up, not sure. Maybe I should try re installing Hal? I'm running 7.5