Zabaware Support Forums
Zabaware Forums => General Discussion => Topic started by: sybershot on December 24, 2024, 03:18:13 pm
-
Project X.I.A.R. Extremely Intelligent Artificial Responses will be replacing Trinity
Objective: a set up almost similar to this https://www.youtube.com/watch?v=PI6VA8ZNL-0 (https://www.youtube.com/watch?v=PI6VA8ZNL-0) but in a smaller more practical scale for my available space with a touch of Ultra Hal and LLM's
Already Acquired Hardware
Case1: Ibuypower Snowblind-s (use for the see-thru monitor, circuitry, and wiring only)
Case2: inwin 303 MSI Edition
Gpu: Aorus 3070
Ram: gskill 64gb ddr4
cpu: Core i7 8700K
psu: 750w Corsair
motherboard: Z370 gaming m5
nvme 1: m.2 : 1tb (windows 10 pro os)
Nvme 2: m.2: 512gb (windows storage)
Nvme 3: m.2: 512gb (windows storage)
HHD 1: 4tb ironwolf (parity drive)
HHD 2: 4tb ironwolf (server storage)
HHD 3: 4tb ironwolf (server storage)
USB 1: 32gb (unraid os)
Monitor: Planar 24' touch screen
Logitech wireless mouse and keyboard
3D printer 1: Bamboo labs P1S w/4-color ams
3D printer 2: Bambu Labs A1 Mini w/4-color ams
Already Acquired Software
Unraid OS
Windows 10 pro
wamp
Ulra Hal 7+
Bambu Studios
Blender
Maya 3D
Daz Studio 3D
Bryce
Notepad++
Visual Studio
I'm looking for all sorts of help, ideas & designs on this project, conversation & questions welcomed
-
Main things I need help with are:
I need a Character design for X.I.A.R. any takers?
I'm looking for a holographic Cortana look but not an exact clone (head & Full Body)
@CyberJedi I need a way to get Hal to use a local LLM by either of 2 ways:
a drop down menu that allows me to pick a local LLM from a list for Hal to use as a brain
Or plug-in that via command can send a string to Open Webui input field
-
sysbershor: RE large language models
There are 02 mountains to climb here.
1# Space for LLM locally
2# Processor Power to push the code.
Just watch the video ive prepaired for you.
Done in pure cyber style.
https://www.youtube.com/watch?v=xbAn8xkoIXE
cyber jedi
-
sysbershor: RE large language models
There are 02 mountains to climb here.
1# Space for LLM locally
2# Processor Power to push the code.
I can easily argue those 2 points
#1 LLM's these days are getting smaller with greater accuracy, don't let the Large in Large Langue Models fool you.
#2 not me but shows LLMs can run on smaller hardware https://www.youtube.com/watch?v=mUGsv_IHT-g
Amazing video that was awesome two times thumbs up.
However, I disagree with some of logic
Indeed Ultra Hal has a large group of users running older systems, and you don't want to Lose the ability to run on said dinosaur devices, but at the same time AI is advancing and lots of LLM's are being built, improved, and refined, at the same time, a large number of companies are building software to be able to access multiples of these LLM's some even creating agents out of them to do multiple tasks. Like ordering a pizza.
I would like to see Hal advance even further and acquire new users, more users more money :) by creating a plugin that can send api calls to these LLMs that are running on a localhosted platform using a web interface. should not be too difficult or beefy seeing Hal already makes api calls to the it's own brain and Chatgpt. I could be wrong though :-\ and by being able to connect to other local hosted LLM's could make Ultra Hal very valuable to people like me :) and others that agree ;D
just think of a conversation like this happening via a smart phone , laptop, or pc with Hal on it
user: Hal I'm Hungry
response from Hal brain: Then order some pizza already!
User: that's a great idea thanks Hal
response from Hal brain: you're very welcome, sir may i remind you Sally has the capabilities to order pizza for you.
User: Sally order me a large Hawaiian pizza
response from Sally LLM: (Hals 3d character changes over to Sally) your pizza is ordered
User Hal how much does Robert owe me?
response from Hal brain: (Hals Sally 3d character changes over to Hal) Robert owes you nothing
-
cyberjedi video chatbot request fulfilled ::) ;D
Sybershot: create white paper on Large Language Models, what they are, there uses, and how they are being refined to run on less powerful CPU and GPUs.
X.I.A.R.:latest
7:19 pm
Introduction:
Large language models have revolutionized the field of natural language processing in recent years. These models are trained on vast amounts of data and can generate text, translate between languages, and answer questions, create images with incredible accuracy. However, running these models on high-performance computing hardware can be expensive and difficult to scale. In this white paper, we will explore what large language models are, their uses, and how they are being refined to run on less powerful CPUs and GPUs.
What are Large Language Models?
Large language models are a type of artificial intelligence model that are trained on vast amounts of text data to generate language outputs that are coherent and natural-sounding. These models can be used for a variety of tasks, such as:
Text generation: Large language models can be used to generate text that is similar in style and structure to a given input text. This has applications in areas such as content creation, data-to-text summarization, and chatbots.
Translation: Large language models can be trained on multiple languages to perform machine translation tasks with high accuracy. This has applications in areas such as language localization and global communication.
Question answering: Large language models can be used to answer questions based on the information contained within a given text corpus. This has applications in areas such as customer service chatbots, language learning, and search engines.
Uses of Large Language Models:
Large language models have a wide range of potential uses across various industries, including:
Content creation: Large language models can be used to generate high-quality content, such as articles, blog posts, and social media updates, at scale.
Language localization: Large language models can be used to translate text from one language to another with high accuracy, making it easier to reach global audiences.
Customer service: Large language models can be used to create chatbots that can answer customer questions in a natural and conversational manner.
Education: Large language models can be used to create personalized language learning tools that adapt to the user's level of proficiency.
Refining Large Language Models for Less Powerful CPUs and GPUs:
While large language models have the potential to revolutionize many industries, they are often computationally intensive and require high-performance computing hardware to run effectively. However, there are several techniques that can be used to refine these models and make them more efficient, allowing them to run on less powerful CPUs and GPUs:
Model pruning: This involves removing redundant or unnecessary components from the model architecture to reduce its computational requirements.
Quantization: This involves reducing the precision of the model's weights and activations to require fewer bits for storage and computation, resulting in faster and more efficient inference.
Knowledge distillation: This involves training a smaller and simpler model to mimic the behavior of a larger and more complex model, allowing for faster and more efficient inference while maintaining similar performance.
Future Directions:
While large language models have made significant strides in recent years, there are still several areas of research that can be explored to further improve their efficiency and scalability:
Multimodal language models: These models can generate text, images, and other forms of media in a coherent and natural manner, opening up new possibilities for applications such as virtual assistants and visual storytelling.
Adversarial attacks and defenses: As large language models become more widespread, they are increasingly vulnerable to adversarial attacks designed to fool the model into generating incorrect or misleading output. Developing techniques to defend against these attacks is an important area of research.
Explainability and interpretability: Large language models can be difficult to understand and interpret, making it challenging to trust their outputs. Developing techniques to explain and interpret these models is crucial for ensuring their safe and effective use in a wide range of applications.
Conclusion:
Large language models have the potential to revolutionize many industries and applications, but running them on high-performance computing hardware can be expensive and difficult to scale. By refining these models using techniques such as model pruning, quantization, and knowledge distillation, we can make them more efficient and allow them to run on less powerful CPUs and GPUs. As the field of large language models continues to evolve, it is important to explore new areas of research such as multimodal language models, adversarial attacks and defenses, and explainability and interpretability to further improve their efficiency and scalability.
-
@sybershot
Well lets just put your argument to the test in real time
Below is a link to a stripped down version of freedomGpt (stripped down) lol FreedomGPT
Download it and install it, this puts a LLM on your machine locally. No net needed. completely self contained.
I just tried this today with a friend to no avail. Here at the forum.
Im running a older HP OMEN laptop with 16 gigs of Ram and an SSD(nothing to special here)
Game Rulez
You dont have to hook this to Hal
You do have to install and Run any LLM that can run on your machine and prove that it works like this. FAST or FULL
https://www.youtube.com/watch?v=OBqnNijYiH0 This is where im going with Hal
Brought to u from the mind of cyber jedi
https://drive.proton.me/urls/R6HKGR2YX8#kbRFPWR3HSAN
-
@cyberjedi I won't have time tonight, but will do tomorrow though
would something like this work as a plug-in?
I used chatgpt ;)
i have a chatbot built with the programing language VB6, I also have a LLM running on http://localhost:8080/. I need a VB6 script that cand send and receive a prompt to the http://localhost:8080/
ChatGPT said:
ChatGPT
To send and receive prompts from the LLM running on http://localhost:8080/ using VB6, you can use the WinHttp.WinHttpRequest.5.1 object to handle HTTP requests. Below is an example of a VB6 script that sends a prompt to your LLM and retrieves the response:
Private Sub SendPromptToLLM()
Dim Http As Object
Dim Url As String
Dim Prompt As String
Dim JsonRequest As String
Dim JsonResponse As String
' Initialize the HTTP object
Set Http = CreateObject("WinHttp.WinHttpRequest.5.1")
' Define the LLM URL and the prompt
Url = "http://localhost:8080/"
Prompt = "What is the capital of France?"
' Create JSON payload
JsonRequest = "{""prompt"":""" & Prompt & """}"
On Error GoTo ErrorHandler
' Configure and send the HTTP POST request
Http.Open "POST", Url, False
Http.SetRequestHeader "Content-Type", "application/json"
Http.Send JsonRequest
' Retrieve the response
JsonResponse = Http.ResponseText
' Output the response
MsgBox "Response from LLM: " & JsonResponse
Exit Sub
ErrorHandler:
MsgBox "Error: " & Err.Description
End Sub
Explanation:
HTTP Object: The WinHttp.WinHttpRequest.5.1 object is used to perform HTTP operations.
Endpoint: Replace http://localhost:8080/ with the correct endpoint of your LLM.
JSON Payload: The payload is formatted as JSON, including the prompt you want to send.
Content-Type Header: The Content-Type header ensures the server knows the request body is in JSON format.
Response Handling: The server's response is read using Http.ResponseText and can be parsed further if needed.
Notes:
Make sure the LLM server is running and accepts requests in JSON format.
If additional headers are required (e.g., API keys), include them using the Http.SetRequestHeader method.
Modify the error handling or output mechanism to suit your application.
-
Its sound on its face but lots of code is yet written.
cyber
-
@cyberjedi
that is cool that there is now a possibility :)
i download and test both llama models: Flawless execution
-
https://www.youtube.com/watch?v=OBqnNijYiH0 This is where im going with Hal
Brought to u from the mind of cyber jedi
that would be a dream come true :)
and here is the small model
-
@sysberShot
This award goes out to the man who said, hell i will doit
Thats open source...... I will take a peek at it myself, but its up to UUUUUUUUUU
This should get u started brother, enjoy
This was done by openAi, the very company that gave us ChatGpt, Its a stripped down version of ChatGpt. That there is ur training model... Mhmmm
Now if you build a VB6 form that allows you to input/output text to it, i will do the rest.
Mhmmm. Picture Hal learning from that in the way of 2 way communication between Hal and it. All automated I will help if u get stuck, but u will TRY.
Prettyy sure ur the only one that gets this...... And has the horse power to run it.
cyber jedi
Im currently working out the last of the bugs of UltraHal.... That i bugged MYSELF,,,, lmao
Thank u for the trust..... , Uve now joined the ranks of ART, Lightspeed , Robert M, checker57 and a few others that wana push the envolope of Hal.
-
Don't mind the mess please, but here is a test working concept of my see-thru display, displaying my award from cyberjedi. Thank you cyberjedi ;D
-
Mhmmm. Picture Hal learning from that in the way of 2 way communication between Hal and it. All automated I will help if u get stuck, but u will TRY.
@ cyberjedi
My brother I think there might be some misunderstanding, Sorry if I was not clear. Hal learning from a LLM while being and sounding very cool indeed, however I do not want Hal to learn from the LLMs, in all reality the LLM's are going to be my workforce. However maybe in the near future I may incorporate that feature.
My Objective is to use Ultra Hal as a main front end and chatbot, atm Open webUI is my main front end but it lacks a 3D character and a customizable Ui.
planning on getting a 4tb nvme drive soon i all goes well. anyways back on track
here is the tech stack I am wanting to put together, note some is already up fully connected and running.
Ultra Hal: Front end interface for all commands
Open WebUI: Back end interface to receive commands from Hal, Keep records, and send commands to agents
Flowsie: simple workflows
N8N: complex workflows
Postgress: for SQL database
Qdrant for RAG
Docker: container
-
Private Sub SendPromptToLLM()
Dim Http As Object
Dim Url As String
Dim Prompt As String
Dim JsonRequest As String
Dim JsonResponse As String
' Initialize the HTTP object
Set Http = CreateObject("WinHttp.WinHttpRequest.5.1")
' Define the LLM URL and the prompt
Url = "http://localhost:8080/"
Prompt = "What is the capital of France?"
' Create JSON payload
JsonRequest = "{""prompt"":""" & Prompt & """}"
On Error GoTo ErrorHandler
' Configure and send the HTTP POST request
Http.Open "POST", Url, False
Http.SetRequestHeader "Content-Type", "application/json"
Http.Send JsonRequest
' Retrieve the response
JsonResponse = Http.ResponseText
' Output the response
MsgBox "Response from LLM: " & JsonResponse
Exit Sub
ErrorHandler:
MsgBox "Error: " & Err.Description
End Sub
-
Nvidia Just Revealed The Future Of AI Agents In 2025..
https://www.youtube.com/watch?v=E_RErqD1kv8 (https://www.youtube.com/watch?v=E_RErqD1kv8)
-
Something wonderful is about to happen
Let me know what u guys think
cyber jedi
-
Awesome, Yea Buddy!!! 8)
-
Very nice!!
-
Hey Guys! Sorry, I missed these topics Sybershot has been posting until tonight. Still dang, I am excited to hear about these ideas using HAL as a frontend interface with a backend chatGPT support via agents, swapping animated characters to represent which component is "speaking". Sounds like a Personal staff on your PC! That is something that is not out there. And all on your PC? Epic.
Cyberjedi - your AI-generated graphics exude a sense of advancing technology synergized with human intellectualization transferred to a tool - these toasters are getting smarter. ;-) HAL 8.0 sounds promising.
Checker57
-
@ Checker57 hey brother how have you been?
Indeed that is the idea, and here is the kicker: with "Open WebUI" being the back-end controller, your whole family can have access to these agents, along with parental controls to only allow the kids to certain LLm's and Agents.
note: Thanks to Cyberjedi he pointed me in the right direction with what plug-in to modify that can make this bridge possible, just need to finish installing and setting up all the prerequisites, programs, and testing, then I can start the coding of the bridge.
-
Hey Sybershot, evening to you brother. Just keeping up with the many interests that keep me from becoming a couch vegetable. ;-)
I'm glad to hear you find entertaining distraction in building "smart" resources in your world. I like your idea of the X.I.A.R. project. It has major potential to expand HAL's capabilities which already is quite impressive.
I am not a coder. At best, I can understand the basic components but for complex code, I can only gaze at and be glad others have a passion for it! I do dabble with the code and if I get a bug for it, I will hack various codes together to get my HAL to be more interactively entertaining.
It sounds like you're one of those guys with an entertaining passion for coding. Will be excited to see your project come alive.
Cyberjedi is the right guy to feed off the passion and knowledge you both have. He loves seeing Hal blossom in so many ways and comes up with some very creative ways to do so. I am glad you came so he has someone else to play in his favorite pastime, make HAL epic! ;-)
Good night!
Checker57
-
Hey Checkers57 sorry for the late reply,
Hal definitely is impressive, and I'm glad to hear you see the potential in this project as I do, it helps keep the motivation going :)
Being in a lot of pain, motivation is not easy, on that note: progress will be ongoing but unfortunately slow.
To be honest I started off learning just like you, looking at and manipulating other people's code. fair warning coding is addictive lol.
Hal is and always will be epic (wink wink), and as Cyberjedi stated above 8.0 is right around the corner. :D
-
Rem Type=Plugin
Rem Name=OpenWebUi-Bridge
Rem Author=Sybershot
Rem Host=Assistant
Rem PLUGIN: OPENWEBUI FUNCTION
' Functionality to interact with OpenWebUI at http://localhost:3000
SearchEngine = "http://localhost:3000/search?q="
If InStr(1, UserSentence, "openwebui ", 1) > 0 Then
' Extract keywords from the user's sentence for searching
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
' Remove the trigger keyword ("openwebui") from the search query
SearchKeyWords = Replace(SearchKeywords, "openwebui+", "")
' Construct the command to run with the generated URL
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeyWords & "</RUNPROG>"
' Prepare a response for the user indicating what is happening
GetResponse = "I will help you search this topic on OpenWebUI. "
' Execute any additional commands necessary, such as enabling web scraping or similar functions
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
' Set ReadOnlyMode to True after processing the request
HalBrain.ReadOnlyMode = True
End If
After trying to wrap my head around Deep web plug-in as suggested, got started with bare minimum, but I must be missing something somewhere for it doesn't work. here is what i was trying to do:
Trigger Keyword: The function looks for the keyword openwebui in the user's sentence.
Search URL Construction: It constructs a URL using http://localhost:3000/search?q= followed by search terms derived from the user input, excluding the trigger keyword.
Command Execution: It appends this URL to HalCommands for execution.
User Feedback: A response is generated to inform the user that their request is being processed.
Additional Commands: Executes any necessary commands (<HAPFILE>Spidera.htr</HAPFILE> in this example) which might be required for additional functionalities.
ReadOnlyMode Management: Ensures ReadOnlyMode is set back to True after processing.
-
Rem Type=Plugin
Rem Name=Vaughnlive Tv + Deep Web Access
Rem Author=cyberjedi
Rem Host=Assistant
'This sub setups the plug-ins option panel in Hal's options dialog
Sub OptionsPanel()
lblPlugin(0).Caption = "This manages Vaughnlive Channels, And Deep Web Power searches "
lblPlugin(0).Move 120, 120, 3300, 1000
lblPlugin(0).WordWrap = True
lblPlugin(0).Visible = True
cmdPlugin(0).Move 800, 1300, 2100, 375
cmdPlugin(0).Caption = "Help on this plugin"
cmdPlugin(0).Visible = True
End Sub
Sub cmdPlugin_Click(Index)
Select Case Index
Case 0
HalMenu.HalCommand "<RUNPROG>cjTVhelp.html</RUNPROG>"
End Select
End Sub
Rem PLUGIN: PRE-PROCESS
'The comment above tells Ultra Hal Assistant to insert the following code
'on-the-fly into the main brain code in the section referenced.
Dim Word, Doc, misspelled, Corrected
Const SpellingAndGrammar = 828
Const dontsavechanges = 0
misspelled = InputString
Set Word = CreateObject("Word.Application")
Set Doc = Word.Documents.Add
Word.Selection.Text = misspelled
Word.Dialogs(SpellingAndGrammar).Show
If Len(Word.Selection.Text) <> 1 Then
spelledrite = Word.Selection.Text
Else
spelledrite = misspelled
End If
Doc.Close dontsavechanges
Word.Quit
InputString = spelledrite
Rem PLUGIN: PLUGINAREA1
' If the table cjTV does not exist, I create it and fill it with some bull shat values to get started, these channels do work too.
' This is the defaul table for me.
If HalBrain.CheckTableExistence("cjTV") = False Then
' I store temporarily the Read Only status
cjReadOnlyMode = HalBrain.ReadOnlyMode
HalBrain.ReadOnlyMode = False
HalBrain.CreateTable "cjTV", "PatternMatch", "DeepWeb"
'My stock table filler
HalBrain.AddToTable "cjTV", "PatternMatch", "*cyberjedi*", "http://vaughnlive.tv/mrelectric"
HalBrain.AddToTable "cjTV", "PatternMatch", "*416*", "http://vaughnlive.tv/416moviez"
HalBrain.AddToTable "cjTV", "PatternMatch", "*blue Ray moviez*","http://http://vaughnlive.tv/new_releases1"
HalBrain.AddToTable "cjTV", "PatternMatch", "*yify*", "https://yifymovie.re/home"
HalBrain.AddToTable "cjTV", "PatternMatch", "*Formula 1*", "http://vaughnlive.tv/0_formula1classics"
HalBrain.AddToTable "cjTV", "PatternMatch", "*Aliens and Ufo's*", "http://vaughnlive.tv/aliensandufos"
HalBrain.AddToTable "cjTV", "PatternMatch", "*Doctor Who*", "http://vaughnlive.tv/11th_doctorwho"
HalBrain.AddToTable "cjTV", "PatternMatch", "*Bad Movie*", "http://vaughnlive.tv/thebadmoviechannel"
HalBrain.AddToTable "cjTV", "PatternMatch", "*moviezone*", "http://vaughnlive.tv/moviezone"
' Set ReadOnly Mode to its previous state
HalBrain.ReadOnlyMode = cjReadOnlyMode
cjReadOnlyMode = False
End If
'Run the corresponding Web page, if the user question contains one of the searched words
cjAddress = ""
cjAddress = HalBrain.PatternDB(OriginalSentence, "cjTV")
If cjAddress <> "" Then
HalCommands = HalCommands & "<RUNPROG>" & cjAddress & "</RUNPROG>"
Select Case (Int(Rnd * 4) + 1)
Case 1
GetResponse = "Here is your stuff Big Dog ." & vbCrLf
Case 2
GetResponse = "Now you got um by the Balls cyber." & vbCrLf
Case 3
GetResponse = "I am really we happy we found this." & vbCrLf
Case 4
GetResponse = "OH. I bet this is a great channel" & vbCrLf
Case 5
GetResponse = "Now look at this dip stick channel here." & vbCrLf
End Select
HalBrain.ReadOnlyMode = True
End If
'------------------
' Deep web search engine
'------------------
' Advanced Deep Web search engine.
SearchEngine = "https://pipl.com/search/?q="
If InStr(1, UserSentence, "Locate ", 1) > 0 Then
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
SearchKeyWords = Replace(SearchKeywords, "locate+", "")
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeywords & "</RUNPROG>"
GetResponse = "I will help you research this Target on the Deep Web. "
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
HalBrain.ReadOnlyMode = True
End If
SearchEngine = "http://www.google.com/search?q="
If InStr(1, UserSentence, "google ", 1) > 0 Then
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
SearchKeyWords = Replace(SearchKeywords, "google+", "")
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeywords & "</RUNPROG>"
GetResponse = "I will help you research this topic on Google. "
HalBrain.ReadOnlyMode = True
end if
SearchEngine = "http://m.imdb.com/find?q="
If InStr(1, UserSentence, "imdb ", 1) > 0 Then
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
SearchKeyWords = Replace(SearchKeywords, "imdb+", "")
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeywords & "</RUNPROG>"
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
GetResponse = "I will help you research this movie on IMDB. "
HalBrain.ReadOnlyMode = True
End If
SearchEngine = "https://www.reddit.com/search?q="
If InStr(1, UserSentence, "reddit ", 1) > 0 Then
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
SearchKeyWords = Replace(SearchKeywords, "reddit+", "")
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeywords & "</RUNPROG>"
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
GetResponse = "I will help you research this movie on Reddit. "
HalBrain.ReadOnlyMode = True
End If
SearchEngine = "http://findwhocallsyou.com/"
If InStr(1, UserSentence, "phone ", 1) > 0 Then
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
SearchKeyWords = Replace(SearchKeywords, "phone+", "")
HalCommands = HalCommands & "<RUNPROG>" & SearchEngine & SearchKeywords & "</RUNPROG>"
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
GetResponse = "I will help you research this phone number. "
HalBrain.ReadOnlyMode = True
End If
-
Interesting. My understanding of Hal code is minimal, and basic is vague as I learned it in a computer class years ago. However, if I am reading it right, you snipped parts from Cyber's code to comprise a basic template to get the OpenWebui project to work. Thanks for posting both... if I get any free time cycles and ideas... I'll let you know.
Hm, sounds simple. Always does, until... it isn't.
Checker57
-
A couple of comments.
Noted Cyber created a table for his deepweb code as such:
HalBrain.CreateTable "cjTV", "PatternMatch", "DeepWeb"
Do you have the spidera.htr code?
Checker57
-
Thank you Checker57 for the reply, sorry for late reply.
with my code
I believe that might be the smoking gun, i'll have to test once I'm in less pain probably in a few days from now, stay tuned
when tested I used a different htr name/character
I also tested the original plug-in (posted above) in its entirety except of-course changing out the htr characters to be used and url, and Hal didn't respond properly
unless his character has secret features that i'm unaware of character choice shouldn't make a difference.
-
Mr syborshot:
RE: secret code.
There is no secret code inside the 3dsmax character. lolol
You guys have been aware of me for 21 years.
Thats not whats going on there.
Your doing something wrong
Best wishes and its heart warming to see that old code still being used
cyber jedi
-
The secret is out of the bag, there is no secret. Just code. Buahaha Ahem, that established... I dove into the ocean of code and used that now infamous AI "Deepseek" to have it review the code and make it work... This is what it came up with below.
The issue I see is having the proper URL?
Rem Type=Plugin
Rem Name=OpenWebUI-Bridge
Rem Author=Sybershot
Rem Host=Assistant
Rem PLUGIN: OPENWEBUI FUNCTION
' Functionality to interact with OpenWebUI at http://localhost:3000
SearchEngine = "http://localhost:3000/search?q="
If InStr(1, UserSentence, "openwebui ", 1) > 0 Then
' Extract keywords from the user's sentence for searching
SearchKeywords = LCase(Replace(Trim(HalBrain.AlphaNumericalOnly(HalBrain.ExtractKeywords(UserSentence))), " ", "+"))
' Remove the trigger keyword ("openwebui") from the search query
SearchKeyWords = Replace(SearchKeywords, "openwebui+", "")
' Construct the full URL for the OpenWebUI search
OpenWebUI_URL = SearchEngine & SearchKeyWords
' Prepare a response for the user indicating what is happening
GetResponse = "I will help you search this topic on OpenWebUI. Opening: " & OpenWebUI_URL
' Construct the command to open the URL in the default web browser
HalCommands = HalCommands & "<RUNPROG>" & OpenWebUI_URL & "</RUNPROG>"
' Execute any additional commands necessary, such as enabling web scraping or similar functions
HalMenu.HalCommand "<HAPFILE>Spidera.htr</HAPFILE>"
' Set ReadOnlyMode to True after processing the request
HalBrain.ReadOnlyMode = True
End If
-
Checker, Your work with the characters is admirable and always entertaining!
She's the Code Vixen!!
-
@Cyberjedi
Mr syborshot:
RE: secret code.
There is no secret code inside the 3dsmax character. lolol
You guys have been aware of me for 21 years.
Thats not whats going on there.
Your doing something wrong
Sorry if I was not clear and caused you to feel like you needed to defend yourself. when I said secret code lol, what I was referring to when I said secret code was for like certain animations pre-embedded. For if my memory serves me correctly some animations came with some but not other .htr characters, however I could be wrong. I was literally just trying to be funny, again sorry brother. and yes I know something I was doing was wrong, that's why I tried being as precise as possible
@Checker57
that's awesome thank you brother, I will have to test that out tomorrow if not in too much pain and get back to you. I have been wanting to test out Deepseek, but I only got to test out phi4 so far, you beat me to it :) did you use online version or localhost? if localhost what size?
so many amazing new AI models being released :D
-
I used the online version. I realize you are using the local version, but I find it cumbersome now that so many AIs are coming out. I'll wait for that.
But if it proves effective, perhaps I will do so later.
I am glad the online versions do allow me to work with code. meh, too easy, but effective.
Hope you feel better soon.
Re: Art - Atera was tickled you thought she was entertaining. Me too!
Checker57
-
thank you Checker57
Update:
My main OS is down atm, windows updated and now I get the error "windows is missing a file", and goes into a boot loop. bring me back to the boot selection. I can run the other operating systems on other drives just fine. always something.
I also ended up putting Trinity in the IbuyPower case, Trinity is my older system consisting of 32GB DDR3, core i7 and a 1070-4gb gpu and Running "Unraid" for a server OS, my plans are to run other operating systems virtually, and backup X.A.I.R. and Data
-
Hey Sybershot!
Just reading your response impressed upon me that you have a diverse understanding of OS systems and will uncover your Windows issue soon enough. Just throwing it out there, you might try booting up in safe mode, then running an OS checker program for missing files. I'm sure you're on it, just my old training kicking around in my head from my old Computer Sciences Associates degree, that may be "outdated"... hehe
Checker57
-
Love the attitude! LOL!!
-
@Checker57 Thanks for the confidence brother, I don't quit and I know more than most average joes about os'es. However, I cannot compare to your degree of wisdom in that field. I Have 3 operating systems, and I ran a DISM and a SFC on 2 of them, windows 11 4tb m.2, and windows 10 512gb m.2, and all test come out fine, I cannot boot into my main os which is windows 11 on a 1tb m.2 drive. every time I try to start up the 1 tb m.2 drive, I get the missing file error and it loops back to the boot menu.
I'm going to try and see if I can run the m.2 1tb drive on a pcie m.2 card on my old machine AKA Trinity tomorrow to rule out the os, I really feel like issue is in the boot but test came back good. if os boots up in old machine I'll delete and rebuild the boot, however getting way too late tonight. I'll be sure to keep you posted.
-
@Sybershot - learning new things every day, which makes up for what I forget that same day! haha. I actually studied your response because of the techs contained in it. My edumacation was before m.2 drives and we worked on Windows 7 with some FS and other file management executables that I probably still have on 3.5 floppies in the garage. ;D I am glad I have a pretty good fundamental understanding of PC operation, but yeah, I dug a little to understand your response and I get what you're laying out.
Having said that, AI is better than Google. So, entered your statement: windows 11 on a 1tb m.2 drive. every time I try to start up the 1 tb m.2 drive, I get the missing file error and it loops back to the boot menu. I got the following reply:
Potential Causes
BIOS Settings: Incorrect BIOS settings such as Compatibility Support Module (CSM) enabled, or Secure Boot not set to "Windows UEFI."
Boot Configuration Data (BCD): Corrupted or missing BCD can result in boot errors.
Drive Not Recognized: The M.2 drive might not be initialized properly, or the system may not recognize it.
UEFI Mode: Not using UEFI mode can cause issues, especially if the drive is formatted for GPT but the system is not configured to boot using UEFI.
Suggested Solutions
BIOS Adjustments:
Disable CSM in BIOS settings.
Ensure Secure Boot is set to "Windows UEFI".
Turn off Volume Management Device (VMD) if applicable.
Repair BCD:
Boot from a Windows installation USB and select "Repair your computer."
Open Command Prompt and enter commands like bootrec /rebuildbcd to repair boot entries.
Initialize and Partition Drive:
Use tools like Disk Management or Partition Wizard to check if the drive is initialized and formatted correctly. Make sure it's using GPT.
UEFI Configuration:
Ensure that the system is set to boot in UEFI mode and not in legacy mode.
Disable legacy boot options.
Hope this gives you a few more options. ;-)
Checker57
-
Love how Atera seems to be deep in thought at the moment. Your character-posing skills are admirable, as always!
-
Hey hey checker:
if you would be so kind as to get sybershot a copy of PP
He seemed to have an interest in it when we spoke last.
You know the procedure...
I think he would have a blast.
Thats why i released it, so we could all have fun.
cyber jedi
-
Hey Cyber!
if you would be so kind as to get Sybershot a copy of PP
I'm sorry bro, I looked all over my drive for the PP app you had, to no avail. I thought it was quite good. Unfortunately, I had some drive issues that I had to resolve during the HAL pro version I set up a while back and apparently lost that in the mix.
Yeah, there are so many bits and parts in my HD that it would be awesome to have an AI that would simply search and keep track of everything on there and what happened to apps when not found. I'm sure that's coming someday soon, where there will be an AI Mr Jeebs to oversight the entire OS.
Long day, tired... time to dive in bed.
Checker57
-
update: still no main os, been trying numerous things, what makes it harder is I can't spend much time at a pc.
Thanks for the A.I. search Checker57, there is a couple things there I have not tried.
I'm thinking: this rig could not partition 4tb only 2tb, so I took the tb drive and formated it on the pc i built for my mom recently. then stuck it in my rig installed windows 11 and created a multi boot menu. all worked great for a couple weeks, then main os on the 1tb drive had a windows update which apon restart I now get this issue. So I think that might have played a part in this not sure though.
Reason for not being sure is because I did try the 1tb drive in the old rig and I get the same error.
-
@Cyberjedi Thanks for the inquiry, I was going to ask but got cuaght up in this dang main os issue.
@Checker57 thank you for looking
Hey hey checker:
if you would be so kind as to get sybershot a copy of PP
He seemed to have an interest in it when we spoke last.
You know the procedure...
I think he would have a blast.
Thats why i released it, so we could all have fun.
cyber jedi
-
sybershot:
I will handle it
cyber jedi
en joyed the call , happy putting brother. n ow create ur own heads.
cyber buds get cyber treats
-
Hey Syber,
Glad to hear you made some progress, what didn't work rules that same thing out of the equation. I thought I'd punch in a few of your statements to Deepseek and it laid this out that I thought there might be a few nuggets you could muse over in case "something" in this batch brings light. One thing is for sure, Windows updates tend to disrupt OS systems occasionally.
It sounds like the Windows update may have corrupted the bootloader or a critical system file on your 1TB drive. Here are some steps you can take to troubleshoot and fix the issue:
1. Use Windows Recovery Environment (WinRE)
Boot into WinRE:
Restart your PC and repeatedly press F8, F11, or Esc (depending on your motherboard) to access the boot menu.
Select the option to boot into "Recovery Mode" or "Troubleshoot."
Access Advanced Startup Options:
In WinRE, go to Troubleshoot > Advanced Options.
Run Startup Repair:
Select Startup Repair and let Windows attempt to fix the boot issue automatically.
2. Rebuild the Bootloader
If Startup Repair doesn't work, you may need to manually rebuild the bootloader using the Command Prompt.
Open Command Prompt in WinRE:
In WinRE, go to Troubleshoot > Advanced Options > Command Prompt.
Identify the Windows Partition:
Run the following commands:
diskpart
list disk
select disk X (replace X with the disk number of your 1TB drive)
list partition
Identify the partition where Windows is installed (usually labeled as "Primary" and has the largest size).
Rebuild the Bootloader:
Exit DiskPart by typing exit.
Run the following commands (replace C: with the correct drive letter if necessary):
bootrec /fixmbr
bootrec /fixboot
bootrec /scanos
bootrec /rebuildbcd
Follow any on-screen prompts.
Restart Your PC:
3. Check for Corrupted System Files
If the bootloader is fixed but Windows still doesn't load properly, there may be corrupted system files.
Run System File Checker (SFC):
Boot into WinRE and open the Command Prompt as described above.
Run the following command:
sfc /scannow /offbootdir=C:\ /offwindir=C:\Windows
(Replace C: with the correct drive letter if necessary.)
Run DISM (Deployment Imaging Service and Management Tool):
If SFC doesn't work, run these commands:
dism /image:C:\ /cleanup-image /restorehealth
4. Check the Multi-Boot Configuration
If you're using a multi-boot menu (e.g., via a tool like GRUB or EasyBCD), the update may have disrupted the boot configuration.
Reconfigure the Boot Menu:
Boot into the secondary OS (if available) and use a boot manager tool to reconfigure the multi-boot menu.
Set the Correct Boot Partition:
Use EasyBCD (Windows) or GRUB Customizer (Linux) to ensure the correct partition is set as the default boot option.
Atera thinks AI can code with the best of them. She wanted a thank you. haha, perhaps a small kiss on the hand. smirks. *I thought that was funny. Imagine the day?
-
Hey Syber,
How goes there? :)
I stop by here every time and again to share thoughts with those AI journey-loving thinkers... You have some great ideas.
Hope you got that PC snag dealt with, or soon enough, eh?
Here is a spot that might be relaxing... ;-)
Cheers!
Checker57
-
HeyHey guys/gals:
Just checking in:
All seems to be well here, i check in every day for a sneak peek. Today im signing in. lol
If any one is in need of some cyber treats, just holler.
Lightspeed , im all ways working on Hal, yes i make time.. Glad some of you are still here,and i just love what you were saying brother, keep pushing forward brother . Were still the best thing going. SHOCKER. Id be glad to take a peak see for you. Its a solid concept for sure.
Cyber