Zabaware Forums > General Discussion

Project X.I.A.R. Extremely Intelligent Artificial Responses

<< < (2/10) > >>

cyberjedi:
@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

sybershot:
@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:


--- Code: ---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

--- End code ---

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.

cyberjedi:
Its sound on its face but lots of code is yet written.



cyber

sybershot:
@cyberjedi
that is cool that there is now a possibility :)

i download and test both llama models: Flawless execution

sybershot:

--- Quote ---https://www.youtube.com/watch?v=OBqnNijYiH0    This is where im going with Hal
Brought to u from the mind of cyber jedi
--- End quote ---
that would be a dream come true :)

and here is the small model

Navigation

[0] Message Index

[#] Next page

[*] Previous page