Nea (macOS)

100% SwiftUI GPT/LLM Client with Prompt Engineering support. With Microsoft's Azure OpenAI functionality.

General Query View	Prompt Studio

Table of Contents

Requirements
Swift Packages & Credits
Setting Up Azure OpenAI
Persisting Chat Messages
Guide WIP
FAQ
More Previews
TODO

Requirements

macOS 12.4+ Build passing 🟢

Swift Packages & Credits

Granite
- This app uses my own design pattern. A decoupling guide will be provided in the repo above. But, should be pretty straightforward overall.
VaultKit
SwiftGPT by @SwiftedMind
GPT3-Tokenizer by @aespinilla
swiftui-markdown by @jaywcjlove
Ink by @JohnSundell
LaunchAtLogin by @sindresorhus
PureSwiftUI by @Brett-Best

Locally Diverged

[SandKit] is a private repo at the moment, diverged a localized version for use. It houses SwiftGPT and swiftui-markdown from above as well. This kit handles custom prompt/command routing for the applicatoin.

Removed

[MarqueKit] is a private repo that handles encryption this has been removed and comments show where encryption can take place to safely store data like API Keys.

Setting Up Azure OpenAI

Enable Azure in Settings

In SandGPT, setup the config to match your Azure OpenAI Resource/Deployment/ApiKey

static var AZURE_CONFIG: ChatGPTAzure.Config {
    .init(apiKey: "...",
          apiVersion: "2023-05-15", //apiVersion not necessary for initialization
          resourceName: "...",
          deploymentName: "...")
}

Persisting Chat Messages

Repo will be updated to include this out of the box, front-end side, in the future.

Back in SandGPT: https://github.com/pexavc/Nea/blob/24fbcfbac23eb7f13b84cdee6307211596ee54d0/Services/Sand/Models/SandGPT.swift#L48

Simply build a flow to store the type ChatMessage prior to using the Swift Package.

private var messages: [ChatMessage] = []
    
func ask<E: EventExecutable>(_ prompt: String,
                             withSystemPrompt systemPrompt: String? = nil,
                             withConfig config: PromptConfig,
                             stream: Bool = false,
                             logMessages: Bool = false,
                             event: E) {

Append the user prompt with the role user.

self.messages.append(.init(role: .user, content: prompt)) //add user prompt

Append the chat-bot's response with the role assistant.

reply = try await client.ask(messages: self?.messages ?? [],
                                                         withConfig: config)
                            
DispatchQueue.main.async { [weak self] in
    self?.isResponding = false
}
    
if logMessages {
    self?.messages.append(.init(role: .assistant, content: reply))
}
    
event.send(Response(data: reply, isComplete: true, isStream: false))

The role .system is good for setting a persona prior to message collection.

self?.messages.append(.init(role: .system, content: "Act as..."))

Linking the reset() function in SandGPT() to clear messages is helpful too:

func reset(messages: Bool = false) {
    self.currentTask?.cancel()
    self.reqDebounceTimer?.invalidate()
    self.replyCompletedTimer?.invalidate()
    self.isResponding = false
    
    if messages {
        self.messages = []
    }
}

Guide

PaneKit

Window resizing and size management occurs here.

Declaritevly update a single window's size whenever an action requires

state.pane?.display {
    WindowComponent(WindowComponent.Kind.query)
    
    if addResponse {
        WindowComponent(WindowComponent.Kind.divider)
        
        WindowComponent(WindowComponent.Kind.response)
        
        WindowComponent(WindowComponent.Kind.spacer)
        
        WindowComponent(WindowComponent.Kind.shortcutbar)
    }
}

InteractionManager

Popups and Hotkey observation/registration

Example of Using PopupableView to easily trigger popups in any window instance.

PopupableView(.promptStudio,
              size: .init(200, 200),
              edge: .maxX, {
    RoundedRectangle(cornerRadius: 6)
        .frame(width: 60, height: 60)
        .foregroundColor(Color(hex: promptColor))
}) {
    ColorPicker(hex: $promptColor)
}
.frame(width: 60, height: 60)

FAQ

Why chat completions over completions for prompts?

No specific reason besides, finding it to provide better results for my own needs.
Completions endpoint capability will be added soon along with a toggle to switch between.