Skip to content

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

License

Notifications You must be signed in to change notification settings

ronaldmannak/enchanted

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Swift Release Stars iOS macOS visionOS

Enchanted

Enchanted is open source, Ollama and Pico AI Homelab compatible, elegant macOS/iOS/visionOS app for working with privately hosted models such as Llama 2, Mistral, Vicuna, Starling and more. It's essentially ChatGPT app UI that connects to your private models. The goal of Enchanted is to deliver a product allowing unfiltered, secure, private and multimodal experience across all of your devices in iOS ecosystem (macOS, iOS, Watch, Vision Pro).

If you like the project, consider leaving a ⭐️ and following on 𝕏.

App Store

Note: You will need to run your own Ollama server or Pico AI Homelab server to use the app. Read instructions below.

Demo

Vision Pro Demo

Showcase

Macbook

image

Dark mode

image

Settings

Completions

Use from anywhere

invoke.mp4

Build custom prompt templates and use anywhere

Xnapper-2024-05-02-18 57 19
summarise.mp4

Custom completion

customcompletion.mp4

iPhone

Multimodal

Markdown

Conversation history

Xnapper-2024-05-03-12 00 28

Vision Pro

image image
  • Text to Speech (Read Aloud)
  • Conversation history included in the API calls
  • Dark/Light mode
  • Conversation history is stored on your device
  • Markdown support (nicely displays tables/lists/code blocks)
  • Voice prompts
  • Image attachments for prompts
  • Specify system prompt used for every conversations
  • Edit message content or submit message with different model
  • Delete single conversation / delete all conversations
  • macOS Spotlight panel Ctrl++K
  • All features works offline

Usage instructions

Enchanted requires Ollama v0.1.14 or later.

Case 1. You run Ollama server with public access

  1. Download Enchanted app from the App Store.
  2. In App Settings specify your server endpoint.

You're done! Make a prompt.

Case 2. You run Ollama on your computer

Video instructions here

  1. Start Ollama server and download models for usage.

  2. Install ngrok forward your Ollama server to make it accessible publicly

    ngrok http 11434 --host-header="localhost:11434"
  3. Copy "Forwarding" URL that will look something like https://b377-82-132-216-51.ngrok-free.app. Your Ollama server API is now accessible through this temporary URL.

  4. Download Enchanted app from the App Store.

  5. In App Settings specify your server endpoint.

    You're done! Make a prompt.

Case 3. You run Pico AI Homelab

  1. Download Pico AI Homelab from the Mac App Store

  2. Download Enchanted app from the App Store.

  3. In App Settings, Click "Scan for servers"

  4. Select the Pico AI Homelab server instance you want to connect to from the list. Note that the Ollama server URI will be set automatically

    You're done! Write a prompt.

Contact

For any questions please do not hesitate to contact me at [email protected]

Author

Augustinas Malinauskas

About

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Swift 100.0%