picoLLM Inference Engine
iOS Quick Start

Platforms

• iOS (16.0+)

Requirements

• Xcode
• CocoaPods

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install Xcode.

2. Install CocoaPods

3. Import the picoLLM-iOS binding by adding the following line to your Podfile:

pod 'picoLLM-iOS'

4. Run the following from the project directory:

pod install

5. Download a picoLLM model file (.pllm) from Picovoice Console.

Model File Deployment

To deploy a model file (.pllm) as part of an iOS app, there are a few options:

1. Include in App Bundle:

   • Add model file to your Application's bundle as a resource.
   • Keep in mind Apple enforces a maximum size limit, not all models will fit.

2. Host Externally:

   • Host the model file on a server or cloud storage service.
   • Download the file from within the app.

3. Copy to Device (for testing or manual installation):

   • Use AirDrop or connect your device via USB and copy your model to the device's storage.
   • Access the file programmatically within your app.

Usage

1. Create an instance of the inference engine:

import PicoLLM

do {
    let pllm = try PicoLLM(
        accessKey: "${ACCESS_KEY}",
        modelPath: "${MODEL_PATH}")
} catch { }

2. Generate a prompt completion:

do {
    let res = pllm.generate(prompt: "${PROMPT}")
} catch { }

3. To interrupt completion generation before it has finished:

do {
    pllm.interrupt();
} catch { }

Demo

For the picoLLM iOS SDK, we offer demo applications that demonstrate how to use it to generate text from a prompt or in a chat-based environment.

Setup

1. Clone the picoLLM repository from GitHub using HTTPS:

git clone https://github.com/Picovoice/picollm.git

2. Connect an iOS device via USB or launch an iOS device simulator.

Usage

1. Install dependencies:

cd picollm/demo/ios/PicoLLMCompletionDemo
pod install

2. Open the PicoLLMCompletionDemo.xcworkspace in XCode.

3. Replace ${YOUR_ACCESS_KEY_HERE} in ViewController.swift with a valid AccessKey.

4. Airdrop or copy the picoLLM model file (.pllm) file to your deployment device.

5. Build and run the app.

For more information on our picoLLM demo for iOS or to see a chat-based demo, head over to our GitHub repository.

Resources