Repository files navigation

GPT4js is a package that simplifies interaction with various AI models, eliminating the need for an API Key or any other authorization method to access these chat completions and image generation models.

This package can be used in Node.js or Browser environments.

• GPT4js 🔮
  • 📚 Table of Contents
  • 🛠️ Installation
    • Using NPM
    • Using Yarn
    • Using Bun
• 🧩 Examples
  • 📤 Chat Completion
    • ⚙️ Basic Usage
      • Simple Fetch
      • Give Your Instructions
      • Conversation Roles
    • 🔩 Configurable Options
    • 🚀 Chat Completion Providers
    • 📚 Chat Completion Models
• 📷 Image Generation
  • 📹 Example usage
  • 🌐 Image Generation Provider Options
  • 🧮 Number Type Options
  • 🖼️ Image Generation Providers
  • 🧠 Google Chrome AI
    • Setting Browser
      • Simple Usage
• 🧪 Testing
• 🚧 Building
  • Webpack
  • Bun
• 🤝 Contribute

npm install gpt4js

yarn add gpt4js

bun add gpt4js

With thechatCompletion function, you can obtain a textual response to a conversation with some context, using providers and models designed for this task. Additionally, you can manipulate the answer before converting it to a stream or force the AI to give you a certain answer by generating several retries.

It will capture the messages and the context, and any provider will respond with a string.

// CommonJSconstGPT4js=require("gpt4js");// ESMimportGPT4jsfrom"gpt4js";constmessages=[{role:"user",content:"hi!"}];constoptions={provider:"BlackBox",model:"BlackBox",};(async()=>{constprovider=GPT4js.createProvider(options.provider);try{consttext=awaitprovider.chatCompletion(messages,options,(data)=>{console.log(data);});console.log(text);}catch(error){console.error("Error:",error);}})();

Note: The conversation needs to include at least one message with the roleuser to provide a proper answer.

You can provide your own instructions for the conversation before it starts using thesystem role.

constmessages=[{role:"system",content:"You're an expert bot in programming."},{role:"user",content:"Hi, write me something."},];constoptions={provider:"BlackBox",};(async()=>{constprovider=GPT4js.createProvider(options.provider);try{consttext=awaitprovider.chatCompletion(messages,options,(data)=>{console.log(data);});console.log(text);}catch(error){console.error("Error:",error);}})();

Website	Provider	GPT-3.5	GPT-4	Stream	Status
Aryahcr	Aryahcr	✔️	✔️	✔️
BlackBox	BlackBox	❌	❌	❌
Nextway	Nextway	✔️	✔️	✔️
Chrome	Chrome	❌	❌	✔️
Ollama	Ollama	❌	❌	✔️
Alibaba	Alibaba	✔️	❌	✔️
ChatBotRu	ChatBotRu	❌	✔️	✔️

constoptions={provider:"DALLE2",};(async()=>{constprovider=GPT4js.createProvider(options.provider);try{constbase64=awaitprovider.imageGeneration("wood",options);console.log(base64);}catch(error){console.error("Error:",error);}})();

With theimageGeneration function, you can generate images from textual input along with optional parameters to customize and stylize the images in various artistic styles.

Provider	Status	Default Style
Dalle2		Semi-realistic, detailed with vivid colors and natural lighting.
StableDiffusion		Photorealistic, capturing fine details and textures to simulate real-life scenes.

Warning: This is an experimental feature and may not work correctly, it only works in Google Chrome 127 or higher (Chrome Dev). Also history is not supported

1. chrome://flags/#prompt-api-for-gemini-nano Select 'Enabled'

2. chrome://flags/#optimization-guide-on-device-model Select 'Enabled BypassPrefRequirement'

3. chrome://components Click 'Check for Update' on Optimization Guide On Device Model to download the model. If you don't see Optimization Guide, ensure you have set the flags correctly above, relaunch your browser, and refresh the page.

constmessages=[{role:"user",content:"hi!"}];constoptions={provider:"Chrome",};(async()=>{constprovider=GPT4js.createProvider(options.provider);try{consttext=awaitprovider.chatCompletion(messages,options,(data)=>{console.log(data);});console.log(text);}catch(error){console.error("Error:",error);}})();

Running:npm test

• npm run build - Build using Webpack.
• npm run dev - Live development build with Webpack.

• npm run build:bun - Build using Bun.
• npm run dev:bun - Live development build with Bun.

If you'd like to contribute to this project, you can do so directly onGitHub. Additionally, if you encounter any errors that hinder your use of any project functionality, pleasereport them here. Your feedback helps our community access AI tools freely!