npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

gpt4js

v1.7.8

Published

Using ChatGPT4/3.5-turbo/Gemini-Pro/BlackBox and etc. unlimited and free.

Downloads

5,428

Readme

GPT4js 🔮

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.

Static Badge GitHub top language GitHub Repo stars GitHub issues NPM Downloads

📚 Table of Contents

🛠️ Installation

Using NPM

npm install gpt4js

Using Yarn

yarn add gpt4js

Using Bun

bun add gpt4js

🧩 Examples

📤 Chat Completion

With the chatCompletion 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.

⚙️ Basic Usage

Simple Fetch

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

// CommonJS
const getGPT4js = require("gpt4js");
const GPT4js = await getGPT4js();
// ESM
import GPT4js from "gpt4js";

const messages = [{ role: "user", content: "hi!" }];
const options = {
  provider: "Nextway",
  model: "gpt-4o-free",
};

(async () => {
  const provider = GPT4js.createProvider(options.provider);
  try {
    const text = await provider.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 role user to provide a proper answer.

Give Your Instructions

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

const messages = [
  { role: "system", content: "You're an expert bot in programming." },
  { role: "user", content: "Hi, write me something." },
];
const options = {
  provider: "Nextway",
  model: "gpt-4o-free",
};

(async () => {
  const provider = GPT4js.createProvider(options.provider);
  try {
    const text = await provider.chatCompletion(messages, options, (data) => {
      console.log(data);
    });
    console.log(text);
  } catch (error) {
    console.error("Error:", error);
  }
})();

Conversation Roles

| Role | Description | | ----------- | ---------------------------------------------------------------------- | | system | Used for providing instructions and context prior to the conversation. | | user | Used to identify user messages | | assistant | Used to identify AI messages |

🔩 Configurable Options

| Option | Type | Description | | --------------- | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | provider | string | Choose the provider to use for chat completions. Possible values include Nextway, BlackBox, etc. This determines which service will handle the request. | | model | string | Choose the model to use by a provider that supports it. For example, gpt-4, gpt-3.5-turbo, etc. This specifies the particular language model for generating completions. | | stream | boolean | Determine if the data should be streamed in parts or not. If true, the response will be streamed in real-time as it's generated. If false, the response will be sent all at once. | | temperature | number | Set the temperature to control the randomness of the output. A value between 0 and 1 where higher values (closer to 1) make the output more random, and lower values (closer to 0) make it more deterministic. | | webSearch | boolean | Enable or disable web search functionality. If true, the system can perform web searches to gather real-time information. If false, it relies solely on pre-existing data. | | codeModelMode | boolean | Enable or disable the code model mode. If true, the system will use a model optimized for understanding and generating code. If false, it uses the general-purpose language model. | | isChromeExt | boolean | Specify whether the system is being used as a Chrome extension. If true, it indicates integration with Chrome, possibly affecting certain functionalities and permissions. |

🚀 Chat Completion Providers

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

📚 Chat Completion Models

| Model | Providers that support it | | ---------------------------- | --------------------------------- | | gpt-4 | Aryahcr, Nextway, ChatBotRu | | gpt-4-0613 | Aryahcr | | gpt-4-32k | Aryahcr | | gpt-4-0314 | Aryahcr | | gpt-4o-free | Nextway | | gpt-4o | ChatBotRu | | gpt-4-32k-0314 | Aryahcr | | gpt-4-turbo | ChatBotRu | | gpt-3.5-turbo | Aryahcr, Nextway, Alibaba | | gpt-3.5-turbo-16k | Aryahcr | | gpt-3.5-turbo-0613 | Aryahcr | | gpt-3.5-turbo-16k-0613 | Aryahcr | | gpt-3.5-turbo-0301 | Aryahcr | | text-davinci-003 | Aryahcr | | text-davinci-002 | Aryahcr | | code-davinci-002 | Aryahcr | | gpt-3 | Aryahcr | | text-curie-001 | Aryahcr | | text-babbage-001 | Aryahcr | | text-ada-001 | Aryahcr | | davinci | Aryahcr | | curie | Aryahcr | | babbage | Aryahcr | | ada | Aryahcr | | babbage-002 | Aryahcr | | davinci-002 | Aryahcr | | gemini-pro | Nextway | | gemini-nano | Chrome | | All Ollama models | Ollama | | SparkDesk-v1.1 | Alibaba | | deepseek-coder | Alibaba | | deepseek-chat | Alibaba | | Qwen2-7B-Instruct | Alibaba | | glm4-9B-chat | Alibaba | | chatglm3-6B | Alibaba | | Yi-1.5-9B-Chat | Alibaba | | llama-3.1-405b-instruct-free | Nextway |

📷 Image Generation

📹 Example usage

const options = {
  provider: "DALLE2",
};

(async () => {
  const provider = GPT4js.createProvider(options.provider);
  try {
    const base64 = await provider.imageGeneration("wood", options);
    console.log(base64);
  } catch (error) {
    console.error("Error:", error);
  }
})();

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

🌐 Image Generation Provider Options

| Option | Type | Description | | ---------------- | ------ | ------------------------------------------------------------------------------------------------------------------- | | negativePrompt | string | Indicates the direction not to take in production. | | height | number | Specifies the image height. | | width | number | Specifies the image width. | | samplingSteps | number | Specifies the number of iterations. A higher number results in higher quality. | | samplingMethod | string | Selects a sampling method to control the diversity, quality, and coherence of images. | | cfgScale | number | Specifies the Classifier-Free Guidance to control how closely the generated image adheres to the given text prompt. |

🧮 Number Type Options

| Provider | Supported Number Type Options and Values | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | StableDiffusion | - height: Default 512, Min 50, Max 1024- width: Default 512, Min 50, Max 1024- samplingSteps: Default 25, Min 1, Max 30- cfgScale: Default 7, Min 1, Max 20 |

🖼️ Image Generation Providers

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

🧠 Google Chrome AI

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

Setting Browser

  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.

Simple Usage

const messages = [{ role: "user", content: "hi!" }];
const options = {
  provider: "Chrome",
};

(async () => {
  const provider = GPT4js.createProvider(options.provider);
  try {
    const text = await provider.chatCompletion(messages, options, (data) => {
      console.log(data);
    });
    console.log(text);
  } catch (error) {
    console.error("Error:", error);
  }
})();

🧪 Testing

Running: npm test

🚧 Building

Webpack

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

Bun

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

🤝 Contribute

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