https://github.com/frontllm/frontllm-sdk

FrontLLM is your public gateway to LLMs. Request LLM directly from your front-end code. No backend needed.
https://github.com/frontllm/frontllm-sdk

ai gateway-api llm llm-framework llm-gateway openai

Last synced: 10 months ago
JSON representation

FrontLLM is your public gateway to LLMs. Request LLM directly from your front-end code. No backend needed.

• Host: GitHub
• URL: https://github.com/frontllm/frontllm-sdk
• Owner: frontllm
• License: mit
• Created: 2025-05-18T21:46:10.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-05-30T21:22:53.000Z (about 1 year ago)
• Last Synced: 2025-08-09T20:18:47.398Z (11 months ago)
• Topics: ai, gateway-api, llm, llm-framework, llm-gateway, openai
• Language: TypeScript
• Homepage: https://frontllm.com/
• Size: 102 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE

Awesome Lists containing this project

README

          
![FrontLLM](.github/cover.png)

# FrontLLM

[![Build Status](https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Ffrontllm%2Ffrontllm-sdk%2Fbadge%3Fref%3Dmain&style=flat-square)](https://actions-badge.atrox.dev/frontllm/frontllm-sdk/goto?ref=main) [![License: MIT](https://img.shields.io/badge/license-MIT-green?style=flat-square)](/LICENSE) [![View this project on NPM](https://img.shields.io/npm/v/frontllm.svg?style=flat-square)](https://npmjs.org/package/frontllm)

FrontLLM is your public gateway to LLMs. Request LLM directly from your front-end code. No backend needed.

📝 Check the [documentation](https://frontllm.com/docs/introduction) for more details.

### 👀 Demos

* [Explain This](https://frontllm.com/docs/demos/explain-this)

* [Streaming](https://frontllm.com/docs/demos/streaming)

* [Translator](https://frontllm.com/docs/demos/translator)

## 🚀 Installation

### NPM

To use FrontLLM in your project, you can install it via npm:

```bash

npm install frontllm

```

Now you can import the library and create an instance of the gateway with your specific gateway ID:

```js

import { frontLLM } from 'frontllm';

const gateway = frontLLM('');

```

### CDN

To use FrontLLM via CDN, you can include the following script tag in your HTML file:

```html

```

This will expose the `frontLLM` function globally, which you can use to create an instance of the gateway:

```html

  const gateway = frontLLM('<gateway_id>');

  // ...

```

## 🎬 Usage

Chat Completion:

```js

// Short syntax - requires the default model configured in the gateway

const response = await gateway.complete('Hello world!'); 

// Full syntax

const response = await gateway.complete({

  model: 'gpt-4',

  messages: [

    { role: 'user', content: 'Hello world!' }

  ],

  temperature: 0.7

});

// Output the generated response text to the console.

console.log(response.choices[0].message.content);

```

Chat Completion with Streaming:

```js

// Short syntax - requires the default model configured in the gateway

const response = await gateway.completeStreaming('Where is Europe?');

// Full syntax

const response = await gateway.completeStreaming({

  model: 'gpt-4',

  messages: [

    { role: 'user', content: 'Where is Europe?' }

  ],

  temperature: 0.7

});

// Output the generated response text to the console.

for (;;) {

  const { finished, chunks } = await response.read();

  for (const chunk of chunks) {

    console.log(chunk.choices[0].delta.content);

  }

  if (finished) {

    break;

  }

}

```

## 💡 License

This project is released under the MIT license.