xsAI

extra-small AI SDK for Browser, Node.js, Deno, Bun or Edge Runtime.

xsAI is a series of utils to help you use OpenAI or OpenAI-compatible API.

import { generateText } from '@xsai/generate-text'
import { createOpenAI } from '@xsai/providers'
import { env } from 'node:process'

const openai = createOpenAI({
  apiKey: env.OPENAI_API_KEY
})

const { text } = await generateText({
  ...openai.chat('gpt-4o'),
  messages: [
    {
      content: 'You are a helpful assistant.',
      role: 'system',
    },
    {
      content: 'This is a test, so please answer \'YES\' and nothing else.',
      role: 'user',
    },
  ],
})

// "YES"
console.log(text)

Features

extra(x)-small(s)

xsAI uses a variety of methods to make itself smaller.

It's just a wrapper for Fetch API, ESM Only, adding additional dependencies only when absolutely necessary.

How xsAI small? you can try install it with pkg-size.dev:

[email protected] is 111KB install size and 11KB bundle size (3KB gzipped).

Notably, this contains dependencies introduced to support tool calls and structured output.

If you only need the basic generateText, @xsai/[email protected] is only 12KB install size and 1.2KB bundle size (678B gzipped). (try install it with pkg-size.dev)

Runtime-agnostic

xsAI doesn't depend on Node.js Built-in Modules, it works well in Browsers, Deno, Bun and even the Edge Runtime.

Usage

Install

You can also install only some of the utils of xsAI, such as @xsai/generate-text and @xsai/stream-text.

# npm
npm install xsai

# yarn
yarn add xsai

# pnpm
pnpm install xsai

# bun
bun install xsai

# deno
deno install xsai

Getting Started

Read the documentation to get started.

Examples

Generating Text (see above)

Streaming Text

import { createOpenAI } from '@xsai/providers'
import { streamText } from '@xsai/stream-text'
import { env } from 'node:process'

const openai = createOpenAI({
  apiKey: env.OPENAI_API_KEY,
})

const { textStream } = await streamText({
  ...openai.chat('gpt-4o'),
  messages: [
    {
      content: 'You are a helpful assistant.',
      role: 'system',
    },
    {
      content: 'This is a test, so please answer \'The quick brown fox jumps over the lazy dog.\' and nothing else.',
      role: 'user',
    },
  ],
})

const text: string[] = []

for await (const textPart of textStream) {
  text.push(textPart)
}

// "The quick brown fox jumps over the lazy dog."
console.log(text)

Generating Text w/ Tool Calling

import { generateText } from '@xsai/generate-text'
import { createOpenAI } from '@xsai/providers'
import { tool } from '@xsai/tool'
import { env } from 'node:process'
import { description, object, pipe, string } from 'valibot'

const openai = createOpenAI({
  apiKey: env.OPENAI_API_KEY,
})

const weather = await tool({
  description: 'Get the weather in a location',
  execute: ({ location }) => JSON.stringify({
    location,
    temperature: 42,
  }),
  name: 'weather',
  parameters: object({
    location: pipe(
      string(),
      description('The location to get the weather for'),
    ),
  }),
})

const { text } = await generateText({
  ...openai.chat('gpt-4o'),
  maxSteps: 2,
  messages: [
    {
      content: 'You are a helpful assistant.',
      role: 'system',
    },
    {
      content: 'What is the weather in San Francisco? do not answer anything else.',
      role: 'user',
    },
  ],
  toolChoice: 'required',
  tools: [weather],
})

// "In San Francisco, it's currently 42°F."
console.log(text)

Community Projects

• moeru-ai/airi
• moeru-ai/arpk
• lingticio/neuri-js

Status

xsAI is currently in an early stage of development and may introduce breaking changes at any time.

License

MIT

Moeru AI / xsAI is not affiliated with OpenAI.