xsAI - 包体积小于 6KB 的 Vercel AI SDK 平替

因为对现有的 AI SDK 都不太满意，就自己写了一个——具备 Vercel AI SDK Core 的大部分功能，但体积更小且根据功能分包。

使用例：

pnpm add @xsai/generate-text # 2.7KB minified (1.3KB gzip)

import { generateText } from '@xsai/generate-text'
import { env } from 'node:process'
 
const { text } = await generateText({
  apiKey: env.OPENAI_API_KEY!,
  baseURL: 'https://api.openai.com/v1/',
  messages: [
    {
      content: 'You\'re a helpful assistant.',
      role: 'system'
    },
    {
      content: 'Why is the sky blue?',
      role: 'user'
    }
  ],
  model: 'gpt-4o',
})

或者流式传输 + 工具调用：

pnpm add @xsai/stream-text @xsai/tool # 6KB minified (2.5KB gzip)

import { streamText } from '@xsai/stream-text'
import { tool } from '@xsai/tool'
import { env } from 'node:process'
import { description, object, pipe, string } from 'valibot'

const weather = await tool({
  description: 'Get the weather in a location',
  execute: ({ location }) => JSON.stringify({
    location,
    temperature: 72 + Math.floor(Math.random() * 21) - 10,
  }),
  name: 'weather',
  parameters: object({
    location: pipe(
      string(),
      description('The location to get the weather for'),
    ),
  }),
})

const { textStream } = await streamText({
  apiKey: env.OPENAI_API_KEY!,
  baseURL: 'https://api.openai.com/v1/',
  messages: [
    {
      content: 'You are a helpful assistant.',
      role: 'system',
    },
    {
      content: 'What is the weather in San Francisco?',
      role: 'user',
    },
  ],
  model: 'gpt-4o',
  tools: [weather],
})

for await (const textPart of textStream) {
  console.log(textPart)
}

或者流式传输对象（并安装整包）:

pnpm add xsai # 16KB minified (5.7KB gzip)

import { type } from 'arktype'
import { streamObject } from 'xsai'
import { env } from 'node:process'
 
const { partialObjectStream } = await streamObject({
  apiKey: env.OPENAI_API_KEY!,
  baseURL: 'https://api.openai.com/v1/',
  messages: [
    {
      content: 'Extract the event information.',
      role: 'system'
    },
    {
      content: 'Alice and Bob are going to a science fair on Friday.',
      role: 'user'
    }
  ],
  model: 'gpt-4o',
  schema: type({
    name: 'string',
    date: 'string',
    participants: 'string[]',
  }),
})
 
for await (const partialObject of partialObjectStream) { 
  console.log(partialObject)
}

一些链接：