Token.js |.Token.js - Beragampengetahuan

Impor klien Token.js dan telepon create Berfungsi dengan petunjuk format OpenAI. Tentukan model dan penyedia LLM menggunakan kolomnya masing-masing.

OPENAI_API_KEY=<openai api key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'openai',
    model: 'gpt-4o',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

ANTHROPIC_API_KEY=<anthropic api key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'anthropic',
    model: 'claude-3-sonnet-20240229',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

GEMINI_API_KEY=<gemini api key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'gemini',
    model: 'gemini-1.5-pro',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

AWS_REGION_NAME=<aws region>
AWS_ACCESS_KEY_ID=<aws access key id>
AWS_SECRET_ACCESS_KEY=<aws secret access key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'bedrock',
    model: 'meta.llama3-70b-instruct-v1:0',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

COHERE_API_KEY=<cohere api key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'cohere',
    model: 'command-r-plus',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

MISTRAL_API_KEY=<mistral api key>

import  TokenJS  from 'token.js'

// Create the Token.js client
const tokenjs = new TokenJS()

async function main() 
  // Create a model response
  const completion = await tokenjs.chat.completions.create(
    // Specify the provider and model
    provider: 'mistral',
    model: 'open-mixtral-8x22b',
    // Define your message
    messages: [
      
        role: 'user',
        content: 'Hello!',
      ,
    ],
  )
  console.log(completion.choices[0])

main()

Kami merekomendasikan penggunaan variabel lingkungan untuk mengonfigurasi kredensial setiap penyedia LLM.

# OpenAI
OPENAI_API_KEY=
# AI21
AI21_API_KEY=
# Anthropic
ANTHROPIC_API_KEY=
# Cohere
COHERE_API_KEY=
# Gemini
GEMINI_API_KEY=
# Groq
GROQ_API_KEY=
# Mistral
MISTRAL_API_KEY=
# Perplexity
PERPLEXITY_API_KEY=
# AWS Bedrock
AWS_REGION_NAME=
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=

Token.js mendukung respons streaming dari semua penyedia yang menawarkannya.

import  TokenJS  from 'token.js'

const tokenjs = new TokenJS()

async function main() 
  const result = await tokenjs.chat.completions.create(
    stream: true,
    provider: 'openai',
    model: 'gpt-4o',
    messages: [
      
        role: 'user',
        content: `Tell me about yourself.`,
      ,
    ],
  )

  for await (const part of result) 
    process.stdout.write(part.choices[0]?.delta?.content 

main()

Token.js mendukung fasilitas pemanggilan fungsi untuk semua penyedia dan model yang menawarkannya.

import  TokenJS, ChatCompletionTool  from 'token.js'

const tokenjs = new TokenJS()

async function main() {
  const tools: ChatCompletionTool[] = [
    {
      type: 'function',
      function: 
        name: 'get_current_weather',
        description: 'Get the current weather in a given location',
        parameters: 
          type: 'object',
          properties: 
            location: 
              type: 'string',
              description: 'The city and state, e.g. San Francisco, CA',
            ,
          ,
          required: ['location'],
        ,
      ,
    },
  ]

  const result = await tokenjs.chat.completions.create(
    provider: 'gemini',
    model: 'gemini-1.5-pro',
    messages: [
      
        role: 'user',
        content: `What's the weather like in San Francisco?`,
      ,
    ],
    tools,
    tool_choice: 'auto',
  )

  console.log(result.choices[0].message.tool_calls)
}
main()

Tabel ini menguraikan fungsionalitas setiap penyedia LLM yang didukung oleh Token.js.

catatan: Beberapa LLM, terutama model lama atau lemah, tidak mendukung beberapa fitur dalam tabel ini. Untuk informasi lebih lanjut tentang batasan ini, silakan lihat dokumentasi penyedia LLM kami.

Contents

rencana pengembangan website

metode pengembangan website

jelaskan beberapa rencana untuk pengembangan website, proses pengembangan website, kekuatan dan kelemahan bisnis pengembangan website
, jasa pengembangan website, tahap pengembangan website, biaya pengembangan website

#Token.js #.Token.js

Token.js |.Token.js – Beragampengetahuan

rencana pengembangan website

metode pengembangan website

Tinggalkan Balasan Batalkan balasan

Maximal

rencana pengembangan website

metode pengembangan website

Tinggalkan Balasan Batalkan balasan

Maximal

Related Posts