Skip to main content

友情链接

¥Friendli

友情链接 通过可扩展、高效的部署选项，提升 AI 应用性能并优化成本节约，专为高需求 AI 工作负载量身定制。

¥Friendli enhances AI application performance and optimizes cost savings with scalable, efficient deployment options, tailored for high-demand AI workloads.

本教程将指导你将 Friendli 与 LangChain 集成。

¥This tutorial guides you through integrating Friendli with LangChain.

设置​

¥Setup

确保已安装 @langchain/community。

¥Ensure the @langchain/community is installed.

tip

请参阅 此部分包含有关安装集成包的一般说明。

¥See this section for general instructions on installing integration packages.

npm install @langchain/community @langchain/core

登录 Friendli Suite 创建个人访问令牌，并将其设置为 FRIENDLI_TOKEN 环境。你可以将团队 ID 设置为 FRIENDLI_TEAM 环境。

¥Sign in to Friendli Suite to create a Personal Access Token, and set it as the FRIENDLI_TOKEN environment. You can set team id as FRIENDLI_TEAM environment.

你可以通过选择要使用的模型来初始化 Friendli 聊天模型。默认模型是 mixtral-8x7b-instruct-v0-1。你可以在 docs.friendli.ai 查看可用的模型。

¥You can initialize a Friendli chat model with selecting the model you want to use. The default model is mixtral-8x7b-instruct-v0-1. You can check the available models at docs.friendli.ai.

用法​

¥Usage

import { Friendli } from "@langchain/community/llms/friendli";

const model = new Friendli({
  model: "mixtral-8x7b-instruct-v0-1", // Default value
  friendliToken: process.env.FRIENDLI_TOKEN,
  friendliTeam: process.env.FRIENDLI_TEAM,
  maxTokens: 18,
  temperature: 0.75,
  topP: 0.25,
  frequencyPenalty: 0,
  stop: [],
});

const response = await model.invoke(
  "Check the Grammar: She dont like to eat vegetables, but she loves fruits."
);

console.log(response);

/*
Correct: She doesn't like to eat vegetables, but she loves fruits
*/

const stream = await model.stream(
  "Check the Grammar: She dont like to eat vegetables, but she loves fruits."
);

for await (const chunk of stream) {
  console.log(chunk);
}

/*
Cor
rect
:
 She
 doesn
...
she
 loves
 fruits
*/

API Reference:

  • Friendli from @langchain/community/llms/friendli

¥Related