跳至主要内容

Google PaLM（旧版）

危险

Google PaLM API 已弃用，将在 0.3.0 中删除。请改用Google GenAI 或VertexAI 集成。

注意

此集成不支持 gemini-* 模型。请检查Google GenAI 或VertexAI。

可以通过首先安装所需的软件包来集成Google PaLM API

提示

查看有关安装集成包的通用说明的本节。

npm install google-auth-library @google-ai/generativelanguage @langchain/community

从Google MakerSuite 创建一个API 密钥。然后，您可以将密钥设置为 GOOGLE_PALM_API_KEY 环境变量，或者在实例化模型时将其作为 apiKey 参数传递。

import { GooglePaLM } from "@langchain/community/llms/googlepalm";

export const run = async () => {
  const model = new GooglePaLM({
    apiKey: "<YOUR API KEY>", // or set it in environment variable as `GOOGLE_PALM_API_KEY`
    // other params
    temperature: 1, // OPTIONAL
    model: "models/text-bison-001", // OPTIONAL
    maxOutputTokens: 1024, // OPTIONAL
    topK: 40, // OPTIONAL
    topP: 3, // OPTIONAL
    safetySettings: [
      // OPTIONAL
      {
        category: "HARM_CATEGORY_DANGEROUS",
        threshold: "BLOCK_MEDIUM_AND_ABOVE",
      },
    ],
    stopSequences: ["stop"], // OPTIONAL
  });
  const res = await model.invoke(
    "What would be a good company name for a company that makes colorful socks?"
  );
  console.log({ res });
};

API 参考

  • GooglePaLM 来自 @langchain/community/llms/googlepalm

GooglePaLM

Langchain.js 支持两种不同的身份验证方法，具体取决于您是在 Node.js 环境中运行还是在 Web 环境中运行。

设置​

Node.js​

要在 Node 中调用 Vertex AI 模型，您需要安装Google 的官方身份验证客户端 作为对等依赖项。

您应确保 Vertex AI API 已为相关项目启用，并且您已使用以下方法之一对 Google Cloud 进行了身份验证

  • 您已登录到允许使用该项目的帐户（使用 gcloud auth application-default login）。
  • 您正在使用允许使用该项目的 service account 的机器上运行。
  • 您已下载允许使用该项目的 service account 的凭据，并将 GOOGLE_APPLICATION_CREDENTIALS 环境变量设置为该文件的路径。
npm install google-auth-library

Web​

要在 Web 环境（如 Edge 函数）中调用 Vertex AI 模型，您需要安装web-auth-library 软件包作为对等依赖项

npm install web-auth-library

然后，您需要将您的 service account 凭据直接作为 GOOGLE_VERTEX_AI_WEB_CREDENTIALS 环境变量添加

GOOGLE_VERTEX_AI_WEB_CREDENTIALS={"type":"service_account","project_id":"YOUR_PROJECT-12345",...}

您也可以像这样在代码中直接传递您的凭据

提示

查看有关安装集成包的通用说明的本节。

npm install @langchain/community
import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai";

const model = new GoogleVertexAI({
  authOptions: {
    credentials: {"type":"service_account","project_id":"YOUR_PROJECT-12345",...},
  },
});

用法​

有几种模型可用，可以通过构造函数中的 model 属性指定。这些包括

  • text-bison（默认）
  • text-bison-32k
  • code-gecko
  • code-bison
import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai";
// Or, if using the web entrypoint:
// import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai/web";

/*
 * Before running this, you should make sure you have created a
 * Google Cloud Project that is permitted to the Vertex AI API.
 *
 * You will also need permission to access this project / API.
 * Typically, this is done in one of three ways:
 * - You are logged into an account permitted to that project.
 * - You are running this on a machine using a service account permitted to
 *   the project.
 * - The `GOOGLE_APPLICATION_CREDENTIALS` environment variable is set to the
 *   path of a credentials file for a service account permitted to the project.
 */
const model = new GoogleVertexAI({
  temperature: 0.7,
});
const res = await model.invoke(
  "What would be a good company name for a company that makes colorful socks?"
);
console.log({ res });

API 参考

Google 还为其“Codey”代码生成模型提供了单独的模型。

“code-gecko” 模型对于代码补全很有用

import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai";

/*
 * Before running this, you should make sure you have created a
 * Google Cloud Project that is permitted to the Vertex AI API.
 *
 * You will also need permission to access this project / API.
 * Typically, this is done in one of three ways:
 * - You are logged into an account permitted to that project.
 * - You are running this on a machine using a service account permitted to
 *   the project.
 * - The `GOOGLE_APPLICATION_CREDENTIALS` environment variable is set to the
 *   path of a credentials file for a service account permitted to the project.
 */

const model = new GoogleVertexAI({
  model: "code-gecko",
});
const res = await model.invoke("for (let co=0;");
console.log({ res });

API 参考

而“code-bison” 模型在基于文本提示进行更大代码生成方面更出色

import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai";

/*
 * Before running this, you should make sure you have created a
 * Google Cloud Project that is permitted to the Vertex AI API.
 *
 * You will also need permission to access this project / API.
 * Typically, this is done in one of three ways:
 * - You are logged into an account permitted to that project.
 * - You are running this on a machine using a service account permitted to
 *   the project.
 * - The `GOOGLE_APPLICATION_CREDENTIALS` environment variable is set to the
 *   path of a credentials file for a service account permitted to the project.
 */

const model = new GoogleVertexAI({
  model: "code-bison",
  maxOutputTokens: 2048,
});
const res = await model.invoke(
  "A Javascript function that counts from 1 to 10."
);
console.log({ res });

API 参考

流式传输​

支持以多个块的形式进行流式传输，以获得更快的响应速度

import { GoogleVertexAI } from "@langchain/community/llms/googlevertexai";

const model = new GoogleVertexAI({
  temperature: 0.7,
});
const stream = await model.stream(
  "What would be a good company name for a company that makes colorful socks?"
);

for await (const chunk of stream) {
  console.log("\n---------\nChunk:\n---------\n", chunk);
}

/*
  ---------
  Chunk:
  ---------
    1. Toe-tally Awesome Socks
  2. The Sock Drawer
  3. Happy Feet
  4. 

  ---------
  Chunk:
  ---------
  Sock It to Me
  5. Crazy Color Socks
  6. Wild and Wacky Socks
  7. Fu

  ---------
  Chunk:
  ---------
  nky Feet
  8. Mismatched Socks
  9. Rainbow Socks
  10. Sole Mates

  ---------
  Chunk:
  ---------
  

*/

API 参考

此页面是否有帮助？


您也可以在 GitHub 上留下详细的反馈 在 GitHub 上.