IBM watsonx.ai

这将帮助您开始使用 IBM watsonx.ai 聊天模型。有关所有 IBM watsonx.ai 功能和配置的详细文档，请前往 IBM watsonx.ai。

概览

集成详情

类	包	本地	可序列化	PY 支持	包下载量	最新包
ChatWatsonx	@langchain/community	❌	✅	✅

模型功能

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	逐令牌流	令牌使用情况	Logprobs
✅	✅	✅	✅	❌	❌	✅	✅	❌

准备工作

要访问 IBM watsonx.ai 模型，您需要创建一个 IBM watsonx.ai 账户，获取 API 密钥，并安装 @langchain/community 集成包。

凭据

前往 IBM Cloud 注册 IBM watsonx.ai 并生成 API 密钥，或提供以下列出的任何其他认证方式。

IAM 认证

export WATSONX_AI_AUTH_TYPE=iam
export WATSONX_AI_APIKEY=<YOUR-APIKEY>

Bearer 令牌认证

export WATSONX_AI_AUTH_TYPE=bearertoken
export WATSONX_AI_BEARER_TOKEN=<YOUR-BEARER-TOKEN>

IBM watsonx.ai 软件认证

export WATSONX_AI_AUTH_TYPE=cp4d
export WATSONX_AI_USERNAME=<YOUR_USERNAME>
export WATSONX_AI_PASSWORD=<YOUR_PASSWORD>
export WATSONX_AI_URL=<URL>

一旦这些变量放置在您的环境变量中并且对象初始化完成，认证将自动进行。

也可以通过将这些值作为参数传递给新实例来完成认证。

IAM 认证

import { WatsonxLLM } from "@langchain/community/llms/ibm";

const props = {
  version: "YYYY-MM-DD",
  serviceUrl: "<SERVICE_URL>",
  projectId: "<PROJECT_ID>",
  watsonxAIAuthType: "iam",
  watsonxAIApikey: "<YOUR-APIKEY>",
};
const instance = new WatsonxLLM(props);

Bearer 令牌认证

import { WatsonxLLM } from "@langchain/community/llms/ibm";

const props = {
  version: "YYYY-MM-DD",
  serviceUrl: "<SERVICE_URL>",
  projectId: "<PROJECT_ID>",
  watsonxAIAuthType: "bearertoken",
  watsonxAIBearerToken: "<YOUR-BEARERTOKEN>",
};
const instance = new WatsonxLLM(props);

IBM watsonx.ai 软件认证

import { WatsonxLLM } from "@langchain/community/llms/ibm";

const props = {
  version: "YYYY-MM-DD",
  serviceUrl: "<SERVICE_URL>",
  projectId: "<PROJECT_ID>",
  watsonxAIAuthType: "cp4d",
  watsonxAIUsername: "<YOUR-USERNAME>",
  watsonxAIPassword: "<YOUR-PASSWORD>",
  watsonxAIUrl: "<url>",
};
const instance = new WatsonxLLM(props);

如果您希望自动追踪模型调用，也可以取消以下 LangSmith API 密钥的注释：

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

安装

LangChain IBM watsonx.ai 集成位于 @langchain/community 包中：

:::提示 请参阅安装集成包的一般说明部分。 :::

npm

npm i @langchain/community @langchain/core

yarn

yarn add @langchain/community @langchain/core

pnpm

pnpm add @langchain/community @langchain/core

实例化

现在我们可以实例化我们的模型对象并生成聊天补全：

import { ChatWatsonx } from "@langchain/community/chat_models/ibm";
const props = {
  maxTokens: 200,
  temperature: 0.5,
};

const instance = new ChatWatsonx({
  version: "YYYY-MM-DD",
  serviceUrl: process.env.API_URL,
  projectId: "<PROJECT_ID>",
  // spaceId: "<SPACE_ID>",
  // idOrName: "<DEPLOYMENT_ID>",
  model: "<MODEL_ID>",
  ...props,
});

注意：

• 除非使用无需指定任何参数的轻量级引擎（参考 watsonx.ai 文档），否则必须提供 spaceId、projectId 或 idOrName（部署 ID）。
• 根据您已配置服务实例的区域，使用正确的 serviceUrl。

调用

const aiMsg = await instance.invoke([
  {
    role: "system",
    content:
      "You are a helpful assistant that translates English to French. Translate the user sentence.",
  },
  {
    role: "user",
    content: "I love programming.",
  },
]);
console.log(aiMsg);

AIMessage {
  "id": "chat-c5341b2062dc42f091e5ae2558e905e3",
  "content": " J'adore la programmation.",
  "additional_kwargs": {
    "tool_calls": []
  },
  "response_metadata": {
    "tokenUsage": {
      "completion_tokens": 10,
      "prompt_tokens": 28,
      "total_tokens": 38
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 28,
    "output_tokens": 10,
    "total_tokens": 38
  }
}

console.log(aiMsg.content);

 J'adore la programmation.

链式调用

我们可以像这样将模型与提示模板进行链式调用：

import { ChatPromptTemplate } from "@langchain/core/prompts";

const prompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "You are a helpful assistant that translates {input_language} to {output_language}.",
  ],
  ["human", "{input}"],
]);
const chain = prompt.pipe(instance);
await chain.invoke({
  input_language: "English",
  output_language: "German",
  input: "I love programming.",
});

AIMessage {
  "id": "chat-c5c2c08d3c984254acc48225c39c6a08",
  "content": " Ich liebe Programmieren.",
  "additional_kwargs": {
    "tool_calls": []
  },
  "response_metadata": {
    "tokenUsage": {
      "completion_tokens": 8,
      "prompt_tokens": 22,
      "total_tokens": 30
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 22,
    "output_tokens": 8,
    "total_tokens": 30
  }
}

流式传输模型输出

import { HumanMessage, SystemMessage } from "@langchain/core/messages";

const messages = [
  new SystemMessage(
    "You are a helpful assistant which telling short-info about provided topic."
  ),
  new HumanMessage("moon"),
];
const stream = await instance.stream(messages);
for await (const chunk of stream) {
  console.log(chunk);
}

 The
 Moon
 is
 Earth
'
s
 only
 natural
 satellite
 and

工具调用

import { tool } from "@langchain/core/tools";
import { z } from "zod";

const calculatorSchema = z.object({
  operation: z
    .enum(["add", "subtract", "multiply", "divide"])
    .describe("The type of operation to execute."),
  number1: z.number().describe("The first number to operate on."),
  number2: z.number().describe("The second number to operate on."),
});

const calculatorTool = tool(
  async ({ operation, number1, number2 }) => {
    if (operation === "add") {
      return `${number1 + number2}`;
    } else if (operation === "subtract") {
      return `${number1 - number2}`;
    } else if (operation === "multiply") {
      return `${number1 * number2}`;
    } else if (operation === "divide") {
      return `${number1 / number2}`;
    } else {
      throw new Error("Invalid operation.");
    }
  },
  {
    name: "calculator",
    description: "Can perform mathematical operations.",
    schema: calculatorSchema,
  }
);

const instanceWithTools = instance.bindTools([calculatorTool]);

const res = await instanceWithTools.invoke("What is 3 * 12");
console.log(res);

AIMessage {
  "id": "chat-d2214d0bdb794483a213b3211cf0d819",
  "content": "",
  "additional_kwargs": {
    "tool_calls": [
      {
        "id": "chatcmpl-tool-257f3d39532141b89178c2120f81f0cb",
        "type": "function",
        "function": "[Object]"
      }
    ]
  },
  "response_metadata": {
    "tokenUsage": {
      "completion_tokens": 38,
      "prompt_tokens": 177,
      "total_tokens": 215
    },
    "finish_reason": "tool_calls"
  },
  "tool_calls": [
    {
      "name": "calculator",
      "args": {
        "number1": 3,
        "number2": 12,
        "operation": "multiply"
      },
      "type": "tool_call",
      "id": "chatcmpl-tool-257f3d39532141b89178c2120f81f0cb"
    }
  ],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 177,
    "output_tokens": 38,
    "total_tokens": 215
  }
}

API 参考文档

有关所有 IBM watsonx.ai 特性和配置的详细文档，请访问 API 参考文档：API 文档

Related

• Chat model conceptual guide
• Chat model how-to guides