如何将运行时参数附加到 Runnable

先决条件

本指南假设您熟悉以下概念

• LangChain 表达式语言 (LCEL)
• 链接 Runnable
• 工具调用

有时我们想要在 Runnable 内调用 RunnableSequence，其中使用并非序列中先前 Runnable 输出的一部分的常量参数，并且这些参数也不是用户输入的一部分。我们可以使用 Runnable.bind() 方法提前设置这些参数。

绑定停止序列

假设我们有一个简单的提示 + 模型链

提示

参见 有关安装集成软件包的通用说明，请参见本节。

npm

npm i @langchain/openai @langchain/core

yarn

yarn add @langchain/openai @langchain/core

pnpm

pnpm add @langchain/openai @langchain/core

import { StringOutputParser } from "@langchain/core/output_parsers";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { ChatOpenAI } from "@langchain/openai";

const prompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "Write out the following equation using algebraic symbols then solve it. Use the format\n\nEQUATION:...\nSOLUTION:...\n\n",
  ],
  ["human", "{equation_statement}"],
]);

const model = new ChatOpenAI({ temperature: 0 });

const runnable = prompt.pipe(model).pipe(new StringOutputParser());

const res = await runnable.invoke({
  equation_statement: "x raised to the third plus seven equals 12",
});

console.log(res);

EQUATION: x^3 + 7 = 12

SOLUTION:
Subtract 7 from both sides:
x^3 = 5

Take the cube root of both sides:
x = ∛5

并且想要使用某些stop 字词调用模型以缩短输出，这在某些类型的提示技术中很有用。虽然我们可以将一些参数传递到构造函数中，但其他运行时参数使用.bind() 方法如下

const runnableWithStop = prompt
  .pipe(model.bind({ stop: ["SOLUTION"] }))
  .pipe(new StringOutputParser());

const shorterResponse = await runnableWithStop.invoke({
  equation_statement: "x raised to the third plus seven equals 12",
});

console.log(shorterResponse);

EQUATION: x^3 + 7 = 12

您可以绑定到 Runnable 的内容将取决于调用它时可以传递的额外参数。

附加 OpenAI 工具

另一个常见的用例是工具调用。虽然您通常应该使用 .bind_tools() 方法来调用工具模型，但如果您想要更底层的控制，也可以直接绑定特定于提供程序的参数

const tools = [
  {
    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",
          },
          unit: { type: "string", enum: ["celsius", "fahrenheit"] },
        },
        required: ["location"],
      },
    },
  },
];

const modelWithTools = new ChatOpenAI({ model: "gpt-4o" }).bind({ tools });

await modelWithTools.invoke("What's the weather in SF, NYC and LA?");

AIMessage {
  lc_serializable: true,
  lc_kwargs: {
    content: "",
    tool_calls: [
      {
        name: "get_current_weather",
        args: { location: "San Francisco, CA" },
        id: "call_iDKz4zU8PKBaaIT052fJkMMF"
      },
      {
        name: "get_current_weather",
        args: { location: "New York, NY" },
        id: "call_niQwZDOqO6OJTBiDBFG8FODc"
      },
      {
        name: "get_current_weather",
        args: { location: "Los Angeles, CA" },
        id: "call_zLXH2cDVQy0nAVC0ViWuEP4m"
      }
    ],
    invalid_tool_calls: [],
    additional_kwargs: {
      function_call: undefined,
      tool_calls: [
        {
          id: "call_iDKz4zU8PKBaaIT052fJkMMF",
          type: "function",
          function: [Object]
        },
        {
          id: "call_niQwZDOqO6OJTBiDBFG8FODc",
          type: "function",
          function: [Object]
        },
        {
          id: "call_zLXH2cDVQy0nAVC0ViWuEP4m",
          type: "function",
          function: [Object]
        }
      ]
    },
    response_metadata: {}
  },
  lc_namespace: [ "langchain_core", "messages" ],
  content: "",
  name: undefined,
  additional_kwargs: {
    function_call: undefined,
    tool_calls: [
      {
        id: "call_iDKz4zU8PKBaaIT052fJkMMF",
        type: "function",
        function: {
          name: "get_current_weather",
          arguments: '{"location": "San Francisco, CA"}'
        }
      },
      {
        id: "call_niQwZDOqO6OJTBiDBFG8FODc",
        type: "function",
        function: {
          name: "get_current_weather",
          arguments: '{"location": "New York, NY"}'
        }
      },
      {
        id: "call_zLXH2cDVQy0nAVC0ViWuEP4m",
        type: "function",
        function: {
          name: "get_current_weather",
          arguments: '{"location": "Los Angeles, CA"}'
        }
      }
    ]
  },
  response_metadata: {
    tokenUsage: { completionTokens: 70, promptTokens: 82, totalTokens: 152 },
    finish_reason: "tool_calls"
  },
  tool_calls: [
    {
      name: "get_current_weather",
      args: { location: "San Francisco, CA" },
      id: "call_iDKz4zU8PKBaaIT052fJkMMF"
    },
    {
      name: "get_current_weather",
      args: { location: "New York, NY" },
      id: "call_niQwZDOqO6OJTBiDBFG8FODc"
    },
    {
      name: "get_current_weather",
      args: { location: "Los Angeles, CA" },
      id: "call_zLXH2cDVQy0nAVC0ViWuEP4m"
    }
  ],
  invalid_tool_calls: []
}

下一步

现在您知道如何将运行时参数绑定到 Runnable。

接下来，您可能对我们的操作指南感兴趣，内容是关于 将数据传递到链中。