如何将回调传递到模块构造函数中

先决条件

本指南假设你熟悉以下概念

• 回调函数

大多数 LangChain 模块允许你将 回调函数 直接传递到构造函数中。在这种情况下，回调函数只会针对该实例（以及任何嵌套运行）被调用。

以下是一个使用 LangChain 的内置 ConsoleCallbackHandler 的示例

import { ConsoleCallbackHandler } from "@langchain/core/tracers/console";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { ChatAnthropic } from "@langchain/anthropic";

const handler = new ConsoleCallbackHandler();

const prompt = ChatPromptTemplate.fromTemplate(`What is 1 + {number}?`);
const model = new ChatAnthropic({
  model: "claude-3-sonnet-20240229",
  callbacks: [handler],
});

const chain = prompt.pipe(model);

await chain.invoke({ number: "2" });

[llm/start] [1:llm:ChatAnthropic] Entering LLM run with input: {
  "messages": [
    [
      {
        "lc": 1,
        "type": "constructor",
        "id": [
          "langchain_core",
          "messages",
          "HumanMessage"
        ],
        "kwargs": {
          "content": "What is 1 + 2?",
          "additional_kwargs": {},
          "response_metadata": {}
        }
      }
    ]
  ]
}
[llm/end] [1:llm:ChatAnthropic] [1.00s] Exiting LLM run with output: {
  "generations": [
    [
      {
        "text": "1 + 2 = 3",
        "message": {
          "lc": 1,
          "type": "constructor",
          "id": [
            "langchain_core",
            "messages",
            "AIMessage"
          ],
          "kwargs": {
            "content": "1 + 2 = 3",
            "tool_calls": [],
            "invalid_tool_calls": [],
            "additional_kwargs": {
              "id": "msg_011Z1cgi3gyNGxT55wnRNkXq",
              "type": "message",
              "role": "assistant",
              "model": "claude-3-sonnet-20240229",
              "stop_sequence": null,
              "usage": {
                "input_tokens": 16,
                "output_tokens": 13
              },
              "stop_reason": "end_turn"
            },
            "response_metadata": {
              "id": "msg_011Z1cgi3gyNGxT55wnRNkXq",
              "model": "claude-3-sonnet-20240229",
              "stop_sequence": null,
              "usage": {
                "input_tokens": 16,
                "output_tokens": 13
              },
              "stop_reason": "end_turn"
            }
          }
        }
      }
    ]
  ],
  "llmOutput": {
    "id": "msg_011Z1cgi3gyNGxT55wnRNkXq",
    "model": "claude-3-sonnet-20240229",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 16,
      "output_tokens": 13
    },
    "stop_reason": "end_turn"
  }
}

AIMessage {
  lc_serializable: true,
  lc_kwargs: {
    content: "1 + 2 = 3",
    tool_calls: [],
    invalid_tool_calls: [],
    additional_kwargs: {
      id: "msg_011Z1cgi3gyNGxT55wnRNkXq",
      type: "message",
      role: "assistant",
      model: "claude-3-sonnet-20240229",
      stop_sequence: null,
      usage: { input_tokens: 16, output_tokens: 13 },
      stop_reason: "end_turn"
    },
    response_metadata: {}
  },
  lc_namespace: [ "langchain_core", "messages" ],
  content: "1 + 2 = 3",
  name: undefined,
  additional_kwargs: {
    id: "msg_011Z1cgi3gyNGxT55wnRNkXq",
    type: "message",
    role: "assistant",
    model: "claude-3-sonnet-20240229",
    stop_sequence: null,
    usage: { input_tokens: 16, output_tokens: 13 },
    stop_reason: "end_turn"
  },
  response_metadata: {
    id: "msg_011Z1cgi3gyNGxT55wnRNkXq",
    model: "claude-3-sonnet-20240229",
    stop_sequence: null,
    usage: { input_tokens: 16, output_tokens: 13 },
    stop_reason: "end_turn"
  },
  tool_calls: [],
  invalid_tool_calls: []
}

你可以看到，我们只看到了来自聊天模型运行的事件 - 没有来自提示或更广泛的链的事件。

下一步

现在你已经了解了如何将回调函数传递到构造函数中。

接下来，查看本节中的其他操作指南，例如如何创建自己的 自定义回调处理程序。