跳至主要内容

如何在聊天模型中使用少量示例

本指南介绍如何使用示例输入和输出提示聊天模型。为模型提供一些这样的示例称为少量提示，这是一种简单而强大的方法来指导生成，在某些情况下可以极大地提高模型性能。

关于如何最好地进行少量提示似乎没有达成一致意见，最佳提示编译可能因模型而异。因此，我们提供了一些提示模板，例如 FewShotChatMessagePromptTemplate 作为灵活的起点，您可以根据需要修改或替换它们。

少量提示模板的目的是根据输入动态选择示例，然后将示例格式化为最终提示以提供给模型。

注意：以下代码示例仅适用于聊天模型，因为 FewShotChatMessagePromptTemplates 被设计为输出格式化的 聊天消息 而不是纯字符串。有关与完成模型 (LLM) 兼容的纯字符串模板的类似少量提示示例，请参阅 少量提示模板 指南。

先决条件

本指南假设您熟悉以下概念

固定示例​

最基本（也是最常见）的少量提示技术是使用固定提示示例。这样，您就可以选择一条链，对其进行评估，并在生产中避免担心额外的活动部件。

模板的基本组成部分是：- examples：要在最终提示中包含的对象示例数组。- examplePrompt：通过其 formatMessages 方法将每个示例转换为一条或多条消息。一个常见示例是将每个示例转换为一条人类消息和一条 AI 消息响应，或一条人类消息后跟一条函数调用消息。

以下是一个简单的演示。首先，定义您要包含的示例

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

const examples = [
  { input: "2+2", output: "4" },
  { input: "2+3", output: "5" },
];

接下来，将它们组合成少量提示模板。

// This is a prompt template used to format each individual example.
const examplePrompt = ChatPromptTemplate.fromMessages([
  ["human", "{input}"],
  ["ai", "{output}"],
]);
const fewShotPrompt = new FewShotChatMessagePromptTemplate({
  examplePrompt,
  examples,
  inputVariables: [], // no input variables
});

const result = await fewShotPrompt.invoke({});
console.log(result.toChatMessages());
[
  HumanMessage {
    lc_serializable: true,
    lc_kwargs: { content: "2+2", additional_kwargs: {}, response_metadata: {} },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "2+2",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {}
  },
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: "4",
      tool_calls: [],
      invalid_tool_calls: [],
      additional_kwargs: {},
      response_metadata: {}
    },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "4",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {},
    tool_calls: [],
    invalid_tool_calls: []
  },
  HumanMessage {
    lc_serializable: true,
    lc_kwargs: { content: "2+3", additional_kwargs: {}, response_metadata: {} },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "2+3",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {}
  },
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: "5",
      tool_calls: [],
      invalid_tool_calls: [],
      additional_kwargs: {},
      response_metadata: {}
    },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "5",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {},
    tool_calls: [],
    invalid_tool_calls: []
  }
]

最后，我们按照以下所示组装最终提示，将 fewShotPrompt 直接传递到 fromMessages 工厂方法中，并将其与模型一起使用

const finalPrompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a wondrous wizard of math."],
  fewShotPrompt,
  ["human", "{input}"],
]);

选择您的聊天模型

安装依赖项

提示

查看 本节了解有关安装集成包的常规说明.

yarn add @langchain/openai

添加环境变量

OPENAI_API_KEY=your-api-key

实例化模型

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0
});
const chain = finalPrompt.pipe(model);

await chain.invoke({ input: "What's the square of a triangle?" });
AIMessage {
  lc_serializable: true,
  lc_kwargs: {
    content: "A triangle does not have a square. The square of a number is the result of multiplying the number by"... 8 more characters,
    tool_calls: [],
    invalid_tool_calls: [],
    additional_kwargs: { function_call: undefined, tool_calls: undefined },
    response_metadata: {}
  },
  lc_namespace: [ "langchain_core", "messages" ],
  content: "A triangle does not have a square. The square of a number is the result of multiplying the number by"... 8 more characters,
  name: undefined,
  additional_kwargs: { function_call: undefined, tool_calls: undefined },
  response_metadata: {
    tokenUsage: { completionTokens: 23, promptTokens: 52, totalTokens: 75 },
    finish_reason: "stop"
  },
  tool_calls: [],
  invalid_tool_calls: []
}

动态少量提示​

有时您可能希望根据输入只从整体示例集中选择几个示例来显示。为此，您可以用 exampleSelector 替换传递到 FewShotChatMessagePromptTemplate 的 examples。其他组件与上面相同！我们的动态少样本提示模板将如下所示

  • exampleSelector：负责为给定输入选择少样本示例（以及返回的顺序）。这些实现了 BaseExampleSelector 接口。一个常见的示例是基于向量存储的 SemanticSimilarityExampleSelector
  • examplePrompt：通过其 formatMessages 方法将每个示例转换为 1 个或多个消息。一个常见的示例是将每个示例转换为一条人类消息和一条 AI 消息回复，或一条人类消息后跟一条函数调用消息。

这些还可以与其他消息和聊天模板组合，以组装最终提示。

让我们以 SemanticSimilarityExampleSelector 为例。由于此实现使用向量存储根据语义相似性选择示例，因此我们将首先填充存储。由于这里的基本思想是希望搜索并返回与文本输入最相似的示例，因此我们将嵌入提示示例的 values，而不是考虑键

import { SemanticSimilarityExampleSelector } from "@langchain/core/example_selectors";
import { MemoryVectorStore } from "langchain/vectorstores/memory";
import { OpenAIEmbeddings } from "@langchain/openai";

const examples = [
  { input: "2+2", output: "4" },
  { input: "2+3", output: "5" },
  { input: "2+4", output: "6" },
  { input: "What did the cow say to the moon?", output: "nothing at all" },
  {
    input: "Write me a poem about the moon",
    output:
      "One for the moon, and one for me, who are we to talk about the moon?",
  },
];

const toVectorize = examples.map(
  (example) => `${example.input} ${example.output}`
);
const embeddings = new OpenAIEmbeddings();
const vectorStore = await MemoryVectorStore.fromTexts(
  toVectorize,
  examples,
  embeddings
);

创建 exampleSelector​

创建了向量存储后，我们可以创建 exampleSelector。在这里我们将单独调用它，并将其上的 k 设置为仅获取与输入最接近的两个示例。

const exampleSelector = new SemanticSimilarityExampleSelector({
  vectorStore,
  k: 2,
});

// The prompt template will load examples by passing the input do the `select_examples` method
await exampleSelector.selectExamples({ input: "horse" });
[
  {
    input: "What did the cow say to the moon?",
    output: "nothing at all"
  },
  { input: "2+4", output: "6" }
]

创建提示模板​

现在我们将使用上面创建的 exampleSelector 组装提示模板。

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

// Define the few-shot prompt.
const fewShotPrompt = new FewShotChatMessagePromptTemplate({
  // The input variables select the values to pass to the example_selector
  inputVariables: ["input"],
  exampleSelector,
  // Define how ech example will be formatted.
  // In this case, each example will become 2 messages:
  // 1 human, and 1 AI
  examplePrompt: ChatPromptTemplate.fromMessages([
    ["human", "{input}"],
    ["ai", "{output}"],
  ]),
});

const results = await fewShotPrompt.invoke({ input: "What's 3+3?" });
console.log(results.toChatMessages());
[
  HumanMessage {
    lc_serializable: true,
    lc_kwargs: { content: "2+3", additional_kwargs: {}, response_metadata: {} },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "2+3",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {}
  },
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: "5",
      tool_calls: [],
      invalid_tool_calls: [],
      additional_kwargs: {},
      response_metadata: {}
    },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "5",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {},
    tool_calls: [],
    invalid_tool_calls: []
  },
  HumanMessage {
    lc_serializable: true,
    lc_kwargs: { content: "2+2", additional_kwargs: {}, response_metadata: {} },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "2+2",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {}
  },
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: "4",
      tool_calls: [],
      invalid_tool_calls: [],
      additional_kwargs: {},
      response_metadata: {}
    },
    lc_namespace: [ "langchain_core", "messages" ],
    content: "4",
    name: undefined,
    additional_kwargs: {},
    response_metadata: {},
    tool_calls: [],
    invalid_tool_calls: []
  }
]

我们可以将此少样本聊天消息提示模板传递给另一个聊天提示模板

const finalPrompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a wondrous wizard of math."],
  fewShotPrompt,
  ["human", "{input}"],
]);

const result = await fewShotPrompt.invoke({ input: "What's 3+3?" });
console.log(result);
ChatPromptValue {
  lc_serializable: true,
  lc_kwargs: {
    messages: [
      HumanMessage {
        lc_serializable: true,
        lc_kwargs: {
          content: "2+3",
          additional_kwargs: {},
          response_metadata: {}
        },
        lc_namespace: [ "langchain_core", "messages" ],
        content: "2+3",
        name: undefined,
        additional_kwargs: {},
        response_metadata: {}
      },
      AIMessage {
        lc_serializable: true,
        lc_kwargs: {
          content: "5",
          tool_calls: [],
          invalid_tool_calls: [],
          additional_kwargs: {},
          response_metadata: {}
        },
        lc_namespace: [ "langchain_core", "messages" ],
        content: "5",
        name: undefined,
        additional_kwargs: {},
        response_metadata: {},
        tool_calls: [],
        invalid_tool_calls: []
      },
      HumanMessage {
        lc_serializable: true,
        lc_kwargs: {
          content: "2+2",
          additional_kwargs: {},
          response_metadata: {}
        },
        lc_namespace: [ "langchain_core", "messages" ],
        content: "2+2",
        name: undefined,
        additional_kwargs: {},
        response_metadata: {}
      },
      AIMessage {
        lc_serializable: true,
        lc_kwargs: {
          content: "4",
          tool_calls: [],
          invalid_tool_calls: [],
          additional_kwargs: {},
          response_metadata: {}
        },
        lc_namespace: [ "langchain_core", "messages" ],
        content: "4",
        name: undefined,
        additional_kwargs: {},
        response_metadata: {},
        tool_calls: [],
        invalid_tool_calls: []
      }
    ]
  },
  lc_namespace: [ "langchain_core", "prompt_values" ],
  messages: [
    HumanMessage {
      lc_serializable: true,
      lc_kwargs: { content: "2+3", additional_kwargs: {}, response_metadata: {} },
      lc_namespace: [ "langchain_core", "messages" ],
      content: "2+3",
      name: undefined,
      additional_kwargs: {},
      response_metadata: {}
    },
    AIMessage {
      lc_serializable: true,
      lc_kwargs: {
        content: "5",
        tool_calls: [],
        invalid_tool_calls: [],
        additional_kwargs: {},
        response_metadata: {}
      },
      lc_namespace: [ "langchain_core", "messages" ],
      content: "5",
      name: undefined,
      additional_kwargs: {},
      response_metadata: {},
      tool_calls: [],
      invalid_tool_calls: []
    },
    HumanMessage {
      lc_serializable: true,
      lc_kwargs: { content: "2+2", additional_kwargs: {}, response_metadata: {} },
      lc_namespace: [ "langchain_core", "messages" ],
      content: "2+2",
      name: undefined,
      additional_kwargs: {},
      response_metadata: {}
    },
    AIMessage {
      lc_serializable: true,
      lc_kwargs: {
        content: "4",
        tool_calls: [],
        invalid_tool_calls: [],
        additional_kwargs: {},
        response_metadata: {}
      },
      lc_namespace: [ "langchain_core", "messages" ],
      content: "4",
      name: undefined,
      additional_kwargs: {},
      response_metadata: {},
      tool_calls: [],
      invalid_tool_calls: []
    }
  ]
}

与聊天模型一起使用​

最后，您可以将模型连接到少样本提示。

选择您的聊天模型

安装依赖项

提示

查看 本节了解有关安装集成包的常规说明.

yarn add @langchain/openai

添加环境变量

OPENAI_API_KEY=your-api-key

实例化模型

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0
});
const chain = finalPrompt.pipe(model);

await chain.invoke({ input: "What's 3+3?" });
AIMessage {
  lc_serializable: true,
  lc_kwargs: {
    content: "6",
    tool_calls: [],
    invalid_tool_calls: [],
    additional_kwargs: { function_call: undefined, tool_calls: undefined },
    response_metadata: {}
  },
  lc_namespace: [ "langchain_core", "messages" ],
  content: "6",
  name: undefined,
  additional_kwargs: { function_call: undefined, tool_calls: undefined },
  response_metadata: {
    tokenUsage: { completionTokens: 1, promptTokens: 51, totalTokens: 52 },
    finish_reason: "stop"
  },
  tool_calls: [],
  invalid_tool_calls: []
}

下一步​

您现在已经了解了如何将少样本示例添加到您的聊天提示中。

接下来，查看本节中有关提示模板的其他操作指南，有关 使用文本完成模型进行少样本训练 的相关操作指南，或其他 示例选择器操作指南。

此页面对您有帮助吗？


您也可以留下详细的反馈 在 GitHub 上.