提示模板

¥Prompt Templates

提示模板有助于将用户输入和参数转换为语言模型的指令。这可用于指导模型的响应，帮助其理解上下文并生成相关且连贯的基于语言的输出。

¥Prompt templates help to translate user input and parameters into instructions for a language model. This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.

提示模板以对象作为输入，其中每个键代表提示模板中需要填写的变量。

¥Prompt Templates take as input an object, where each key represents a variable in the prompt template to fill in.

提示模板输出一个 PromptValue。此 PromptValue 可以传递给 LLM 或 ChatModel，也可以转换为字符串或消息列表。此 PromptValue 存在的原因是为了方便在字符串和消息之间切换。

¥Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages. The reason this PromptValue exists is to make it easy to switch between strings and messages.

有几种不同类型的提示模板：

¥There are a few different types of prompt templates:

字符串提示模板

¥String PromptTemplates

这些提示模板用于格式化单个字符串，通常用于更简单的输入。例如，构建和使用 PromptTemplate 的常用方法如下：

¥These prompt templates are used to format a single string, and generally are used for simpler inputs. For example, a common way to construct and use a PromptTemplate is as follows:

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

const promptTemplate = PromptTemplate.fromTemplate(
  "Tell me a joke about {topic}"
);

await promptTemplate.invoke({ topic: "cats" });

StringPromptValue {
  value: 'Tell me a joke about cats'
}

ChatPromptTemplates

这些提示模板用于格式化消息列表。这些 "templates" 本身由一个模板列表组成。例如，构建和使用 ChatPromptTemplate 的常用方法如下：

¥These prompt templates are used to format a list of messages. These "templates" consist of a list of templates themselves. For example, a common way to construct and use a ChatPromptTemplate is as follows:

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

const promptTemplate = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant"],
  ["user", "Tell me a joke about {topic}"],
]);

await promptTemplate.invoke({ topic: "cats" });

ChatPromptValue {
  messages: [
    SystemMessage {
      "content": "You are a helpful assistant",
      "additional_kwargs": {},
      "response_metadata": {}
    },
    HumanMessage {
      "content": "Tell me a joke about cats",
      "additional_kwargs": {},
      "response_metadata": {}
    }
  ]
}

在上面的示例中，此 ChatPromptTemplate 在调用时将构造两条消息。第一步是系统消息，它没有需要格式化的变量。第二个参数是 HumanMessage，将由用户传入的 topic 变量格式化。

¥In the above example, this ChatPromptTemplate will construct two messages when called. The first is a system message, that has no variables to format. The second is a HumanMessage, and will be formatted by the topic variable the user passes in.

MessagesPlaceholder

此提示模板负责在特定位置添加消息列表。在上面的 ChatPromptTemplate 中，我们看到了如何格式化两条消息，每条消息都是一个字符串。但是，如果我们希望用户传入一个消息列表，我们会将其插入到特定位置，该怎么办？这就是使用 MessagesPlaceholder 的方式。

¥This prompt template is responsible for adding a list of messages in a particular place. In the above ChatPromptTemplate, we saw how we could format two messages, each one a string. But what if we wanted the user to pass in a list of messages that we would slot into a particular spot? This is how you use MessagesPlaceholder.

import {
  ChatPromptTemplate,
  MessagesPlaceholder,
} from "@langchain/core/prompts";
import { HumanMessage } from "@langchain/core/messages";

const promptTemplate = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant"],
  new MessagesPlaceholder("msgs"),
]);

await promptTemplate.invoke({ msgs: [new HumanMessage("hi!")] });

ChatPromptValue {
  messages: [
    SystemMessage {
      "content": "You are a helpful assistant",
      "additional_kwargs": {},
      "response_metadata": {}
    },
    HumanMessage {
      "content": "hi!",
      "additional_kwargs": {},
      "response_metadata": {}
    }
  ]
}

这将生成一个包含两条消息的列表，第一条是系统消息，第二条是我们传入的 HumanMessage。如果我们传入了 5 条消息，那么总共会产生 6 条消息（系统消息加上传入的 5 条消息）。这对于将消息列表插入特定位置很有用。

¥This will produce a list of two messages, the first one being a system message, and the second one being the HumanMessage we passed in. If we had passed in 5 messages, then it would have produced 6 messages in total (the system message plus the 5 passed in). This is useful for letting a list of messages be slotted into a particular spot.

另一种无需显式使用 MessagesPlaceholder 类即可完成相同操作的方法是：

¥An alternative way to accomplish the same thing without using the MessagesPlaceholder class explicitly is:

const promptTemplate = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant"],
  ["placeholder", "{msgs}"], // <-- This is the changed part
]);

有关如何使用输出解析器的详细信息，请参阅相关操作指南。

¥For specifics on how to use prompt templates, see the relevant how-to guides here.

提示模板

字符串提示模板​

ChatPromptTemplates​

MessagesPlaceholder​

字符串提示模板

ChatPromptTemplates

MessagesPlaceholder