Skip to main content
兼容性仅在 Node.js 上可用。
该模块基于 llama.cppnode-llama-cpp Node.js 绑定,允许你使用本地运行的 LLM。这使你可以使用能够在笔记本电脑环境中运行的更小的量化模型,非常适合测试和记录想法,而无需产生费用!

设置

你需要安装 node-llama-cpp 模块的 3 主版本,以便与你的本地模型进行通信。
npm
npm install -S node-llama-cpp@3 @langchain/community @langchain/core
你还需要一个本地 Llama 3 模型(或 node-llama-cpp 支持的模型)。你需要将此模型的路径作为参数的一部分传递给 LlamaCpp 模块(见示例)。 开箱即用的 node-llama-cpp 已针对在 MacOS 平台上运行进行了调整,支持 Apple M 系列处理器的 Metal GPU。如果你需要关闭此功能或需要支持 CUDA 架构,请参阅 node-llama-cpp 的文档。 关于获取和准备 llama3 的建议,请参阅此模块的 LLM 版本的文档。 LangChain.js 贡献者注意事项:如果你想运行与此模块相关的测试,你需要将本地模型的路径放入环境变量 LLAMA_PATH 中。

用法

基本用法

在这种情况下,我们传入一个包装为消息的提示,并期望得到一个响应。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { HumanMessage } from "@langchain/core/messages";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const model = await ChatLlamaCpp.initialize({ modelPath: llamaPath });

const response = await model.invoke([
  new HumanMessage({ content: "My name is John." }),
]);
console.log({ response });

/*
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: 'Hello John.',
      additional_kwargs: {}
    },
    lc_namespace: [ 'langchain', 'schema' ],
    content: 'Hello John.',
    name: undefined,
    additional_kwargs: {}
  }
*/

系统消息

我们还可以提供系统消息,请注意,使用 llama_cpp 模块时,系统消息将导致创建一个新会话。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { SystemMessage, HumanMessage } from "@langchain/core/messages";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const model = await ChatLlamaCpp.initialize({ modelPath: llamaPath });

const response = await model.invoke([
  new SystemMessage(
    "You are a pirate, responses must be very verbose and in pirate dialect, add 'Arr, m'hearty!' to each sentence."
  ),
  new HumanMessage("Tell me where Llamas come from?"),
]);
console.log({ response });

/*
  AIMessage {
    lc_serializable: true,
    lc_kwargs: {
      content: "Arr, m'hearty! Llamas come from the land of Peru.",
      additional_kwargs: {}
    },
    lc_namespace: [ 'langchain', 'schema' ],
    content: "Arr, m'hearty! Llamas come from the land of Peru.",
    name: undefined,
    additional_kwargs: {}
  }
*/

此模块也可以与链一起使用,请注意,使用更复杂的链将需要足够强大的 llama3 版本,例如 70B 版本。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { LLMChain } from "@langchain/classic/chains";
import { PromptTemplate } from "@langchain/core/prompts";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const model = await ChatLlamaCpp.initialize({
  modelPath: llamaPath,
  temperature: 0.5,
});

const prompt = PromptTemplate.fromTemplate(
  "What is a good name for a company that makes {product}?"
);
const chain = new LLMChain({ llm: model, prompt });

const response = await chain.invoke({ product: "colorful socks" });

console.log({ response });

/*
  {
  text: `I'm not sure what you mean by "colorful socks" but here are some ideas:\n` +
    '\n' +
    '- Sock-it to me!\n' +
    '- Socks Away\n' +
    '- Fancy Footwear'
  }
*/

流式传输

我们也可以使用 Llama CPP 进行流式传输,这可以使用原始的“单提示”字符串:
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const model = await ChatLlamaCpp.initialize({
  modelPath: llamaPath,
  temperature: 0.7,
});

const stream = await model.stream("Tell me a short story about a happy Llama.");

for await (const chunk of stream) {
  console.log(chunk.content);
}

/*

  Once
   upon
   a
   time
  ,
   in
   a
   green
   and
   sunny
   field
  ...
*/
或者你可以提供多条消息,请注意,这将获取输入,然后向模型提交 Llama3 格式的提示。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { SystemMessage, HumanMessage } from "@langchain/core/messages";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const llamaCpp = await ChatLlamaCpp.initialize({
  modelPath: llamaPath,
  temperature: 0.7,
});

const stream = await llamaCpp.stream([
  new SystemMessage(
    "You are a pirate, responses must be very verbose and in pirate dialect."
  ),
  new HumanMessage("Tell me about Llamas?"),
]);

for await (const chunk of stream) {
  console.log(chunk.content);
}

/*

  Ar
  rr
  r
  ,
   me
   heart
  y
  !

   Ye
   be
   ask
  in
  '
   about
   llam
  as
  ,
   e
  h
  ?
  ...
*/
使用 invoke 方法,我们也可以实现流式生成,并使用 signal 来中止生成。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { SystemMessage, HumanMessage } from "@langchain/core/messages";

const llamaPath = "/Replace/with/path/to/your/model/gguf-llama3-Q4_0.bin";

const model = await ChatLlamaCpp.initialize({
  modelPath: llamaPath,
  temperature: 0.7,
});

const controller = new AbortController();

setTimeout(() => {
  controller.abort();
  console.log("Aborted");
}, 5000);

await model.invoke(
  [
    new SystemMessage(
      "You are a pirate, responses must be very verbose and in pirate dialect."
    ),
    new HumanMessage("Tell me about Llamas?"),
  ],
  {
    signal: controller.signal,
    callbacks: [
      {
        handleLLMNewToken(token) {
          console.log(token);
        },
      },
    ],
  }
);
/*

  Once
   upon
   a
   time
  ,
   in
   a
   green
   and
   sunny
   field
  ...
  Aborted

  AbortError

*/

相关