Llama CPP
仅适用于 Node.js。
此模块基于 node-llama-cpp 用于 llama.cpp 的 Node.js 绑定,允许您与本地运行的 LLM 进行交互。这使您可以与运行在笔记本电脑环境中的较小的量化模型进行交互,非常适合在不产生费用的情况下测试和草拟想法!
设置
您需要安装 node-llama-cpp 模块来与您的本地模型进行通信。
请参阅 此部分以获取有关安装集成软件包的常规说明。
- npm
- Yarn
- pnpm
npm install -S node-llama-cpp @langchain/community
yarn add node-llama-cpp @langchain/community
pnpm add node-llama-cpp @langchain/community
您还需要一个本地 Llama 2 模型(或 node-llama-cpp 支持的模型)。您需要将此模型的路径作为参数传递给 LlamaCpp 模块(请参阅示例)。
开箱即用的 node-llama-cpp
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。如果您需要关闭此功能或需要 CUDA 架构支持,请参阅 node-llama-cpp 的文档。
有关获取和准备 llama2
的建议,请参阅此模块的 LLM 版本的文档。
致 LangChain.js 贡献者:如果您要运行与此模块相关的测试,则需要将本地模型的路径放入环境变量 LLAMA_PATH
中。
使用
基本使用
在这种情况下,我们传递一个作为消息包装的提示并期望得到响应。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { HumanMessage } from "@langchain/core/messages";
const llamaPath = "/Replace/with/path/to/your/model/gguf-llama2-q4_0.bin";
const model = new ChatLlamaCpp({ 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: {}
}
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
- HumanMessage 来自
@langchain/core/messages
系统消息
我们还可以提供系统消息,请注意,使用 llama_cpp
模块,系统消息将导致创建新的会话。
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-llama2-q4_0.bin";
const model = new ChatLlamaCpp({ 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: {}
}
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
- SystemMessage 来自
@langchain/core/messages
- HumanMessage 来自
@langchain/core/messages
链
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适合 llama2
的强大版本,例如 70B 版本。
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
import { LLMChain } from "langchain/chains";
import { PromptTemplate } from "@langchain/core/prompts";
const llamaPath = "/Replace/with/path/to/your/model/gguf-llama2-q4_0.bin";
const model = new ChatLlamaCpp({ 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'
}
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
- LLMChain 来自
langchain/chains
- PromptTemplate 来自
@langchain/core/prompts
流式传输
我们还可以使用 Llama CPP 进行流式传输,这可以使用原始的“单个提示”字符串来完成
import { ChatLlamaCpp } from "@langchain/community/chat_models/llama_cpp";
const llamaPath = "/Replace/with/path/to/your/model/gguf-llama2-q4_0.bin";
const model = new ChatLlamaCpp({ 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
...
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
或者,您可以提供多条消息,请注意,这会获取输入,然后将 Llama2 格式的提示提交给模型。
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-llama2-q4_0.bin";
const llamaCpp = new ChatLlamaCpp({ 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
?
...
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
- SystemMessage 来自
@langchain/core/messages
- HumanMessage 来自
@langchain/core/messages
使用 invoke
方法,我们还可以实现流生成,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-llama2-q4_0.bin";
const model = new ChatLlamaCpp({ 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
*/
API 参考
- ChatLlamaCpp 来自
@langchain/community/chat_models/llama_cpp
- SystemMessage 来自
@langchain/core/messages
- HumanMessage 来自
@langchain/core/messages