ChatHuggingFace

这将帮助你开始使用langchain_huggingface 聊天模型。要查看所有ChatHuggingFace功能和配置的详细文档，请参阅API参考。要查看Hugging Face支持的模型列表，请参阅此页面。

概览

集成细节

集成细节

Class	包	本地	序列化	JS支持	Package downloads	Package 最新版本
ChatHuggingFace	langchain-huggingface	✅	beta	❌

模型特性​

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	Token级流式传输	原生异步	Token 使用	对数概率
✅	✅	❌	✅	✅	✅	❌	✅	✅	❌

设置

要访问Hugging Face模型，您需要创建一个Hugging Face账户，获取API密钥，并安装langchain-huggingface集成包。

Credentials

生成一个Hugging Face 访问令牌，并将其存储为环境变量：HUGGINGFACEHUB_API_TOKEN。

import getpass
import os

if not os.getenv("HUGGINGFACEHUB_API_TOKEN"):
    os.environ["HUGGINGFACEHUB_API_TOKEN"] = getpass.getpass("Enter your token: ")

安装

Class	包	本地	序列化	JS支持	Package downloads	Package 最新版本
ChatHuggingFace	langchain_huggingface	✅	❌	❌

模型特性​

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	Token级流式传输	原生异步	Token 使用	对数概率
✅	✅	❌	❌	❌	❌	❌	❌	❌	❌

设置

要访问langchain_huggingface模型，您需要创建一个/Hugging Face账户、获取API密钥并安装langchain_huggingface集成包。

Credentials

您需要将一个Hugging Face访问令牌保存为环境变量：HUGGINGFACEHUB_API_TOKEN。

import getpass
import os

os.environ["HUGGINGFACEHUB_API_TOKEN"] = getpass.getpass(
    "Enter your Hugging Face API key: "
)

%pip install --upgrade --quiet  langchain-huggingface text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2 bitsandbytes accelerate

[notice] A new release of pip is available: 24.0 -> 24.1.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.

Instantiation

您可以以两种不同的方式实例化一个ChatHuggingFace模型，要么从一个HuggingFaceEndpoint，要么从一个HuggingFacePipeline。

HuggingFaceEndpoint

from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint

llm = HuggingFaceEndpoint(
    repo_id="HuggingFaceH4/zephyr-7b-beta",
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
)

chat_model = ChatHuggingFace(llm=llm)

API 参考:ChatHuggingFace |HuggingFace 端点

The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: fineGrained).
Your token has been saved to /Users/isaachershenson/.cache/huggingface/token
Login successful

HuggingFacePipeline

from langchain_huggingface import ChatHuggingFace, HuggingFacePipeline

llm = HuggingFacePipeline.from_model_id(
    model_id="HuggingFaceH4/zephyr-7b-beta",
    task="text-generation",
    pipeline_kwargs=dict(
        max_new_tokens=512,
        do_sample=False,
        repetition_penalty=1.03,
    ),
)

chat_model = ChatHuggingFace(llm=llm)

API 参考:ChatHuggingFace |HuggingFace 流水线

config.json:   0%|          | 0.00/638 [00:00<?, ?B/s]

model.safetensors.index.json:   0%|          | 0.00/23.9k [00:00<?, ?B/s]

Downloading shards:   0%|          | 0/8 [00:00<?, ?it/s]

model-00001-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]

model-00002-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00003-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00004-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00005-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00006-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]

model-00007-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]

model-00008-of-00008.safetensors:   0%|          | 0.00/816M [00:00<?, ?B/s]

Loading checkpoint shards:   0%|          | 0/8 [00:00<?, ?it/s]

generation_config.json:   0%|          | 0.00/111 [00:00<?, ?B/s]

使用量化初始化

要运行模型的量化版本，可以指定一个bitsandbytes量化配置，如下所示：

from transformers import BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype="float16",
    bnb_4bit_use_double_quant=True,
)

并将它作为其model_kwargs的一部分传递给HuggingFacePipeline:

llm = HuggingFacePipeline.from_model_id(
    model_id="HuggingFaceH4/zephyr-7b-beta",
    task="text-generation",
    pipeline_kwargs=dict(
        max_new_tokens=512,
        do_sample=False,
        repetition_penalty=1.03,
        return_full_text=False,
    ),
    model_kwargs={"quantization_config": quantization_config},
)

chat_model = ChatHuggingFace(llm=llm)

Invocation

from langchain_core.messages import (
    HumanMessage,
    SystemMessage,
)

messages = [
    SystemMessage(content="You're a helpful assistant"),
    HumanMessage(
        content="What happens when an unstoppable force meets an immovable object?"
    ),
]

ai_msg = chat_model.invoke(messages)

API 参考:人类消息 |系统消息

print(ai_msg.content)

According to the popular phrase and hypothetical scenario, when an unstoppable force meets an immovable object, a paradoxical situation arises as both forces are seemingly contradictory. On one hand, an unstoppable force is an entity that cannot be stopped or prevented from moving forward, while on the other hand, an immovable object is something that cannot be moved or displaced from its position. 

In this scenario, it is un

API 参考

详细文档请参阅所有ChatHuggingFace功能和配置： https://python.langchain.com/api_reference/huggingface/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html

API 参考

详细介绍了所有ChatHuggingFace特性和配置的文档请参阅API参考：https://python.langchain.com/api_reference/huggingface/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html

相关

• 聊天模型 概念指南
• 聊天模型 使用指南