Skip to main content
Open on GitHub

Hugging Face

与Hugging Face平台相关的所有功能。

安装​

大多数 Hugging Face 集成都可在 langchain-huggingface 包中使用。

pip install langchain-huggingface

聊天模型​

ChatHuggingFace​

我们可以使用 Hugging Face LLM 类或直接使用 ChatHuggingFace 类。

查看一个 使用示例。

from langchain_huggingface import ChatHuggingFace
API 参考：ChatHuggingFace

LLMs​

HuggingFaceEndpoint​

查看一个 使用示例。

from langchain_huggingface import HuggingFaceEndpoint
API 参考：HuggingFaceEndpoint

HuggingFacePipeline​

Hugging Face模型可以通过HuggingFacePipeline类在本地运行。

查看一个 使用示例。

from langchain_huggingface import HuggingFacePipeline
API 参考：HuggingFacePipeline

嵌入模型​

HuggingFaceEmbeddings​

查看一个 使用示例。

from langchain_huggingface import HuggingFaceEmbeddings

HuggingFaceEndpointEmbeddings​

查看一个 使用示例。

from langchain_huggingface import HuggingFaceEndpointEmbeddings

HuggingFaceInferenceAPIEmbeddings​

查看一个 使用示例。

from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings

HuggingFaceInstructEmbeddings​

查看一个 使用示例。

from langchain_community.embeddings import HuggingFaceInstructEmbeddings

HuggingFaceBgeEmbeddings​

BGE models on the HuggingFace are one of the best open-source embedding models. BGE model is created by the Beijing Academy of Artificial Intelligence (BAAI). BAAI is a private non-profit organization engaged in AI research and development.

查看一个 使用示例。

from langchain_community.embeddings import HuggingFaceBgeEmbeddings

文档加载器​

Hugging Face数据集​

Hugging Face Hub is home to over 75,000 datasets in more than 100 languages that can be used for a broad range of tasks across NLP, Computer Vision, and Audio. They used for a diverse range of tasks such as translation, automatic speech recognition, and image classification.

我们需要安装 datasets 个 Python 包。

pip install datasets

查看一个 使用示例。

from langchain_community.document_loaders.hugging_face_dataset import HuggingFaceDatasetLoader

Hugging Face模型加载器​

Load model information from Hugging Face Hub, including README content.

This loader interfaces with the Hugging Face Models API to fetch and load model metadata and README files. The API allows you to search and filter models based on specific criteria such as model tags, authors, and more.

from langchain_community.document_loaders import HuggingFaceModelLoader

图片说明​

它使用 Hugging Face 模型来自动生成图像描述。

我们需要安装几个 Python 包。

pip install transformers pillow

查看一个 使用示例。

from langchain_community.document_loaders import ImageCaptionLoader
API 参考：ImageCaptionLoader

工具​

Hugging Face Hub 工具​

Hugging Face Tools support text I/O and are loaded using the load_huggingface_tool function.

我们需要安装几个 Python 包。

pip install transformers huggingface_hub

查看一个 使用示例。

from langchain_community.agent_toolkits.load_tools import load_huggingface_tool

Hugging Face 文本转语音模型推理。​

It is a wrapper around OpenAI Text-to-Speech API.

from langchain_community.tools.audio import HuggingFaceTextToSpeechModelInference