> ## Documentation Index
> Fetch the complete documentation index at: https://cndoc-langchain.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Hugging Face 集成

> 使用 LangChain Python 集成 Hugging Face 嵌入模型。

## 本地嵌入

您可以使用 `HuggingFaceEmbeddings` 类在本地生成嵌入。这利用了 `sentence_transformers` 库来下载模型权重并直接在您的机器上运行。

让我们加载 Hugging Face 嵌入类。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU  langchain langchain-huggingface sentence_transformers
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_huggingface.embeddings import HuggingFaceEmbeddings
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
text = "This is a test document."
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
query_result = embeddings.embed_query(text)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
query_result[:3]
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[-0.04895168915390968, -0.03986193612217903, -0.021562768146395683]
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
doc_result = embeddings.embed_documents([text])
```

## Hugging Face 推理端点（无服务器 API）

如果您不想在本地下载模型，可以通过 [推理端点](https://huggingface.co/docs/inference-endpoints/index) 访问嵌入模型，这让我们能够使用 Hugging Face 可扩展无服务器基础设施上的开源模型。

确保您已安装 huggingface\_hub，它通常已包含在 langchain-huggingface 中。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
!pip install huggingface_hub
```

首先，我们需要从 [Hugging Face](https://huggingface.co/settings/tokens) 获取一个只读 API 密钥。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import os
from getpass import getpass

os.environ["HUGGINGFACEHUB_API_TOKEN"] = getpass()
```

现在我们可以使用 `HuggingFaceEndpointEmbeddings` 类通过 API 远程运行开源嵌入模型。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
embeddings = HuggingFaceEndpointEmbeddings(
    model="sentence-transformers/all-MiniLM-L6-v2"
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
text = "This is a test document."
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
query_result = embeddings.embed_query(text)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
query_result[:3]
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [连接这些文档](/use-these-docs) 到 Claude、VSCode 等，通过 MCP 获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/embeddings/huggingfacehub.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>