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

# MathpixPDFLoader 集成

> 使用 LangChain Python 集成 MathpixPDFLoader 文档加载器。

灵感来源于 Daniel Gross 的代码片段：[https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21](https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21)

## 概述

### 集成详情

| 类                                                                                                                      | 包                                                                                   | 本地支持 | 可序列化 | JS 支持 |
| :--------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------- | :--: | :--: | :---: |
| [`MathPixPDFLoader`](https://reference.langchain.com/python/langchain-community/document_loaders/pdf/MathpixPDFLoader) | [`langchain-community`](https://reference.langchain.com/python/langchain-community) |   ✅  |   ❌  |   ❌   |

### 加载器特性

|         来源         | 文档惰性加载 | 原生异步支持 |
| :----------------: | :----: | :----: |
| `MathPixPDFLoader` |    ✅   |    ❌   |

## 设置

### 凭证

注册 Mathpix 并[创建 API 密钥](https://mathpix.com/docs/ocr/creating-an-api-key)，以在环境中设置 `MATHPIX_API_KEY` 变量。

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

if "MATHPIX_API_KEY" not in os.environ:
    os.environ["MATHPIX_API_KEY"] = getpass.getpass("请输入您的 Mathpix API 密钥：")
```

要启用模型调用的自动追踪，请设置您的 [LangSmith](/langsmith/home) API 密钥：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("请输入您的 LangSmith API 密钥：")
os.environ["LANGSMITH_TRACING"] = "true"
```

### 安装

安装 **langchain-community**。

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

## 初始化

现在我们可以初始化加载器了：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.document_loaders import MathpixPDFLoader

file_path = "./example_data/layout-parser-paper.pdf"
loader = MathpixPDFLoader(file_path)
```

## 加载

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
docs = loader.load()
docs[0]
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
print(docs[0].metadata)
```

## 惰性加载

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
page = []
for doc in loader.lazy_load():
    page.append(doc)
    if len(page) >= 10:
        # 执行一些分页操作，例如：
        # index.upsert(page)

        page = []
```

***

## API 参考

有关 `MathpixPDFLoader` 所有功能和配置的详细文档，请访问 [API 参考](https://reference.langchain.com/python/langchain-community/document_loaders/pdf/MathpixPDFLoader)

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\document_loaders\mathpix.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>
