> ## 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.

# Azure AI 数据集成

> 使用 LangChain Python 与 Azure AI 数据文档加载器集成。

> [Azure AI Foundry（原 Azure AI Studio）](https://ai.azure.com/) 提供将数据资产上传到云存储以及从以下来源注册现有数据资产的功能：
>
> * `Microsoft OneLake`
> * `Azure Blob Storage`
> * `Azure Data Lake gen 2`

与 `AzureBlobStorageContainerLoader` 和 `AzureBlobStorageFileLoader` 相比，这种方法的优势在于身份验证被无缝处理到云存储中。你可以使用*基于身份的*数据访问控制或*基于凭据的*（例如 SAS 令牌、账户密钥）数据访问控制。在基于凭据的数据访问情况下，你无需在代码中指定密钥或设置密钥保管库——系统会为你处理这些。

本笔记本介绍如何从 AI Studio 中的数据资产加载文档对象。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU azureml-fsspec azure-ai-generative
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from azure.ai.resources.client import AIClient
from azure.identity import DefaultAzureCredential
from langchain_community.document_loaders import AzureAIDataLoader
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 创建与项目的连接
client = AIClient(
    credential=DefaultAzureCredential(),
    subscription_id="<subscription_id>",
    resource_group_name="<resource_group_name>",
    project_name="<project_name>",
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 获取数据资产的最新版本
data_asset = client.data.get(name="<data_asset_name>", label="latest")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 加载数据资产
loader = AzureAIDataLoader(url=data_asset.path)
```

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

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpaa9xl6ch/fake.docx'}, lookup_index=0)]
```

## 指定 glob 模式

你还可以指定 glob 模式，以更精细地控制要加载的文件。在下面的示例中，只有扩展名为 `pdf` 的文件会被加载。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
loader = AzureAIDataLoader(url=data_asset.path, glob="*.pdf")
```

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

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpujbkzf_l/fake.docx'}, lookup_index=0)]
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档连接](/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/document_loaders/azure_ai_data.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>