> ## 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.

# Athena 集成

> 使用 LangChain Python 与 Athena 文档加载器集成。

> [Amazon Athena](https://aws.amazon.com/athena/) 是一项基于开源框架构建的无服务器交互式分析服务，支持开放表和文件格式。`Athena` 提供了一种简化、灵活的方式来分析存储在其原始位置的海量数据（PB 级）。您可以使用 SQL 或 Python 从 Amazon Simple Storage Service (S3) 数据湖以及 30 多种数据源（包括本地数据源或其他云系统）中分析数据或构建应用程序。`Athena` 基于开源的 `Trino` 和 `Presto` 引擎以及 `Apache Spark` 框架构建，无需进行任何资源预置或配置工作。

本笔记本将介绍如何从 `AWS Athena` 加载文档。

## 环境设置

请按照 [设置 AWS 账户的说明](https://docs.aws.amazon.com/athena/latest/ug/setting-up.html) 进行操作。

安装 Python 库：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
! pip install boto3
```

## 示例

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

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
database_name = "my_database"
s3_output_path = "s3://my_bucket/query_results/"
query = "SELECT * FROM my_table"
profile_name = "my_profile"

loader = AthenaLoader(
    query=query,
    database=database_name,
    s3_output_uri=s3_output_path,
    profile_name=profile_name,
)

documents = loader.load()
print(documents)
```

包含元数据列的示例

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
database_name = "my_database"
s3_output_path = "s3://my_bucket/query_results/"
query = "SELECT * FROM my_table"
profile_name = "my_profile"
metadata_columns = ["_row", "_created_at"]

loader = AthenaLoader(
    query=query,
    database=database_name,
    s3_output_uri=s3_output_path,
    profile_name=profile_name,
    metadata_columns=metadata_columns,
)

documents = loader.load()
print(documents)
```

***

<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\athena.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>