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

# DatabricksSandbox 集成

> Databricks沙盒是Databricks平台上的受管理、隔离的计算环境。DatabricksSandbox在Databricks沙盒中运行深度智能体壳和文件系统工具，通过databricks-sdk。请参阅Databricks文档了解工作区设置和身份验证。

[Databricks](https://www.databricks.com/)沙盒是Databricks平台上的受管理、隔离的计算环境。`DatabricksSandbox`在Databricks沙盒中运行[深度智能体](https://github.com/langchain-ai/deepagents)壳和文件系统工具，通过[`databricks-sdk`](https://pypi.org/project/databricks-sdk/)。请参阅[Databricks文档](https://docs.databricks.com/)了解工作区设置和身份验证。

> [!NOTE]
>
> `DatabricksSandbox`后端需要`databricks-langchain>=0.22.0`。

## 安装

```bash pip theme={null}
pip install 'databricks-langchain[deepagents]>=0.22.0'
```

```bash uv theme={null}
uv add 'databricks-langchain[deepagents]>=0.22.0'
```

## 创建沙盒后端

`DatabricksSandbox`绑定到一个已经运行的沙盒。使用Databricks SDK进行配置（或复用）沙盒，等待其达到`RUNNING`，然后将其包装为[深度智能体后端](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/backends.md)。沙盒生命周期（创建、启动、删除）保留在您的应用代码中，而不是智能体。

```python theme={null}
import time

from databricks.sdk import WorkspaceClient
from databricks.sdk.service.sandbox import (
    ComputeSpec,
    Sandbox,
    SandboxSpec,
    SandboxState,
)
from google.protobuf.duration_pb2 import Duration

from databricks_langchain import DatabricksSandbox

client = WorkspaceClient()

sandbox_id = "my-agent-sandbox"
name = f"sandboxes/{sandbox_id}"

client.sandbox.create_sandbox(
    Sandbox(
        spec=SandboxSpec(
            compute=ComputeSpec(inactivity_timeout=Duration(seconds=900))
        )
    ),
    sandbox_id=sandbox_id,
)

# Wait until the sandbox is RUNNING before running commands.
while client.sandbox.get_sandbox(name).status.state != SandboxState.SANDBOX_STATE_RUNNING:
    time.sleep(3)

backend = DatabricksSandbox(client, name)

result = backend.execute("echo hello")
print(result.output)
```

## 与深度智能体一起使用

```python theme={null}
from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic

# `backend` from the previous step, bound to a RUNNING Databricks sandbox.
agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a coding assistant with sandbox access.",
    backend=backend,
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "Write and run a Python script"}]}
)
```

您可以使用任何LangChain对话模型，包括[Databricks模型服务支持的`ChatDatabricks`](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/chat/databricks)。

## 清理

您负责管理沙盒生命周期。
沙盒在删除之前会消耗资源，因此完成工作后请删除沙盒。

```python theme={null}
client.sandbox.delete_sandbox(name)
```

另请参阅：[沙盒](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/sandboxes.md)。

***

> 官方原文：[src/oss/python/integrations/sandboxes/databricks.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/sandboxes/databricks.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.