> ## 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.

# Databricks Unity Catalog (UC) 集成

> 使用 LangChain Python 与 Databricks Unity Catalog (UC) 工具进行集成。

本笔记本展示了如何使用 UC 函数作为 LangChain 工具，同时利用 LangChain 和 LangGraph 代理 API。

请参阅 Databricks 文档（[AWS](https://docs.databricks.com/en/sql/language-manual/sql-ref-syntax-ddl-create-sql-function.html)|[Azure](https://learn.microsoft.com/en-us/azure/databricks/sql/language-manual/sql-ref-syntax-ddl-create-sql-function)|[GCP](https://docs.gcp.databricks.com/en/sql/language-manual/sql-ref-syntax-ddl-create-sql-function.html)）以了解如何在 UC 中创建 SQL 或 Python 函数。请勿跳过函数和参数注释，这对 LLM 正确调用函数至关重要。

在本示例笔记本中，我们创建一个执行任意代码的简单 Python 函数，并将其用作 LangChain 工具：

```sql theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
CREATE FUNCTION main.tools.python_exec (
  code STRING COMMENT 'Python code to execute. Remember to print the final result to stdout.'
)
RETURNS STRING
LANGUAGE PYTHON
COMMENT 'Executes Python code and returns its stdout.'
AS $$
  import sys
  from io import StringIO
  stdout = StringIO()
  sys.stdout = stdout
  exec(code)
  return stdout.getvalue()
$$
```

它在 Databricks SQL 仓库内的安全且隔离的环境中运行。

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

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

llm = ChatDatabricks(endpoint="databricks-meta-llama-3-70b-instruct")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from databricks_langchain.uc_ai import (
    DatabricksFunctionClient,
    UCFunctionToolkit,
    set_uc_function_client,
)

client = DatabricksFunctionClient()
set_uc_function_client(client)

tools = UCFunctionToolkit(
    # Include functions as tools using their qualified names.
    # You can use "{catalog_name}.{schema_name}.*" to get all functions in a schema.
    function_names=["main.tools.python_exec"]
).tools
```

（可选）若要增加获取函数执行响应的重试时间，请设置环境变量 UC\_TOOL\_CLIENT\_EXECUTION\_TIMEOUT。默认重试时间值为 120 秒。

## LangGraph 代理示例

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

os.environ["UC_TOOL_CLIENT_EXECUTION_TIMEOUT"] = "200"
```

## LangGraph 代理示例

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent


agent = create_agent(
    llm,
    tools,
    system_prompt="You are a helpful assistant. Make sure to use tool for information.",
)
agent.invoke({"messages": [{"role": "user", "content": "36939 * 8922.4"}]})
```

```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'messages': [HumanMessage(content='36939 * 8922.4', additional_kwargs={}, response_metadata={}, id='1a10b10b-8e37-48c7-97a1-cac5006228d5'),
  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_a8f3986f-4b91-40a3-8d6d-39f431dab69b', 'type': 'function', 'function': {'name': 'main__tools__python_exec', 'arguments': '{"code": "print(36939 * 8922.4)"}'}}]}, response_metadata={'prompt_tokens': 771, 'completion_tokens': 29, 'total_tokens': 800}, id='run-865c3613-20ba-4e80-afc8-fde1cfb26e5a-0', tool_calls=[{'name': 'main__tools__python_exec', 'args': {'code': 'print(36939 * 8922.4)'}, 'id': 'call_a8f3986f-4b91-40a3-8d6d-39f431dab69b', 'type': 'tool_call'}]),
  ToolMessage(content='{"format": "SCALAR", "value": "329584533.59999996\\n", "truncated": false}', name='main__tools__python_exec', id='8b63d4c8-1a3d-46a5-a719-393b2ef36770', tool_call_id='call_a8f3986f-4b91-40a3-8d6d-39f431dab69b'),
  AIMessage(content='The result of the multiplication is:\n\n329584533.59999996', additional_kwargs={}, response_metadata={'prompt_tokens': 846, 'completion_tokens': 22, 'total_tokens': 868}, id='run-22772404-611b-46e4-9956-b85e4a385f0f-0')]}
```

## LangChain 代理示例

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant. Make sure to use tool for information.",
        ),
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}"),
    ]
)

agent = create_tool_calling_agent(llm, tools, prompt)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "36939 * 8922.4"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new AgentExecutor chain...

Invoking: `main__tools__python_exec` with `{'code': 'print(36939 * 8922.4)'}`


{"format": "SCALAR", "value": "329584533.59999996\n", "truncated": false}The result of the multiplication is:

329584533.59999996

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'input': '36939 * 8922.4',
 'output': 'The result of the multiplication is:\n\n329584533.59999996'}
```

***

<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\tools\databricks.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>