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

# Databricks unity catalog (Uc) integration

> Integrate with the Databricks unity catalog (Uc) tool using LangChain Python.

This notebook shows how to use UC functions as LangChain tools, with both LangChain and LangGraph agent APIs.

See Databricks documentation ([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)) to learn how to create SQL or Python functions in UC. Do not skip function and parameter comments, which are critical for LLMs to call functions properly.

In this example notebook, we create a simple Python function that executes arbitrary code and use it as a LangChain tool:

```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 $$
  import sys
  from io import StringIO
  stdout = StringIO()
  sys.stdout = stdout
  exec(code)
  return stdout.getvalue()
$$
```

It runs in a secure and isolated environment within a Databricks SQL warehouse.

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

(Optional) To increase the retry time for getting a function execution response, set environment variable UC\_TOOL\_CLIENT\_EXECUTION\_TIMEOUT. Default retry time value is 120s.

## LangGraph agent example

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

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

## LangGraph agent example

```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 agent example

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

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/tools/databricks.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>