Databricks Unity Catalog (UC)
本笔记本展示了如何将UC函数用作LangChain工具，包括LangChain和LangGraph代理API。
请参阅Databricks文档（AWS|Azure|GCP）以了解如何在UC中创建SQL或Python函数。不要跳过函数和参数注释，这些注释对于LLM正确调用函数至关重要。
在这个示例笔记本中，我们创建了一个简单的Python函数，该函数执行任意代码，并将其用作LangChain工具：
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仓库内的一个安全和隔离的环境中运行。
%pip install --upgrade --quiet databricks-sdk langchain-community databricks-langchain langgraph mlflow
Note: you may need to restart the kernel to use updated packages.
from databricks_langchain import ChatDatabricks
llm = ChatDatabricks(endpoint="databricks-meta-llama-3-70b-instruct")
from databricks.sdk import WorkspaceClient
from langchain_community.tools.databricks import UCFunctionToolkit
tools = (
UCFunctionToolkit(
# You can find the SQL warehouse ID in its UI after creation.
warehouse_id="xxxx123456789"
)
.include(
# Include functions as tools using their qualified names.
# You can use "{catalog_name}.{schema_name}.*" to get all functions in a schema.
"main.tools.python_exec",
)
.get_tools()
)
API Reference:UCFunctionToolkit
（可选）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
import os
os.environ["UC_TOOL_CLIENT_EXECUTION_TIMEOUT"] = "200"
LangGraph 代理示例
from langgraph.prebuilt import create_react_agent
agent = create_react_agent(
llm,
tools,
state_modifier="You are a helpful assistant. Make sure to use tool for information.",
)
agent.invoke({"messages": [{"role": "user", "content": "36939 * 8922.4"}]})
API Reference:create_react_agent
{'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
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)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "36939 * 8922.4"})
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `main__tools__python_exec` with `{'code': 'print(36939 * 8922.4)'}`
[0m[36;1m[1;3m{"format": "SCALAR", "value": "329584533.59999996\n", "truncated": false}[0m[32;1m[1;3mThe result of the multiplication is:
329584533.59999996[0m
[1m> Finished chain.[0m
{'input': '36939 * 8922.4',
'output': 'The result of the multiplication is:\n\n329584533.59999996'}