DEVOCEAN

#홈페이지 Example
from langchain import hub
from langchain_community.llms import OpenAI
from langchain.agents import AgentExecutor, create_react_agent

from langchain_core.prompts import PromptTemplate

template = '''Answer the following questions as best you can. You have access to the following tools:

{tools}

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: {input}
Thought:{agent_scratchpad}'''

prompt = PromptTemplate.from_template(template)
model = OpenAI()
tools = ...

agent = create_react_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

agent_executor.invoke({"input": "hi"})

# Use with chat history
from langchain_core.messages import AIMessage, HumanMessage
agent_executor.invoke(
    {
        "input": "what's my name?",
        # Notice that chat_history is a string
        # since this prompt is aimed at LLMs, not chat models
        "chat_history": "Human: My name is Bob\nAI: Hello Bob!",
    }
)

Warning

This implementation is based on the foundational ReAct paper but is older and not 
well-suited for production applications. For a more robust and feature-rich 
implementation, we recommend using the create_react_agent function from the LangGraph 
library. See the [reference doc](https://langchain-
ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.crea
te_react_agent) for more information.

#공식예제
#https://langchain-ai.github.io/langgraph/agents/agents/#2-create-an-agent
from langgraph.prebuilt import create_react_agent

def get_weather(city: str) -> str:  
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_react_agent(
    model="anthropic:claude-3-7-sonnet-latest",  
    tools=[get_weather],  
    prompt="You are a helpful assistant"  
)

# Run the agent
agent.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)

#langchain
import logging
import requests
from langchain.agents import (
    AgentExecutor,
    create_react_agent,
)
from langchain_core.tools import Tool
from langchain_openai import ChatOpenAI

import logging
# Set up logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)

#logging을 통해서 debbuging진행
class LoggingChatOpenAI(ChatOpenAI):
    def _call(self, prompt: str, stop=None) -> str:
        logger.debug(f"Prompt: {prompt}")
        logger.debug(f"Stop: {stop}")
        response = super()._call(prompt, stop)
        logger.debug(f"Response: {response}")
        return response


# Use the LoggingChatOpenAI class instead of ChatOpenAI
model = LoggingChatOpenAI(
    model="MyModel",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    api_key="mytoken", 
    base_url="http://myvllmservice/v1",
)

# Define a very simple tool function that returns the current time
def get_weather(city: str) -> str:  
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"
    
# List of tools available to the agent
tools = [
    Tool(
        name="Weather",  # Name of the tool
        func=get_weather,  # Function that the tool will execute
        # Description of the tool
        description=get_weather.__doc__,
    ),
]

# Initialize a ChatOpenAI model
from langchain_core.prompts import PromptTemplate

template = '''Answer the following questions as best you can. You have access to the following tools:

{tools}

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: {input}
Thought:{agent_scratchpad}'''

prompt = PromptTemplate.from_template(template)

# Create the ReAct agent using the create_react_agent function
agent = create_react_agent(
    llm=model,
    tools=tools,
    prompt=prompt,
    stop_sequence=True,
)

# Create an agent executor from the agent and tools
agent_executor = AgentExecutor.from_agent_and_tools(
    agent=agent,
    tools=tools,
    verbose=True,
)

# Run the agent with a test query
response = agent_executor.invoke({"input": "tell me what time is it now"})

# Print the response from the agent
print("response:", response)

#langgraph
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
from langchain_mcp_adapters.tools import load_mcp_tools
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
import asyncio

import logging
# Set up logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)

class LoggingChatOpenAI(ChatOpenAI):
    def _call(self, prompt: str, stop=None) -> str:
        logger.debug(f"Prompt: {prompt}")
        logger.debug(f"Stop: {stop}")
        response = super()._call(prompt, stop)
        logger.debug(f"Response: {response}")
        return response

def get_weather(city: str) -> str:  
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

# Use the LoggingChatOpenAI class instead of ChatOpenAI
model = LoggingChatOpenAI(
    model="MyModel",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    api_key="mytoken", 
    base_url="http://myvllmservice/v1",
)
# MCP Server 설정(이경우 Client.py파일과 Server.py파일이 같은 위치에 있음)
server_params = StdioServerParameters(
    command="python",
    # Make sure to update to the full absolute path to your math_server.py file
    args=["weather_server_stdio.py"],
)
from langchain_core.prompts import PromptTemplate

template = '''Answer the following questions as best you can. You have access to the following tools:

{tools}

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: {input}
Thought:{agent_scratchpad}'''

# MCP Python SDK를 활용해서 MCP Server를 사용함
async def run_agent():
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            # Initialize the connection
            await session.initialize()

            # MCP Server에 있는 Tool리스트를 가지고 옵니다.
            tools = await load_mcp_tools(session)

            # Tools와 Model을 사용해서 Agent 생성
            agent = create_react_agent(
                model = model,
                tools = tools,
                prompt = template
            )
            
            # Agent한테 Query를 진행해, Agent가 알아서 tools을 사용하게 만듭니다.
            agent_response = await agent.ainvoke({"messages": "what's time is it now?. i'm live in seoul city. find about city seoul"})
            return agent_response

# Run the async function
if __name__ == "__main__":
    result = asyncio.run(run_agent())
    print(result)

#weather_server_stdio.py
from mcp.server.fastmcp import FastMCP
import datetime

mcp = FastMCP("Weather")

@mcp.tool()
async def get_weather(location: str) -> str:
    """Get weather for location."""
    return "It's always sunny in New York"

if __name__ == "__main__":
    mcp.run(transport="stdio")

#langchain을 사용한 경우
DEBUG:openai._base_client:Request options: {'method': 'post', 'url': 
'/chat/completions', 'files': None, 'idempotency_key': 'stainless-python-retry-
75c082d1-3005-4aa5-9924-8b88f7afb4b3', 'json_data': {'messages': [{'content': 'Answer 
the following questions as best you can. You have access to the following 
tools:\n\nTime(city: str) -> str - Get weather for a given city.\n\nUse the following 
format:\n\nQuestion: the input question you must answer\nThought: you should always 
think about what to do\nAction: the action to take, should be one of [Time]\nAction 
Input: the input to the action\nObservation: the result of the action\n... (this 
Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the 
final answer\nFinal Answer: the final answer to the original input 
question\n\nBegin!\n\nQuestion: how about weather in seoul?\nThought:', 'role': 
'user'}], 'model': 'Gemma-3-27b-it', 'stop': ['\nObservation'], 'stream': True, 
'temperature': 0.0}}

Answer the following questions as best you can. You have access to the following tools:
Time(city: str) -> str - Get weather for a given city.

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [Time]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer\nFinal Answer: the final answer to the original input question

Begin!

Question: how about weather in seoul?
Thought:'

#https://python.langchain.com/api_reference/_modules/langchain/agents/react/agent.html#create_react_agent
def create_react_agent(
    llm: BaseLanguageModel,
    tools: Sequence[BaseTool],
    prompt: BasePromptTemplate,
    output_parser: Optional[AgentOutputParser] = None,
    tools_renderer: ToolsRenderer = render_text_description,
    *,
    stop_sequence: Union[bool, list[str]] = True,
) -> Runnable:
    
    missing_vars = {"tools", "tool_names", "agent_scratchpad"}.difference(
        prompt.input_variables + list(prompt.partial_variables)
    )
    if missing_vars:
        raise ValueError(f"Prompt missing required variables: {missing_vars}")

    prompt = prompt.partial(
        tools=tools_renderer(list(tools)),
        tool_names=", ".join([t.name for t in tools]),
    )
    ...

DEBUG:openai._base_client:Request options: {'method': 'post', 'url': 
'/chat/completions', 'files': None, 'idempotency_key': 'stainless-python-retry-
2ce447ef-a0e2-434c-94a2-5577d9ffcbb7', 'json_data': {'messages': [{'content': 'Answer 
the following questions as best you can. You have access to the following 
tools:\n\n{tools}\n\nUse the following format:\n\nQuestion: the input question you 
must answer\nThought: you should always think about what to do\nAction: the action to 
take, should be one of [{tool_names}]\nAction Input: the input to the 
action\nObservation: the result of the action\n... (this Thought/Action/Action 
Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal 
Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: 
{input}\nThought:{agent_scratchpad}', 'role': 'system'}, {'content': "what's time is 
it now?. i'm live in seoul city. find about city seoul", 'role': 'user'}], 'model': 
'Gemma-3-27b-it', 'stream': False, 'temperature': 0.0, 'tools': [{'type': 'function', 
'function': {'name': 'get_current_time', 'description': 'useful tools when you need 
to know current time', 'parameters': {'properties': {'city': {'type': 'string'}}, 
'required': ['city'], 'type': 'object'}}}]}}

'tools': [
    {'type': 'function',
    'function': {
        'name': 'get_current_time',
        'description': 'useful tools when you need to know current time', 
        'parameters': {
            'properties': {
                'city': {'type': 'string'}
            }, 'required': ['city'],
                'type': 'object'
            }
        }
    }
]