LangGraph로 추적하기

pip install langchain_openai langgraph

export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>
# 이 예제는 OpenAI를 사용하지만, 원하는 LLM 제공자를 사용할 수 있습니다
export OPENAI_API_KEY=<your-openai-api-key>
# 여러 워크스페이스에 연결된 LangSmith API 키의 경우, 사용할 워크스페이스를 지정하기 위해 LANGSMITH_WORKSPACE_ID 환경 변수를 설정하세요.
export LANGSMITH_WORKSPACE_ID=<your-workspace-id>

from typing import Literal
from langchain.messages import HumanMessage
from langchain_openai import ChatOpenAI
from langchain.tools import tool
from langgraph.prebuilt import ToolNode
from langgraph.graph import StateGraph, MessagesState

@tool
def search(query: str):
    """Call to surf the web."""
    if "sf" in query.lower() or "san francisco" in query.lower():
        return "It's 60 degrees and foggy."
    return "It's 90 degrees and sunny."

tools = [search]
tool_node = ToolNode(tools)

model = ChatOpenAI(model="gpt-4o", temperature=0).bind_tools(tools)

def should_continue(state: MessagesState) -> Literal["tools", "__end__"]:
    messages = state['messages']
    last_message = messages[-1]
    if last_message.tool_calls:
        return "tools"
    return "__end__"

def call_model(state: MessagesState):
    messages = state['messages']
    # Invoking `model` will automatically infer the correct tracing context
    response = model.invoke(messages)
    return {"messages": [response]}

workflow = StateGraph(MessagesState)
workflow.add_node("agent", call_model)
workflow.add_node("tools", tool_node)
workflow.add_edge("__start__", "agent")
workflow.add_conditional_edges(
    "agent",
    should_continue,
)
workflow.add_edge("tools", 'agent')

app = workflow.compile()

final_state = app.invoke(
    {"messages": [HumanMessage(content="what is the weather in sf")]},
    config={"configurable": {"thread_id": 42}}
)

final_state["messages"][-1].content

pip install openai langsmith langgraph

export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>
# 이 예제는 OpenAI를 사용하지만, 원하는 LLM 제공자를 사용할 수 있습니다
export OPENAI_API_KEY=<your-openai-api-key>

import json
import openai
import operator
from langsmith import traceable
from langsmith.wrappers import wrap_openai
from typing import Annotated, Literal, TypedDict
from langgraph.graph import StateGraph

class State(TypedDict):
    messages: Annotated[list, operator.add]

tool_schema = {
    "type": "function",
    "function": {
        "name": "search",
        "description": "Call to surf the web.",
        "parameters": {
            "type": "object",
            "properties": {"query": {"type": "string"}},
            "required": ["query"],
        },
    },
}

# 도구 함수를 데코레이팅하면 올바른 컨텍스트로 자동으로 추적됩니다
@traceable(run_type="tool", name="Search Tool")
def search(query: str):
    """Call to surf the web."""
    if "sf" in query.lower() or "san francisco" in query.lower():
        return "It's 60 degrees and foggy."
    return "It's 90 degrees and sunny."

tools = [search]

def call_tools(state):
    function_name_to_function = {"search": search}
    messages = state["messages"]
    tool_call = messages[-1]["tool_calls"][0]
    function_name = tool_call["function"]["name"]
    function_arguments = tool_call["function"]["arguments"]
    arguments = json.loads(function_arguments)
    function_response = function_name_to_function[function_name](**arguments)
    tool_message = {
        "tool_call_id": tool_call["id"],
        "role": "tool",
        "name": function_name,
        "content": function_response,
    }
    return {"messages": [tool_message]}

wrapped_client = wrap_openai(openai.Client())

def should_continue(state: State) -> Literal["tools", "__end__"]:
    messages = state["messages"]
    last_message = messages[-1]
    if last_message["tool_calls"]:
        return "tools"
    return "__end__"

def call_model(state: State):
    messages = state["messages"]
    # 래핑된 클라이언트를 호출하면 올바른 추적 컨텍스트가 자동으로 추론됩니다
    response = wrapped_client.chat.completions.create(
        messages=messages, model="gpt-4o-mini", tools=[tool_schema]
    )
    raw_tool_calls = response.choices[0].message.tool_calls
    tool_calls = [tool_call.to_dict() for tool_call in raw_tool_calls] if raw_tool_calls else []
    response_message = {
        "role": "assistant",
        "content": response.choices[0].message.content,
        "tool_calls": tool_calls,
    }
    return {"messages": [response_message]}

workflow = StateGraph(State)
workflow.add_node("agent", call_model)
workflow.add_node("tools", call_tools)
workflow.add_edge("__start__", "agent")
workflow.add_conditional_edges(
    "agent",
    should_continue,
)
workflow.add_edge("tools", 'agent')

app = workflow.compile()

final_state = app.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)

final_state["messages"][-1]["content"]