LangSmith 通过 OpenTelemetry 集成支持跟踪 Google Agent Development Kit（ADK）应用程序。本指南向您展示如何自动捕获 Google ADK 智能体的跟踪并将它们发送到 LangSmith 进行监控和分析。

​
安装

使用您首选的包管理器安装所需的包： 
pip install langsmith google-adk
需要 LangSmith Python SDK 版本 langsmith>=0.4.26 以获得最佳的 OpenTelemetry 支持。

​
设置

​
1. 配置环境变量

设置您的 LangSmith API 密钥和项目名称： 
export LANGSMITH_API_KEY=<your_langsmith_api_key>
export LANGSMITH_PROJECT=<your_project_name>

​
2. 配置 OpenTelemetry 集成

在您的 Google ADK 应用程序中，导入并配置 LangSmith OpenTelemetry 集成。这将自动为 OpenTelemetry 检测 Google ADK 跨度。 
from langsmith.integrations.otel import configure

# Configure LangSmith tracing
configure(project_name="adk-example")  # Optional: can also use LANGSMITH_PROJECT and LANGSMITH_API_KEY environment variables
Alternatively, you can use the Openinference GoogleADKInstrumentor: 
from langsmith.integrations.otel import configure
from openinference.instrumentation.google_adk import GoogleADKInstrumentor

# Configure LangSmith tracing
configure(project_name="adk-example")

# Instrument Google ADK directly
GoogleADKInstrumentor().instrument()
您不需要设置任何 OpenTelemetry 环境变量或手动配置导出器 —configure() 自动处理所有内容。

​
3. 创建并运行您的 ADK 智能体

配置完成后，您的 Google ADK 应用程序将自动将跟踪发送到 LangSmith： 此示例包括一个设置智能体、会话和运行器的最小应用，然后发送消息并流式传输事件。 
import asyncio
from langsmith.integrations.otel import configure
from google.adk import Runner
from google.adk.agents import LlmAgent
from google.adk.sessions import InMemorySessionService
from google.genai import types

# Configure LangSmith tracing
configure(project_name="travel-assistant")

# Define your tools
def get_flight_info(destination: str, departure_date: str) -> dict:
    """Get flight information for a destination."""
    return {
        "destination": destination,
        "departure_date": departure_date,
        "price": "$450",
        "duration": "5h 30m",
        "airline": "Example Airways"
    }

def get_hotel_recommendations(city: str, check_in: str) -> dict:
    """Get hotel recommendations for a city."""
    return {
        "city": city,
        "check_in": check_in,
        "hotels": [
            {"name": "Grand Plaza Hotel", "rating": 4.5, "price": "$120/night"},
            {"name": "City Center Inn", "rating": 4.2, "price": "$95/night"}
        ]
    }

async def main():
    # Create your ADK agent
    agent = LlmAgent(
        name="travel_assistant",
        tools=[get_flight_info, get_hotel_recommendations],
        model="gemini-2.5-flash-lite",
        instruction="You are a helpful travel assistant that can help with flights and hotels.",
    )

    # Set up session service and runner
    session_service = InMemorySessionService()
    runner = Runner(
        app_name="travel_app",
        agent=agent,
        session_service=session_service
    )

    # Create a session
    user_id = "traveler_456"
    session_id = "session_789"
    await session_service.create_session(
        app_name="travel_app",
        user_id=user_id,
        session_id=session_id
    )

    # Send a message to the agent
    new_message = types.Content(
        parts=[types.Part(text="I need to book a flight to Paris for March 15th and find a good hotel.")],
        role="user",
    )

    # Run the agent and process events
    events = runner.run(
        user_id=user_id,
        session_id=session_id,
        new_message=new_message,
    )

    for event in events:
        print(event)

if __name__ == "__main__":
    asyncio.run(main())

​
View traces in LangSmith

  • Agent conversations: Complete conversation flows between users and your ADK agents.
  • Tool calls: Individual function calls made by your agents.
  • Model interactions: LLM requests and responses using Gemini models.
  • Session information: User and session context for organizing related traces.
  • Model interactions: LLM requests and responses using Gemini models
LangSmith dashboard with raw input from run and trace information.

​
Advanced usage

​
Custom metadata and tags

You can add custom metadata to your traces by setting span attributes in your ADK application: 
from opentelemetry import trace

# Get the current tracer
tracer = trace.get_tracer(__name__)

async def main():
    with tracer.start_as_current_span("travel_booking_session") as span:
        # Add custom metadata
        span.set_attribute("langsmith.metadata.user_type", "premium")
        span.set_attribute("langsmith.metadata.booking_source", "mobile_app")
        span.set_attribute("langsmith.span.tags", "travel,booking,premium")

        agent = LlmAgent(
            name="travel_assistant",
            tools=[get_flight_info, get_hotel_recommendations],
            model="gemini-2.5-flash-lite",
            instruction="You are a helpful travel assistant that can help with flights and hotels.",
        )

        session_service = InMemorySessionService()
        runner = Runner(
            app_name="travel_app",
            agent=agent,
            session_service=session_service
        )

        # Continue with your ADK workflow
        # ...
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.