使用 OpenTelemetry 进行追踪

OTEL_EXPORTER_OTLP_ENDPOINT: 覆盖端点 URL
OTEL_EXPORTER_OTLP_HEADERS: 添加自定义头（LangSmith API 密钥和项目会自动添加）
OTEL_SERVICE_NAME: 设置自定义服务名称（默认为 "langsmith"）

import os

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor

# 为 LangChain 设置环境变量
os.environ["LANGSMITH_OTEL_ENABLED"] = "true"
os.environ["LANGSMITH_TRACING"] = "true"

# 为您的自定义端点配置 OTLP 导出器
provider = TracerProvider()
otlp_exporter = OTLPSpanExporter(
    # 更改为您的提供程序端点
    endpoint="https://otel.your-provider.com/v1/traces",
    # 添加任何所需的认证头
    headers={"api-key": "your-api-key"},
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

# 创建并运行 LangChain 应用程序
prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}")
model = ChatOpenAI()
chain = prompt | model
result = chain.invoke({"topic": "programming"})
print(result.content)

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

# 配置 LangSmith OpenTelemetry 导出（无需 OTEL 环境变量或头）
configure(project_name="adk-otel-demo")


async def main():
    agent = LlmAgent(
        name="travel_assistant",
        model="gemini-2.5-flash-lite",
        instruction="You are a helpful travel assistant.",
    )

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

    user_id = "user_123"
    session_id = "session_abc"
    await session_service.create_session(app_name="travel_app", user_id=user_id, session_id=session_id)

    new_message = types.Content(parts=[types.Part(text="Hi! Recommend a weekend trip to Paris.")], role="user")

    for event in runner.run(user_id=user_id, session_id=session_id, new_message=new_message):
        print(event)


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

import asyncio
import base64
import json
from pathlib import Path
from dotenv import load_dotenv
from google.adk import Runner
from google.adk.agents import LlmAgent
from google.adk.sessions import InMemorySessionService
from google.genai import types
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider, SpanProcessor
from langsmith.integrations.otel import OtelSpanProcessor


class AttachmentSpanProcessor(SpanProcessor):
    """自定义 SpanProcessor，用于向调用 span 添加附件。"""

    def __init__(self):
        self.attachment_data = None

    def set_attachment(self, attachment_data):
        self.attachment_data = attachment_data

    def on_end(self, span):
        if span.name == "invocation" and self.attachment_data:
            attachments_json = json.dumps([self.attachment_data])
            span._attributes["langsmith.attachments"] = attachments_json

load_dotenv()

# 手动设置 TracerProvider
provider = TracerProvider()
trace.set_tracer_provider(provider)

# 首先添加附件处理器（在 LangSmith 处理器之前运行）
attachment_processor = AttachmentSpanProcessor()
provider.add_span_processor(attachment_processor)

# 其次添加 LangSmith 处理器（接收已修改的 span）
langsmith_processor = OtelSpanProcessor(project="travel-assistant")
provider.add_span_processor(langsmith_processor)

def get_flight_info(destination: str, departure_date: str) -> dict:
    """获取目的地的航班信息。"""
    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:
    """获取城市的酒店推荐。"""
    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():
    # 准备附件
    receipt_path = Path("receipt-template-example.png")
    with open(receipt_path, "rb") as img_file:
        image_bytes = img_file.read()
        image_base64 = base64.b64encode(image_bytes).decode("ascii")

    attachment_data = {
        "name": "receipt-template-example",
        "content": image_base64,
        "mime_type": "image/jpeg",
    }

    attachment_processor.set_attachment(attachment_data)

    # 创建 ADK 代理
    agent = LlmAgent(
        name="travel_assistant",
        tools=[get_flight_info, get_hotel_recommendations],
        model="gemini-2.0-flash-exp",
        instruction="You are a helpful travel assistant that can help with flights and hotels.",
    )

    # 设置会话和运行器
    session_service = InMemorySessionService()
    runner = Runner(
        app_name="travel_app",
        agent=agent,
        session_service=session_service
    )

    await session_service.create_session(
        app_name="travel_app",
        user_id="traveler_456",
        session_id="session_789"
    )

    # 向代理发送消息
    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",
    )

    # 运行代理并处理事件
    events = runner.run(
        user_id="traveler_456",
        session_id="session_789",
        new_message=new_message,
    )

    for event in events:
        print(event)

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

import os
from opentelemetry import trace
from opentelemetry.propagate import inject, extract
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
import requests
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

# 设置 OpenTelemetry 追踪提供程序
provider = TracerProvider()
otlp_exporter = OTLPSpanExporter(
    endpoint="https://api.smith.langchain.com/otel/v1/traces",
    headers={"x-api-key": os.getenv("LANGSMITH_API_KEY"), "Langsmith-Project": "my_project"}
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)
tracer = trace.get_tracer(__name__)

# 服务 A：创建一个 span 并将上下文传播到服务 B
def service_a():
    with tracer.start_as_current_span("service_a_operation") as span:
        # 创建一个链
        prompt = ChatPromptTemplate.from_template("Summarize: {text}")
        model = ChatOpenAI()
        chain = prompt | model

        # 运行链
        result = chain.invoke({"text": "OpenTelemetry is an observability framework"})

        # 将上下文传播到服务 B
        headers = {}
        inject(headers)  # 将追踪上下文注入到头中

        # 使用追踪上下文调用服务 B
        response = requests.post(
            "http://service-b.example.com/process",
            headers=headers,
            json={"summary": result.content}
        )
        return response.json()

# 服务 B：提取上下文并继续追踪
from flask import Flask, request, jsonify

app = Flask(__name__)

@app.route("/process", methods=["POST"])
def service_b_endpoint():
    # 从请求头中提取追踪上下文
    context = extract(request.headers)
    with tracer.start_as_current_span("service_b_operation", context=context) as span:
        data = request.json
        summary = data.get("summary", "")

        # 使用另一个 LLM 链处理摘要
        prompt = ChatPromptTemplate.from_template("Analyze the sentiment of: {text}")
        model = ChatOpenAI()
        chain = prompt | model
        result = chain.invoke({"text": summary})

        return jsonify({"analysis": result.content})

if __name__ == "__main__":
    app.run(port=5000)