现已发布！阅读关于 11 月新增功能和修复的内容。

AI 工具包中的跟踪

AI 工具包提供跟踪功能，帮助您监控和分析 AI 应用程序的性能。您可以跟踪 AI 应用程序的执行情况，包括与生成式 AI 模型的交互，从而深入了解其行为和性能。

AI 工具包托管本地 HTTP 和 gRPC 服务器以收集跟踪数据。收集器服务器与 OTLP（OpenTelemetry 协议）兼容，大多数语言模型 SDK 都直接支持 OTLP，或者有非 Microsoft 的检测库来支持它。使用 AI 工具包可视化收集的检测数据。

所有支持 OTLP 并遵循 生成式 AI 系统的语义约定的框架或 SDK 都受支持。下表包含经过兼容性测试的常用 AI SDK。

Azure AI 推理 Foundry Agent Service Anthropic Gemini LangChain OpenAI SDK 3 OpenAI Agents SDK
Python ✅ ✅ ✅ （traceloop，monocle）1,2 ✅ （monocle） ✅ （LangSmith，monocle）1,2 ✅ （opentelemetry-python-contrib，monocle）1 ✅ （Logfire，monocle）1,2
TS/JS ✅ ✅ ✅ （traceloop）1,2 ❌ ✅ （traceloop）1,2 ✅ （traceloop）1,2 ❌
  1. 方括号中的 SDK 是非 Microsoft 工具，它们添加了 OTLP 支持，因为官方 SDK 不支持 OTLP。
  2. 这些工具不完全遵循 OpenTelemetry 关于生成式 AI 系统的规则。
  3. 对于 OpenAI SDK，仅支持 聊天完成 API。不支持 响应 API。

如何开始跟踪

  1. 通过在树状视图中选择“**跟踪**”来打开跟踪 Web 视图。

  2. 选择“**启动收集器**”按钮以启动本地 OTLP 跟踪收集器服务器。

    Screenshot showing the Start Collector button in the Tracing webview.

  3. 使用代码片段启用检测。有关不同语言和 SDK 的代码片段，请参阅“设置检测”部分。

  4. 通过运行应用程序生成跟踪数据。

  5. 在跟踪 Web 视图中，选择“**刷新**”按钮以查看新的跟踪数据。

    Screenshot showing the Trace List in the Tracing webview.

设置检测

在 AI 应用程序中设置跟踪以收集跟踪数据。以下代码片段展示了如何为不同的 SDK 和语言设置跟踪。

所有 SDK 的过程相似。

  • 向 LLM 或代理应用程序添加跟踪。
  • 设置 OTLP 跟踪导出器以使用 AITK 本地收集器。
Azure AI 推理 SDK - Python

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http azure-ai-inference[opentelemetry]

设置

import os
os.environ["AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED"] = "true"
os.environ["AZURE_SDK_TRACING_IMPLEMENTATION"] = "opentelemetry"

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter

resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-azure-ai-agents"
})
provider = TracerProvider(resource=resource)
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces",
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

from azure.ai.inference.tracing import AIInferenceInstrumentor
AIInferenceInstrumentor().instrument(True)
Azure AI 推理 SDK - TypeScript/JavaScript

安装

npm install @azure/opentelemetry-instrumentation-azure-sdk @opentelemetry/api @opentelemetry/exporter-trace-otlp-proto @opentelemetry/instrumentation @opentelemetry/resources @opentelemetry/sdk-trace-node

设置

const { context } = require('@opentelemetry/api');
const { resourceFromAttributes } = require('@opentelemetry/resources');
const {
  NodeTracerProvider,
  SimpleSpanProcessor
} = require('@opentelemetry/sdk-trace-node');
const { OTLPTraceExporter } = require('@opentelemetry/exporter-trace-otlp-proto');

const exporter = new OTLPTraceExporter({
  url: 'https://:4318/v1/traces'
});
const provider = new NodeTracerProvider({
  resource: resourceFromAttributes({
    'service.name': 'opentelemetry-instrumentation-azure-ai-inference'
  }),
  spanProcessors: [new SimpleSpanProcessor(exporter)]
});
provider.register();

const { registerInstrumentations } = require('@opentelemetry/instrumentation');
const {
  createAzureSdkInstrumentation
} = require('@azure/opentelemetry-instrumentation-azure-sdk');

registerInstrumentations({
  instrumentations: [createAzureSdkInstrumentation()]
});
Foundry Agent Service - Python

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http azure-ai-inference[opentelemetry]

设置

import os
os.environ["AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED"] = "true"
os.environ["AZURE_SDK_TRACING_IMPLEMENTATION"] = "opentelemetry"

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter

resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-azure-ai-agents"
})
provider = TracerProvider(resource=resource)
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces",
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

from azure.ai.agents.telemetry import AIAgentsInstrumentor
AIAgentsInstrumentor().instrument(True)
Foundry Agent Service - TypeScript/JavaScript

安装

npm install @azure/opentelemetry-instrumentation-azure-sdk @opentelemetry/api @opentelemetry/exporter-trace-otlp-proto @opentelemetry/instrumentation @opentelemetry/resources @opentelemetry/sdk-trace-node

设置

const { context } = require('@opentelemetry/api');
const { resourceFromAttributes } = require('@opentelemetry/resources');
const {
  NodeTracerProvider,
  SimpleSpanProcessor
} = require('@opentelemetry/sdk-trace-node');
const { OTLPTraceExporter } = require('@opentelemetry/exporter-trace-otlp-proto');

const exporter = new OTLPTraceExporter({
  url: 'https://:4318/v1/traces'
});
const provider = new NodeTracerProvider({
  resource: resourceFromAttributes({
    'service.name': 'opentelemetry-instrumentation-azure-ai-inference'
  }),
  spanProcessors: [new SimpleSpanProcessor(exporter)]
});
provider.register();

const { registerInstrumentations } = require('@opentelemetry/instrumentation');
const {
  createAzureSdkInstrumentation
} = require('@azure/opentelemetry-instrumentation-azure-sdk');

registerInstrumentations({
  instrumentations: [createAzureSdkInstrumentation()]
});
Anthropic - Python

OpenTelemetry

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-instrumentation-anthropic

设置

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter

resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-anthropic-traceloop"
})
provider = TracerProvider(resource=resource)
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces",
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

from opentelemetry.instrumentation.anthropic import AnthropicInstrumentor
AnthropicInstrumentor().instrument()

Monocle

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http monocle_apptrace

设置

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-anthropic",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)
Anthropic - TypeScript/JavaScript

安装

npm install @traceloop/node-server-sdk

设置

const { initialize } = require('@traceloop/node-server-sdk');
const { trace } = require('@opentelemetry/api');

initialize({
  appName: 'opentelemetry-instrumentation-anthropic-traceloop',
  baseUrl: 'https://:4318',
  disableBatch: true
});
Google Gemini - Python

OpenTelemetry

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-instrumentation-google-genai

设置

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter

resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-google-genai"
})
provider = TracerProvider(resource=resource)
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces",
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

from opentelemetry.instrumentation.google_genai import GoogleGenAiSdkInstrumentor
GoogleGenAiSdkInstrumentor().instrument(enable_content_recording=True)

Monocle

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http monocle_apptrace

设置

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-google-genai",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)
LangChain - Python

LangSmith

安装

pip install langsmith[otel]

设置

import os
os.environ["LANGSMITH_OTEL_ENABLED"] = "true"
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://:4318"

Monocle

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http monocle_apptrace

设置

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-langchain",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)
LangChain - TypeScript/JavaScript

安装

npm install @traceloop/node-server-sdk

设置

const { initialize } = require('@traceloop/node-server-sdk');
initialize({
  appName: 'opentelemetry-instrumentation-langchain-traceloop',
  baseUrl: 'https://:4318',
  disableBatch: true
});
OpenAI - Python

OpenTelemetry

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-instrumentation-openai-v2

设置

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter
from opentelemetry.instrumentation.openai_v2 import OpenAIInstrumentor
import os

os.environ["OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT"] = "true"

# Set up resource
resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-openai"
})

# Create tracer provider
trace.set_tracer_provider(TracerProvider(resource=resource))

# Configure OTLP exporter
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces"
)

# Add span processor
trace.get_tracer_provider().add_span_processor(
    BatchSpanProcessor(otlp_exporter)
)

# Set up logger provider
logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

# Enable OpenAI instrumentation
OpenAIInstrumentor().instrument()

Monocle

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http monocle_apptrace

设置

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-openai",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)
OpenAI - TypeScript/JavaScript

安装

npm install @traceloop/instrumentation-openai @traceloop/node-server-sdk

设置

const { initialize } = require('@traceloop/node-server-sdk');
initialize({
  appName: 'opentelemetry-instrumentation-openai-traceloop',
  baseUrl: 'https://:4318',
  disableBatch: true
});
OpenAI Agents SDK - Python

Logfire

安装

pip install logfire

设置

import logfire
import os

os.environ["OTEL_EXPORTER_OTLP_TRACES_ENDPOINT"] = "https://:4318/v1/traces"

logfire.configure(
    service_name="opentelemetry-instrumentation-openai-agents-logfire",
    send_to_logfire=False,
)
logfire.instrument_openai_agents()

Monocle

安装

pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http monocle_apptrace

设置

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-openai-agents",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)

示例 1：使用 Opentelemetry 通过 Azure AI 推理 SDK 设置跟踪

以下端到端示例使用 Python 中的 Azure AI 推理 SDK，并展示了如何设置跟踪提供程序和检测。

先决条件

要运行此示例，您需要以下先决条件：

设置您的开发环境

使用以下说明部署一个预配置的开发环境，其中包含运行此示例所需的所有依赖项。

  1. 设置 GitHub 个人访问令牌

    使用免费的 GitHub Models 作为示例模型。

    打开 GitHub 开发人员设置并选择“**生成新令牌**”。

    重要

    令牌需要 models:read 权限，否则将返回未经授权。令牌将发送到 Microsoft 服务。

  2. 创建环境变量

    创建一个环境变量，使用以下代码片段之一将您的令牌设置为客户端代码的密钥。将 <your-github-token-goes-here> 替换为您实际的 GitHub 令牌。

    bash

    export GITHUB_TOKEN="<your-github-token-goes-here>"

    powershell

    $Env:GITHUB_TOKEN="<your-github-token-goes-here>"

    Windows 命令提示符

    set GITHUB_TOKEN=<your-github-token-goes-here>

  3. 安装 Python 包

    以下命令将安装使用 Azure AI 推理 SDK 进行跟踪所需的 Python 包。

    pip install opentelemetry-sdk opentelemetry-exporter-otlp-proto-http azure-ai-inference[opentelemetry]

  4. 设置跟踪

    1. 在计算机上为项目创建一个新的本地目录。

      mkdir my-tracing-app

    2. 导航到您创建的目录。

      cd my-tracing-app

    3. 在该目录中打开 Visual Studio Code。

      code .

  5. 创建 Python 文件

    1. 在 my-tracing-app 目录中，创建一个名为 main.py 的 Python 文件。

      您将在此处添加设置跟踪和与 Azure AI 推理 SDK 交互的代码。

    2. 将以下代码添加到 main.py 并保存文件。

      import os

### Set up for OpenTelemetry tracing ###
os.environ["AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED"] = "true"
os.environ["AZURE_SDK_TRACING_IMPLEMENTATION"] = "opentelemetry"

from opentelemetry import trace, _events
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.sdk._logs import LoggerProvider
from opentelemetry.sdk._logs.export import BatchLogRecordProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk._events import EventLoggerProvider
from opentelemetry.exporter.otlp.proto.http._log_exporter import OTLPLogExporter

github_token = os.environ["GITHUB_TOKEN"]

resource = Resource(attributes={
    "service.name": "opentelemetry-instrumentation-azure-ai-inference"
})
provider = TracerProvider(resource=resource)
otlp_exporter = OTLPSpanExporter(
    endpoint="https://:4318/v1/traces",
)
processor = BatchSpanProcessor(otlp_exporter)
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)

logger_provider = LoggerProvider(resource=resource)
logger_provider.add_log_record_processor(
    BatchLogRecordProcessor(OTLPLogExporter(endpoint="https://:4318/v1/logs"))
)
_events.set_event_logger_provider(EventLoggerProvider(logger_provider))

from azure.ai.inference.tracing import AIInferenceInstrumentor
AIInferenceInstrumentor().instrument()
### Set up for OpenTelemetry tracing ###

from azure.ai.inference import ChatCompletionsClient
from azure.ai.inference.models import UserMessage
from azure.ai.inference.models import TextContentItem
from azure.core.credentials import AzureKeyCredential

client = ChatCompletionsClient(
    endpoint = "https://models.inference.ai.azure.com",
    credential = AzureKeyCredential(github_token),
    api_version = "2024-08-01-preview",
)

response = client.complete(
    messages = [
        UserMessage(content = [
            TextContentItem(text = "hi"),
        ]),
    ],
    model = "gpt-4.1",
    tools = [],
    response_format = "text",
    temperature = 1,
    top_p = 1,
)

print(response.choices[0].message.content)

  6. 运行代码

    1. 在 Visual Studio Code 中打开一个新终端。

    2. 在终端中，使用命令 python main.py 运行代码。

  7. 在 AI 工具包中检查跟踪数据

    运行代码并刷新跟踪 Web 视图后，列表中会出现一个新的跟踪。

    选择跟踪以打开跟踪详细信息 Web 视图。

    Screenshot showing selecting a trace from the Trace List in the Tracing webview.

    在左侧的 span 树状视图中查看应用程序的完整执行流程。

    选择右侧的 span 详细信息视图中的 span，然后在“**输入 + 输出**”选项卡中查看生成式 AI 消息。

    选择“**元数据**”选项卡以查看原始元数据。

    Screenshot showing the Trace Details view in the Tracing webview.

示例 2：使用 Monocle 通过 OpenAI Agents SDK 设置跟踪

以下端到端示例在 Python 中使用 OpenAI Agents SDK 和 Monocle，并展示了如何为多代理旅行预订系统设置跟踪。

先决条件

要运行此示例，您需要以下先决条件：

设置您的开发环境

使用以下说明部署一个预配置的开发环境，其中包含运行此示例所需的所有依赖项。

  1. 创建环境变量

    使用以下代码片段之一为您的 OpenAI API 密钥创建环境变量。将 <your-openai-api-key> 替换为您实际的 OpenAI API 密钥。

    bash

    export OPENAI_API_KEY="<your-openai-api-key>"

    powershell

    $Env:OPENAI_API_KEY="<your-openai-api-key>"

    Windows 命令提示符

    set OPENAI_API_KEY=<your-openai-api-key>

    或者，在您的项目目录中创建一个 .env 文件。

    OPENAI_API_KEY=<your-openai-api-key>

  2. 安装 Python 包

    创建具有以下内容的 requirements.txt 文件。

    opentelemetry-sdk
opentelemetry-exporter-otlp-proto-http
monocle_apptrace
openai-agents
python-dotenv

    使用以下命令安装包：

    pip install -r requirements.txt

  3. 设置跟踪

    1. 在计算机上为项目创建一个新的本地目录。

      mkdir my-agents-tracing-app

    2. 导航到您创建的目录。

      cd my-agents-tracing-app

    3. 在该目录中打开 Visual Studio Code。

      code .

  4. 创建 Python 文件

    1. 在 my-agents-tracing-app 目录中，创建一个名为 main.py 的 Python 文件。

      您将在此处添加使用 Monocle 设置跟踪和与 OpenAI Agents SDK 交互的代码。

    2. 将以下代码添加到 main.py 并保存文件。

      import os

from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

# Import monocle_apptrace
from monocle_apptrace import setup_monocle_telemetry

# Setup Monocle telemetry with OTLP span exporter for traces
setup_monocle_telemetry(
    workflow_name="opentelemetry-instrumentation-openai-agents",
    span_processors=[
        BatchSpanProcessor(
            OTLPSpanExporter(endpoint="https://:4318/v1/traces")
        )
    ]
)

from agents import Agent, Runner, function_tool

# Define tool functions
@function_tool
def book_flight(from_airport: str, to_airport: str) -> str:
    """Book a flight between airports."""
    return f"Successfully booked a flight from {from_airport} to {to_airport} for 100 USD."

@function_tool
def book_hotel(hotel_name: str, city: str) -> str:
    """Book a hotel reservation."""
    return f"Successfully booked a stay at {hotel_name} in {city} for 50 USD."

@function_tool
def get_weather(city: str) -> str:
    """Get weather information for a city."""
    return f"The weather in {city} is sunny and 75°F."

# Create specialized agents
flight_agent = Agent(
    name="Flight Agent",
    instructions="You are a flight booking specialist. Use the book_flight tool to book flights.",
    tools=[book_flight],
)

hotel_agent = Agent(
    name="Hotel Agent",
    instructions="You are a hotel booking specialist. Use the book_hotel tool to book hotels.",
    tools=[book_hotel],
)

weather_agent = Agent(
    name="Weather Agent",
    instructions="You are a weather information specialist. Use the get_weather tool to provide weather information.",
    tools=[get_weather],
)

# Create a coordinator agent with tools
coordinator = Agent(
    name="Travel Coordinator",
    instructions="You are a travel coordinator. Delegate flight bookings to the Flight Agent, hotel bookings to the Hotel Agent, and weather queries to the Weather Agent.",
    tools=[
        flight_agent.as_tool(
            tool_name="flight_expert",
            tool_description="Handles flight booking questions and requests.",
        ),
        hotel_agent.as_tool(
            tool_name="hotel_expert",
            tool_description="Handles hotel booking questions and requests.",
        ),
        weather_agent.as_tool(
            tool_name="weather_expert",
            tool_description="Handles weather information questions and requests.",
        ),
    ],
)

# Run the multi-agent workflow
if __name__ == "__main__":
    import asyncio

    result = asyncio.run(
        Runner.run(
            coordinator,
            "Book me a flight today from SEA to SFO, then book the best hotel there and tell me the weather.",
        )
    )
    print(result.final_output)

  5. 运行代码

    1. 在 Visual Studio Code 中打开一个新终端。

    2. 在终端中，使用命令 python main.py 运行代码。

  6. 在 AI 工具包中检查跟踪数据

    运行代码并刷新跟踪 Web 视图后，列表中会出现一个新的跟踪。

    选择跟踪以打开跟踪详细信息 Web 视图。

    Screenshot showing selecting a trace from the Trace List in the Tracing webview.

    在左侧的 span 树状视图中，查看应用程序的完整执行流程，包括代理调用、工具调用和代理委托。

    选择右侧的 span 详细信息视图中的 span，然后在“**输入 + 输出**”选项卡中查看生成式 AI 消息。

    选择“**元数据**”选项卡以查看原始元数据。

    Screenshot showing the Trace Details view in the Tracing webview.

您学到了什么

在本文中，您学习了如何

  • 使用 Azure AI 推理 SDK 和 OpenTelemetry 在 AI 应用程序中设置跟踪。
  • 配置 OTLP 跟踪导出器，将跟踪数据发送到本地收集器服务器。
  • 运行您的应用程序以生成跟踪数据，并在 AI 工具包 Web 视图中查看跟踪。
  • 使用多种 SDK 和语言（包括 Python 和 TypeScript/JavaScript）以及通过 OTLP 的非 Microsoft 工具来使用跟踪功能。
  • 使用提供的代码片段检测各种 AI 框架（Anthropic、Gemini、LangChain、OpenAI 等）。
  • 使用跟踪 Web 视图 UI，包括“**启动收集器**”和“**刷新**”按钮来管理跟踪数据。
  • 设置您的开发环境，包括环境变量和包安装，以启用跟踪。
  • 使用 span 树状图和详细信息视图分析应用程序的执行流程，包括生成式 AI 消息流程和元数据。
10/03/2025
English 한국어 中文(简体)
© . This site is unofficial and not affiliated with Microsoft.