主题
追踪 Semantic Kernel 应用
LangSmith 可以使用 Semantic Kernel 内置的 OpenTelemetry 支持捕获其生成的追踪。本指南展示如何自动捕获 Semantic Kernel 应用的追踪,并将其发送到 LangSmith 进行监控和分析。
安装
使用你偏好的包管理器安装所需依赖包:
bash
pip install langsmith semantic-kernel opentelemetry-instrumentation-openaibash
uv add langsmith semantic-kernel opentelemetry-instrumentation-openai设置
1. 配置环境变量
设置你的 API key 和项目名称:
bash
export LANGSMITH_API_KEY=<your_langsmith_api_key>
export LANGSMITH_PROJECT=<your_project_name>
export OPENAI_API_KEY=<your_openai_api_key>2. 配置 OpenTelemetry 集成
在你的 Semantic Kernel 应用中,配置 LangSmith OpenTelemetry 集成以及 OpenAI instrumentor:
python
from langsmith.integrations.otel import configure
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
# Configure LangSmith tracing
configure(project_name="semantic-kernel-demo")
# Instrument OpenAI calls
OpenAIInstrumentor().instrument()NOTE
你无需设置任何 OpenTelemetry 环境变量,也无需手动配置 exporter——configure() 会自动处理一切。
3. 创建并运行你的 Semantic Kernel 应用
配置完成后,你的 Semantic Kernel 应用会自动将追踪发送到 LangSmith:
python
import asyncio
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from semantic_kernel.prompt_template import InputVariable, PromptTemplateConfig
from langsmith.integrations.otel import configure
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
# Configure LangSmith tracing
configure(project_name="semantic-kernel-assistant")
# Instrument OpenAI calls
OpenAIInstrumentor().instrument()
# Configure Semantic Kernel
kernel = Kernel()
kernel.add_service(OpenAIChatCompletion())
# Create a prompt template
code_analysis_prompt = """
Analyze the following code and provide insights:
Code: {{$code}}
Please provide:
1. A brief summary of what the code does
2. Any potential improvements
3. Code quality assessment
"""
prompt_template_config = PromptTemplateConfig(
template=code_analysis_prompt,
name="code_analyzer",
template_format="semantic-kernel",
input_variables=[
InputVariable(name="code", description="The code to analyze", is_required=True),
],
)
# Add the function to the kernel
code_analyzer = kernel.add_function(
function_name="analyzeCode",
plugin_name="codeAnalysisPlugin",
prompt_template_config=prompt_template_config,
)
async def main():
sample_code = """
def fibonacci(n):
if n <= 1:
return n
return fibonacci(n-1) + fibonacci(n-2)
"""
result = await kernel.invoke(code_analyzer, code=sample_code)
print("Code Analysis:")
print(result)
if __name__ == "__main__":
asyncio.run(main())高级用法
自定义元数据和标签
你可以通过设置 span 属性为追踪添加自定义元数据:
python
from opentelemetry import trace
tracer = trace.get_tracer(__name__)
async def analyze_with_metadata(code: str):
with tracer.start_as_current_span("semantic_kernel_workflow") as span:
span.set_attribute("langsmith.metadata.workflow_type", "code_analysis")
span.set_attribute("langsmith.metadata.user_id", "developer_123")
span.set_attribute("langsmith.span.tags", "semantic-kernel,code-analysis")
result = await kernel.invoke(code_analyzer, code=code)
return result与其他 instrumentor 组合使用
你可以将 Semantic Kernel 追踪与其他 OpenTelemetry instrumentor 组合使用:
python
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor
# Initialize multiple instrumentors
OpenAIInstrumentor().instrument()
HTTPXClientInstrumentor().instrument()