​
MLflow 概述

MLflow 是一个开源平台，旨在帮助机器学习从业者和团队处理机器学习过程的复杂性。

它提供了一个跟踪功能，通过捕获应用程序服务执行的详细信息，增强了生成式 AI 应用程序中的 LLM 可观测性。跟踪提供了一种记录请求中每个中间步骤相关的输入、输出和元数据的方式，使您能够轻松查明错误和意外行为的来源。

​
功能

  • 跟踪仪表板：使用详细的仪表板监控您的 crewAI Agent 活动，包括 span 的输入、输出和元数据。
  • 自动化跟踪：与 crewAI 的完全自动化集成，可以通过运行 mlflow.crewai.autolog() 启用。
  • 少量工作的手动跟踪检测：通过 MLflow 的高级流利 API（如装饰器、函数包装器和上下文管理器）自定义跟踪检测。
  • OpenTelemetry 兼容性：MLflow 跟踪支持将跟踪导出到 OpenTelemetry Collector，然后可用于将跟踪导出到各种后端，如 Jaeger、Zipkin 和 AWS X-Ray。
  • 打包和部署 Agent：将您的 crewAI Agent 打包并部署到推理服务器，支持多种部署目标。
  • 安全托管 LLM：通过 MLflow 网关在一个统一的端点中托管来自不同提供商的多个 LLM。
  • 评估：使用便捷的 API mlflow.evaluate()，通过广泛的指标评估您的 crewAI Agent。

​
设置说明

1

安装 MLflow 包

# The crewAI integration is available in mlflow>=2.19.0
pip install mlflow
2

启动 MLflow 跟踪服务器

# This process is optional, but it is recommended to use MLflow tracking server for better visualization and broader features.
mlflow server
3

在您的应用程序中初始化 MLflow

将以下两行添加到您的应用程序代码中

import mlflow

mlflow.crewai.autolog()

# Optional: Set a tracking URI and an experiment name if you have a tracking server
mlflow.set_tracking_uri("https://:5000")
mlflow.set_experiment("CrewAI")

跟踪 CrewAI Agent 的示例用法

from crewai import Agent, Crew, Task
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai_tools import SerperDevTool, WebsiteSearchTool

from textwrap import dedent

content = "Users name is John. He is 30 years old and lives in San Francisco."
string_source = StringKnowledgeSource(
    content=content, metadata={"preference": "personal"}
)

search_tool = WebsiteSearchTool()


class TripAgents:
    def city_selection_agent(self):
        return Agent(
            role="City Selection Expert",
            goal="Select the best city based on weather, season, and prices",
            backstory="An expert in analyzing travel data to pick ideal destinations",
            tools=[
                search_tool,
            ],
            verbose=True,
        )

    def local_expert(self):
        return Agent(
            role="Local Expert at this city",
            goal="Provide the BEST insights about the selected city",
            backstory="""A knowledgeable local guide with extensive information
        about the city, it's attractions and customs""",
            tools=[search_tool],
            verbose=True,
        )


class TripTasks:
    def identify_task(self, agent, origin, cities, interests, range):
        return Task(
            description=dedent(
                f"""
                Analyze and select the best city for the trip based
                on specific criteria such as weather patterns, seasonal
                events, and travel costs. This task involves comparing
                multiple cities, considering factors like current weather
                conditions, upcoming cultural or seasonal events, and
                overall travel expenses.
                Your final answer must be a detailed
                report on the chosen city, and everything you found out
                about it, including the actual flight costs, weather
                forecast and attractions.

                Traveling from: {origin}
                City Options: {cities}
                Trip Date: {range}
                Traveler Interests: {interests}
            """
            ),
            agent=agent,
            expected_output="Detailed report on the chosen city including flight costs, weather forecast, and attractions",
        )

    def gather_task(self, agent, origin, interests, range):
        return Task(
            description=dedent(
                f"""
                As a local expert on this city you must compile an
                in-depth guide for someone traveling there and wanting
                to have THE BEST trip ever!
                Gather information about key attractions, local customs,
                special events, and daily activity recommendations.
                Find the best spots to go to, the kind of place only a
                local would know.
                This guide should provide a thorough overview of what
                the city has to offer, including hidden gems, cultural
                hotspots, must-visit landmarks, weather forecasts, and
                high level costs.
                The final answer must be a comprehensive city guide,
                rich in cultural insights and practical tips,
                tailored to enhance the travel experience.

                Trip Date: {range}
                Traveling from: {origin}
                Traveler Interests: {interests}
            """
            ),
            agent=agent,
            expected_output="Comprehensive city guide including hidden gems, cultural hotspots, and practical travel tips",
        )


class TripCrew:
    def __init__(self, origin, cities, date_range, interests):
        self.cities = cities
        self.origin = origin
        self.interests = interests
        self.date_range = date_range

    def run(self):
        agents = TripAgents()
        tasks = TripTasks()

        city_selector_agent = agents.city_selection_agent()
        local_expert_agent = agents.local_expert()

        identify_task = tasks.identify_task(
            city_selector_agent,
            self.origin,
            self.cities,
            self.interests,
            self.date_range,
        )
        gather_task = tasks.gather_task(
            local_expert_agent, self.origin, self.interests, self.date_range
        )

        crew = Crew(
            agents=[city_selector_agent, local_expert_agent],
            tasks=[identify_task, gather_task],
            verbose=True,
            memory=True,
            knowledge={
                "sources": [string_source],
                "metadata": {"preference": "personal"},
            },
        )

        result = crew.kickoff()
        return result


trip_crew = TripCrew("California", "Tokyo", "Dec 12 - Dec 20", "sports")
result = trip_crew.run()

print(result)

有关更多配置和用例，请参阅 MLflow 跟踪文档。

4

可视化 Agent 的活动

现在您的 crewAI Agent 的跟踪信息已被 MLflow 捕获。让我们访问 MLflow 跟踪服务器来查看跟踪信息并了解您的 Agent 的详情。

在您的浏览器中打开 127.0.0.1:5000 以访问 MLflow 跟踪服务器。

MLflow 跟踪仪表板