1 项目地址
https://github.com/joaomdmoura/crewAI
2 功能
通过设置多个智能体，协同解决问题，以处理复杂任务；这种方法的实现方式是将一个任务的输出作为另一个任务的输入。它的优势在于小而有效，原理直观易懂，而且所需的调用代码也相当简单。
很多工作需要多次交互才能完成，不同角色 的 Agent 可设置成不同模型，不同辅助工具，非常好用。
3 代码分析
当前版本 python 代码 800 多行，但几乎是我看过最简单好用的多工具组合策略。
4 模型
除了 openai，还可以支持本地搭建的模型 ollama。
5 安装
$ pip install crewai
6 代码
6.1 示例
import os
from crewai import Agent, Task, Crew, Process
os.environ["OPENAI_API_KEY"] = "YOUR KEY"
from langchain.tools import DuckDuckGoSearchRun
search_tool = DuckDuckGoSearchRun()
# Define your agents with roles and goals
researcher = Agent(
role='Senior Research Analyst',
goal='Uncover cutting-edge developments in AI and data science in',
backstory="""You work at a leading tech think tank.
Your expertise lies in identifying emerging trends.
You have a knack for dissecting complex data and presenting
actionable insights.""",
verbose=True,
allow_delegation=False,
tools=[search_tool]
)
writer = Agent(
role='Tech Content Strategist',
goal='Craft compelling content on tech advancements',
backstory="""You are a renowned Content Strategist, known for
your insightful and engaging articles.
You transform complex concepts into compelling narratives.""",
verbose=True,
allow_delegation=True,
)
# Create tasks for your agents
task1 = Task(
description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
Identify key trends, breakthrough technologies, and potential industry impacts.
Your final answer MUST be a full analysis report""",
agent=researcher
)
task2 = Task(
description="""Using the insights provided, develop an engaging blog
post that highlights the most significant AI advancements.
Your post should be informative yet accessible, catering to a tech-savvy audience.
Make it sound cool, avoid complex words so it doesn't sound like AI.
Your final answer MUST be the full blog post of at least 4 paragraphs.""",
agent=writer
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
verbose=2, # You can set it to 1 or 2 to different logging levels
)
# Get your crew to work!
result = crew.kickoff()
print("######################")
print(result)
6.2 代码分析
在上述代码中，定义了两个智能体：分析师和内容创作者。他们共同协作，完成了一篇关于预测 AI 2014 发展趋势的博文。
值得一提的是，在这里使用 Langchain 来调用 DuckDuckGo 搜索引擎，以便分析师智能体收集相关信息。具体来说，首先，分析师智能体会利用收集到的信息生成分析结果；然后，这些分析结果将被传递给内容创作者智能体，由他来撰写博文。
6.3 注意事项
模型默认调用 OpenAI GPT-4，测试花费比较高，如果介意，请在 Agent 中设置成便宜的版本
