推荐github热榜项目_crewAI

发布时间:2024年01月14日

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

文章来源:https://blog.csdn.net/xieyan0811/article/details/135587404
本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。