[crewai] Hello World! 실행해 보기

재미있는 AI를 발견해서 Getting Started 를 따라해 보았습니다.

 

crewAI - Platform for Multi AI Agents Systems

crewAI - Platform for Multi AI Agents Systems

 

윈도우10에서 wsl2 로 Ubuntu 를 설치 한후에, 테스트를 했습니다.

Ubuntu 22.04

python 3.12.4

 

따라한 예제

Assembling and Activating Your CrewAI Team - crewAI

Assembling and Activating Your CrewAI Team - crewAI

예제를 그대로 따라하면 일단 

BrowserbaseTool, ExaSearchTool 가 없다고 오류가 납니다. 

수정중인건지 아님 못찾는건지 확인은 안되었으니,

어쨌든 이름을 모두 바꿔 줍니다.

 

BrowserbaseTool -> BrowserbaseLoadTool

ExaSearchTool  -> EXASearchTool

 

그리고, 예제에서는 openai, serperapi 만 가입해서 키를 쓰면 된다고 하는거 같은데, 아닙니다 -_-;

browserbase 라는 사이트와 exa 라는 사이트도 가입해서 api key 를 받아야 하고, 키를 모두 선언해야

정상적으로 동작 합니다.

 

API platform | OpenAI

 

Serper - The World's Fastest and Cheapest Google Search API

Serper - The World's Fastest and Cheapest Google Search API

Browserbase: Headless browsers for AI agents & applications

Browserbase: Headless browsers for AI agents & applications

Exa | Web API for AI

Exa

 

모두가입해서, key를 획득후, 샘플소스의 최상단에 써주면 됩니다.

import os
os.environ["SERPER_API_KEY"] = "key"  # serper.dev API key
os.environ["OPENAI_API_KEY"] = "key"
os.environ["BROWSERBASE_API_KEY"]="key"
os.environ["BROWSERBASE_PROJECT_ID"] ="id"
os.environ["EXA_API_KEY"] = "key"

from crewai import Agent
from crewai_tools import SerperDevTool, BrowserbaseLoadTool, EXASearchTool
search_tool = SerperDevTool()
browser_tool = BrowserbaseLoadTool()
exa_search_tool = EXASearchTool()

# Creating a senior researcher agent with memory and verbose mode
researcher = Agent(
  role='Senior Researcher',
  goal='Uncover groundbreaking technologies in {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "Driven by curiosity, you're at the forefront of"
    "innovation, eager to explore and share knowledge that could change"
    "the world."
  ),
  tools=[search_tool, browser_tool],
)

# Creating a writer agent with custom tools and delegation capability
writer = Agent(
  role='Writer',
  goal='Narrate compelling tech stories about {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "With a flair for simplifying complex topics, you craft"
    "engaging narratives that captivate and educate, bringing new"
    "discoveries to light in an accessible manner."
  ),
  tools=[exa_search_tool],
  allow_delegation=False
)

# Setting a specific manager agent
manager = Agent(
  role='Manager',
  goal='Ensure the smooth operation and coordination of the team',
  verbose=True,
  backstory=(
    "As a seasoned project manager, you excel in organizing"
    "tasks, managing timelines, and ensuring the team stays on track."
  )
)

from crewai import Task

# Research task
research_task = Task(
  description=(
    "Identify the next big trend in {topic}."
    "Focus on identifying pros and cons and the overall narrative."
    "Your final report should clearly articulate the key points,"
    "its market opportunities, and potential risks."
  ),
  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
  tools=[search_tool],
  agent=researcher,
  callback="research_callback",  # Example of task callback
  human_input=True
)

# Writing task with language model configuration
write_task = Task(
  description=(
    "Compose an insightful article on {topic}."
    "Focus on the latest trends and how it's impacting the industry."
    "This article should be easy to understand, engaging, and positive."
    "Write in Korean"
  ),
  expected_output='A 4 paragraph article on {topic} advancements formatted as markdown.',
  tools=[exa_search_tool],
  agent=writer,
  output_file='new-blog-post.md',  # Example of output customization
)

from crewai import Crew, Process

# Forming the tech-focused crew with some enhanced configurations
crew = Crew(
  agents=[researcher, writer],
  tasks=[research_task, write_task],
  process=Process.sequential,  # Optional: Sequential task execution is default
  memory=True,
  cache=True,
  max_rpm=100,
  manager_agent=manager
)

if __name__ == "__main__":
  # Starting the task execution process with enhanced feedback
  result = crew.kickoff(inputs={'topic': 'AI in healthcare'})
  print(result)

 

그리고 실행하면  자기-_-들끼리 이야기를 하다가, 결과가 나옵니다.

Finished chain 이후를 보면 됩니다.