No response

[anmolgupta321]

!pip install --q crewai
!pip install --q -U duckduckgo-search
!pip install --q langchain_google_genai
import os
from langchain_google_genai import ChatGoogleGenerativeAI
from crewai import Agent, Task, Crew, Process
# Set gemini pro as llm
llm = ChatGoogleGenerativeAI(model="gemini-pro",
                             verbose = True,
                             temperature = 0.6,
                             google_api_key="")
                 
llm
# Make sure to Install duckduckgo-search for this example:
# !pip install -U duckduckgo-search

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',
  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,
  llm = llm,  #using google gemini pro API
  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,
  llm = llm
  )


# 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""",
  expected_output='A bullet list summary of the top 5 most important AI news',
  async_execution=True,
  agent=researcher,
  tools=[],
)

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.""",
  expected_output='A bullet list summary of the top 5 most important AI news',
  async_execution=True,
  agent=researcher,
  tools=[]
)

# 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
)

crew

# Get your crew to work!
result = crew.kickoff()

[DEBUG]: == Working Agent: Senior Research Analyst
 [INFO]: == Starting Task: 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
 [DEBUG]: == [Senior Research Analyst] Task output: 


 [DEBUG]: == Working Agent: Senior Research Analyst
 [INFO]: == Starting Task: 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.
 [DEBUG]: == [Senior Research Analyst] Task output: 




> Entering new CrewAgentExecutor chain...


> Entering new CrewAgentExecutor chain...

print(result)

[anmolgupta321]

not even working with chat gpt API.

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

[github-actions[bot]]

This issue was closed because it has been stalled for 5 days with no activity.