app.py

import os
import gradio as gr
from textwrap import dedent
from dotenv import load_dotenv

from crewai.tools.gemini_tools import GeminiSearchTools

from crewai import Agent, Task, Crew, Process

os.environ["OPENAI_API_KEY"] = "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"

# Crew Bot: https://chat.openai.com/g/g-qqTuUWsBY-crewai-assistant


# Base Example with Gemini Search

def crewai_process(research_topic):
    # Define your agents with roles and goals
    researcher = Agent(
        role='Senior Research Analyst',
        goal=f'Uncover cutting-edge developments in AI and data science in {research_topic}',
        backstory="""You are a Senior Research Analyst at a leading tech think tank.
        Your expertise lies in identifying emerging trends and technologies in AI and
        data science. You have a knack for dissecting complex data and presenting
        actionable insights.""",
        verbose=True,
        allow_delegation=False,
        tools=[
        GeminiSearchTools.gemini_search
      ]
    )
    writer = Agent(
        role='Tech Content Strategist',
        goal='Craft compelling content on tech advancements',
        backstory="""You are a renowned Tech Content Strategist, known for your insightful
        and engaging articles on technology and innovation. With a deep understanding of
        the tech industry, you transform complex concepts into compelling narratives.""",
        verbose=True,
        allow_delegation=True
     
        # Add tools and other optional parameters as needed
    )

    # Create tasks for your agents
    task1 = Task(
        description=f"""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
        Identify key trends, breakthrough technologies, and potential industry impacts in {research_topic}.
        Compile your findings in a detailed report. Your final answer MUST be a full analysis report""",
        agent=researcher
    )

    task2 = Task(
        description="""Using the insights from the researcher's report, 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.
        Aim for a narrative that captures the essence of these breakthroughs and their
        implications for the future. Your final answer MUST be the full blog post of at least 3 paragraphs.""",
        agent=writer
    )

    # Instantiate your crew with a sequential process
    crew = Crew(
        agents=[researcher, writer],
        tasks=[task1, task2],
        verbose=2,
        process=Process.sequential
    )

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

# Create a Gradio interface
iface = gr.Interface(
    fn=crewai_process, 
    inputs=gr.Textbox(lines=2, placeholder="Enter Research Topic Here..."), 
    outputs="text",
    title="CrewAI Research and Writing Assistant",
    description="Input a research topic to get a comprehensive analysis and a blog post draft."
)

# Launch the interface
iface.launch()

    

# Stock Evaluation
    
'''
    
from stock_analysis_agents import StockAnalysisAgents
from stock_analysis_tasks import StockAnalysisTasks

#from dotenv import load_dotenv

#load_dotenv()

def run_financial_analysis(company_name):
    # Assuming StockAnalysisAgents and StockAnalysisTasks are defined elsewhere
    agents = StockAnalysisAgents()
    tasks = StockAnalysisTasks()

    research_analyst_agent = agents.research_analyst()
    financial_analyst_agent = agents.financial_analyst()
    investment_advisor_agent = agents.investment_advisor()

    research_task = tasks.research(research_analyst_agent, company_name)
    financial_task = tasks.financial_analysis(financial_analyst_agent)
    filings_task = tasks.filings_analysis(financial_analyst_agent)
    recommend_task = tasks.recommend(investment_advisor_agent)

    crew = Crew(
        agents=[
            research_analyst_agent,
            financial_analyst_agent,
            investment_advisor_agent
        ],
        tasks=[
            research_task,
            financial_task,
            filings_task,
            recommend_task
        ],
        verbose=True
    )

    result = crew.kickoff()
    return result

iface = gr.Interface(
    fn=run_financial_analysis,
    inputs=gr.Textbox(lines=2, placeholder="Enter Company Name Here"),
    outputs="text",
    title="CrewAI Financial Analysis",
    description="Enter a company name to get financial analysis."
)

#if __name__ == "__main__":
iface.launch()

'''


# Therapy Group

'''
def run_therapy_session(group_size, topic):
    participant_names = ['Alice', 'Bob', 'Charlie', 'Diana', 'Ethan', 'Fiona', 'George', 'Hannah', 'Ivan']
    
    if group_size > len(participant_names) + 1:  # +1 for the therapist
        return "Group size exceeds the number of available participant names."

    # Create the therapist agent
    dr_smith = Agent(
        role='Therapist', 
        goal='Facilitate a supportive group discussion', 
        backstory='An experienced therapist specializing in group dynamics.', 
        verbose=True,
        allow_delegation=False
    )
    # Create participant agents

    participants = [Agent(
        role=f'Group Therapy Participant - {name}', 
        goal='Participate in group therapy', 
        backstory=f'{name} is interested in sharing and learning from the group.', 
        verbose=True,
        allow_delegation=False)
        for name in participant_names[:group_size - 1]]
    participants.append(dr_smith)

    # Define tasks for each participant
    tasks = [Task(description=f'{participant.role.split(" - ")[-1]}, please share your thoughts on the topic: "{topic}".', agent=participant)
         for participant in participants]

    # Instantiate the crew with a sequential process
    therapy_crew = Crew(
        agents=participants,
        tasks=tasks,
        process=Process.sequential,
        verbose=True
    )

    # Start the group therapy session
    result = therapy_crew.kickoff()

    # Simulating a conversation (placeholder, adjust based on CrewAI capabilities)
    conversation = "\n".join([f"{participant.role.split(' - ')[-1]}: [Participant's thoughts on '{topic}']" for participant in participants])
    
    return result

# Gradio interface
iface = gr.Interface(
    fn=run_therapy_session,
    inputs=[
        gr.Slider(minimum=2, maximum=10, label="Group Size", value=4),
        gr.Textbox(lines=2, placeholder="Enter a topic or question for discussion", label="Discussion Topic")
    ],
    outputs="text"
)

# Launch the interface
iface.launch()

'''




# Choosing topics

'''
def run_crew(topic):
    # Define your agents
    researcher = Agent(
        role='Senior Research Analyst',
        goal='Uncover cutting-edge developments',
        backstory="""You are a Senior Research Analyst at a leading tech think tank...""",
        verbose=True,
        allow_delegation=False
    )

    writer = Agent(
        role='Tech Content Strategist',
        goal='Craft compelling content',
        backstory="""You are a renowned Tech Content Strategist...""",
        verbose=True,
        allow_delegation=False
    )

    # Assign tasks based on the selected topic
    if topic == "write short story":
        task_description = "Write a captivating short story about a journey through a futuristic city."
    elif topic == "write an article":
        task_description = "Compose an insightful article on the latest trends in technology."
    elif topic == "analyze stock":
        task_description = "Perform a detailed analysis of recent trends in the stock market."
    elif topic == "create a vacation":
        task_description = "Plan a perfect vacation itinerary for a family trip to Europe."

    task1 = Task(
        description=task_description,
        agent=researcher
    )

    task2 = Task(
        description=f"Use the findings from the researcher's task to develop a comprehensive report on '{topic}'.",
        agent=writer
    )

    # Instantiate your crew with a sequential process
    crew = Crew(
        agents=[researcher, writer],
        tasks=[task1, task2],
        verbose=2,
        process=Process.sequential
    )

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

# Gradio Interface with Dropdown for Topic Selection
iface = gr.Interface(
    fn=run_crew,
    inputs=gr.Dropdown(choices=["write short story", "write an article", "analyze stock", "create a vacation"], label="Select Topic"),
    outputs="text",
    title="AI Research and Writing Crew",
    description="Select a topic and click the button to run the crew of AI agents."
)

iface.launch()

'''