Automate Event Planning - The crew must end with at most one asynchronous task

Short Course Q&A Multi AI Agent Systems with crewAI
1

Hi! I’m getting this error when I try to create the Crew as it is in the notebook.

ValidationError: 1 validation error for Crew
  The crew must end with at most one asynchronous task. [type=async_task_count, input_value={'agents': [Agent(role=Ve...own.)], 'verbose': True}, input_type=dict]

I’m using the crewAI version 0.51.1. I know it is a different version compared to the one in the sandbox lab. But I’d like to understand what I need to change to make it work.

My agents:

venue_coordinator = Agent(
    role="Venue Coordinator",
    goal="Identify and book an appropriate venue "
    "based on event requirements",
    tools=[search_tool, scrape_tool],
    verbose=True,
    backstory=(
        "With a keen sense of space and "
        "understanding of event logistics, "
        "you excel at finding and securing "
        "the perfect venue that fits the event's theme, "
        "size, and budget constraints."
    )
)

 # Agent 2: Logistics Manager
logistics_manager = Agent(
    role='Logistics Manager',
    goal=(
        "Manage all logistics for the event "
        "including catering and equipmen"
    ),
    tools=[search_tool, scrape_tool],
    verbose=True,
    backstory=(
        "Organized and detail-oriented, "
        "you ensure that every logistical aspect of the event "
        "from catering to equipment setup "
        "is flawlessly executed to create a seamless experience."
    )
)

# Agent 3: Marketing and Communications Agent
marketing_communications_agent = Agent(
    role="Marketing and Communications Agent",
    goal="Effectively market the event and "
         "communicate with participants",
    tools=[search_tool, scrape_tool],
    verbose=True,
    backstory=(
        "Creative and communicative, "
        "you craft compelling messages and "
        "engage with potential attendees "
        "to maximize event exposure and participation."
    )
)

Taks

venue_task = Task(
    description="Find a venue in {event_city} "
                "that meets criteria for {event_topic}.",
    expected_output="All the details of a specifically chosen"
                    "venue you found to accommodate the event.",
    human_input=True,
    output_json=VenueDetails,
    output_file="venue_details.json",  
      # Outputs the venue details as a JSON file
    agent=venue_coordinator
)

logistics_task = Task(
    description="Coordinate catering and "
                 "equipment for an event "
                 "with {expected_participants} participants "
                 "on {tentative_date}.",
    expected_output="Confirmation of all logistics arrangements "
                    "including catering and equipment setup.",
    human_input=True,
    async_execution=True,
    agent=logistics_manager
)

marketing_task = Task(
    description="Promote the {event_topic} "
                "aiming to engage at least"
                "{expected_participants} potential attendees.",
    expected_output="Report on marketing activities "
                    "and attendee engagement formatted as markdown.",
    async_execution=True,
    output_file="marketing_report.md",  # Outputs the report as a text file
    agent=marketing_communications_agent
)

Crew

# Define the crew with agents and tasks
event_management_crew = Crew(
    agents=[venue_coordinator, 
            logistics_manager, 
            marketing_communications_agent],
    
    tasks=[venue_task, 
           logistics_task, 
           marketing_task],
    
    verbose=True
)
2 Likes
2

I had the same issue as well. I turned off the asynchronous flag for logistics manager.

2 Likes
3

I did as well. I’m curious what the correct approach would be here though.

4

After setting only one async task, it worked anyway. For examle, just turned off the flag of maketing task’s async_execution.

5

I agree with @diem389, it only works with a single asynchronous task as mentioned in the error message.

As per my understanding running multiple tasks asynchronously within a single Crew could create significant complexity in coordinating task completions, handling dependencies between them, and meaningfully aggregating results.

6

There is potentially great benefit to being able to execute multiple tasks asynchronously.
Let’s say we have tasks = [task1_sync, task2_async, task3_async, task4_sync]

  1. task1_sync starts out the research
  2. task2_async and task3_async are allowed to execute in parallel (e.g. one collects data from an SQL database and another scrapes the web). (We can save time here!)
  3. task4_sync can aggregate and prepare the report

Ideally, specifying the dependency such that there is only ONE “last task” should theoretically pass the validation e.g.

marketing_task = Task(
    description="Promote the {event_topic} aiming to engage at least{expected_participants} potential attendees.",
    expected_output="Report on marketing activities and attendee engagement formatted as markdown.",
    async_execution=True,
    output_file="marketing_report.md",  # Outputs the report as a text file
    agent=marketing_communications_agent,
    context=[logistics_task, venue_task],
)

Unfortunately, the validation implementation is quite strict.

Hence, to overcome the restriction, we can make the last task in tasks synchronous.
To save LLM costs, we would need to create a custom dummy LLM (seems to have a lot of angles to test/cover: Custom LLM Implementation - CrewAI ) and dummy task…

I am using

crewai==0.119.0
crewai-tools==0.44.0