​
Understanding Process Types

Process types in Praison Labs define how tasks are executed and how agents collaborate. Each process type offers different patterns for task execution and agent coordination.

​
Process Types Overview

Sequential Process

Linear task execution in a predefined order

Hierarchical Process

Manager-coordinated task execution with dynamic assignment

Workflow Process

Complex task flows with conditional execution and state management

​
Sequential Process

The simplest form of task execution where tasks are performed one after another.

​
Characteristics

  • Linear execution flow
  • Predictable order
  • Simple dependency management
  • Direct task progression

​
Usage 

agents = Praison LabsAgents(
    agents=[agent1, agent2],
    tasks=[task1, task2, task3],
    process="sequential"
)

​
Hierarchical Process

Uses a manager agent to coordinate task execution and agent assignments.

​
Characteristics

  • Manager-driven coordination
  • Dynamic task assignment
  • Flexible execution order
  • Intelligent resource allocation

​
Configuration 

agents = Praison LabsAgents(
    agents=[manager_agent, worker_agent1, worker_agent2],
    tasks=[task1, task2],
    process="hierarchical",
    manager_llm="gpt-4o"
)

​
Workflow Process

Advanced process type supporting complex task relationships and conditional execution.

​
Features

  • Task dependencies
  • Conditional branching
  • Loop handling
  • Context sharing
  • State management

​
Implementation 

task_workflow = {
    "start_task": {
        "next": ["decision_task"],
        "type": "task"
    },
    "decision_task": {
        "type": "decision",
        "conditions": {
            "success": ["process_task"],
            "failure": ["error_task"]
        }
    }
}

​
Getting Started

1

Install Praison Labs

Install the core package:

Terminal 
pip install praisonaiagents
2

Configure Environment

Terminal 
export OPENAI_API_KEY=your_openai_key

Generate your OpenAI API key from OpenAI Use other LLM providers like Ollama, Anthropic, Groq, Google, etc. Please refer to the Models for more information.

3

Create Agent

Create app.py:

from praisonaiagents import Agent, Task, Praison LabsAgents

# Create an agent
researcher = Agent(
    name="Researcher",
    role="Senior Research Analyst",
    goal="Uncover cutting-edge developments in AI",
    backstory="You are an expert at a technology research group",
    verbose=True,
    llm="gpt-4o"
)

# Define a task
task = Task(
    name="research_task",
    description="Analyze 2024's AI advancements",
    expected_output="A detailed report",
    agent=researcher
)

# Run the agents
agents = Praison LabsAgents(
    agents=[researcher],
    tasks=[task],
    verbose=False,
    process="sequential"
)

result = agents.start()

​
Advanced Features

State Management

Error Handling

Monitoring

Integration

​
Async Processing

All process types support asynchronous execution through async generators, enabling efficient parallel processing and non-blocking operations.

​
Core Async Methods

asequential

Async version of sequential process for non-blocking linear execution

aworkflow

Async workflow process for complex parallel task execution

ahierarchical

Async hierarchical process for distributed task management

​
Process-Specific Features

  • Tasks execute in order but don’t block
  • Maintains sequence while allowing async operations
  • Perfect for I/O-heavy tasks
async def main():
    agents = Praison LabsAgents(
        process="sequential",
        async_mode=True
    )
    await agents.astart()

​
Key Benefits

Performance

  • Efficient resource utilization
  • Reduced waiting time
  • Better throughput

Flexibility

  • Mix sync and async tasks
  • Adaptable execution patterns
  • Easy scaling