Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.praison.ai/llms.txt

Use this file to discover all available pages before exploring further.

A workflow that distributes tasks across multiple LLM calls simultaneously, aggregating results to handle complex or large-scale operations efficiently.

​
Quick Start

1

Install Package

First, install the PraisonAI Agents package:
pip install praisonaiagents
2

Set API Key

Set your OpenAI API key as an environment variable in your terminal:
export OPENAI_API_KEY=your_api_key_here
3

Create a file

Create a new file app.py with the basic setup:
from praisonaiagents import Agent, AgentFlow
from praisonaiagents import parallel

# Create parallel research agents
market_researcher = Agent(
    name="MarketResearcher",
    role="Market Research Analyst",
    goal="Research market trends and opportunities",
    instructions="Analyze market trends. Provide concise market insights."
)

competitor_researcher = Agent(
    name="CompetitorResearcher", 
    role="Competitive Intelligence Analyst",
    goal="Research competitor strategies",
    instructions="Analyze competitors. Provide key competitive insights."
)

customer_researcher = Agent(
    name="CustomerResearcher",
    role="Customer Research Analyst", 
    goal="Research customer needs and behaviors",
    instructions="Analyze customer segments. Provide customer insights."
)

# Create aggregator agent
aggregator = Agent(
    name="Aggregator",
    role="Research Synthesizer",
    goal="Synthesize research findings",
    instructions="Combine all research findings into a comprehensive summary."
)

# Create workflow with parallel execution
workflow = AgentFlow(
    steps=[
        parallel([market_researcher, competitor_researcher, customer_researcher]),
        aggregator
    ]
)

# Run workflow - all researchers work in parallel, then aggregator summarizes
result = workflow.start("Research the AI industry")
print(result["output"])
4

Start Workflow

Type this in your terminal to run your workflow:
python app.py
Requirements
  • Python 3.10 or higher
  • OpenAI API key. Generate OpenAI API key here. Use Other models using this guide.
  • Basic understanding of Python and async programming

​
Understanding Parallelisation

What is Parallelisation?

Parallelisation enables:
  • Concurrent execution of multiple tasks
  • Improved performance through parallel processing
  • Efficient handling of independent operations
  • Aggregation of parallel task results

​
Features

Parallel Execution

Run multiple tasks simultaneously for improved performance.

Async Support

Built-in support for asynchronous execution.

Result Aggregation

Combine results from parallel tasks efficiently.

Process Control

Monitor and manage parallel task execution.

​
Configuration Options

from praisonaiagents import AgentFlow, WorkflowContext, StepResult
from praisonaiagents import parallel

# Define parallel workers
def worker1(ctx: WorkflowContext) -> StepResult:
    return StepResult(output="Result from worker 1")

def worker2(ctx: WorkflowContext) -> StepResult:
    return StepResult(output="Result from worker 2")

def worker3(ctx: WorkflowContext) -> StepResult:
    return StepResult(output="Result from worker 3")

# Aggregator combines parallel results
def aggregate(ctx: WorkflowContext) -> StepResult:
    outputs = ctx.variables.get("parallel_outputs", [])
    return StepResult(output=f"Combined: {len(outputs)} results")

# Create workflow with parallel execution
workflow = AgentFlow(
    steps=[
        parallel([worker1, worker2, worker3]),
        aggregate
    ]
)

# Async workflow execution
import asyncio

async def run_workflow():
    result = await workflow.astart("Start parallel work")
    return result

result = asyncio.run(run_workflow())

​
Troubleshooting

Execution Issues

If parallel execution fails:
  • Check async configuration
  • Verify task independence
  • Monitor resource usage

Result Aggregation

If aggregation is incorrect:
  • Review task outputs
  • Check context connections
  • Verify aggregator logic

​
Next Steps

AutoAgents

Learn about automatically created and managed AI agents

Mini Agents

Explore lightweight, focused AI agents
For optimal results, ensure your parallel tasks are truly independent and your system has sufficient resources to handle concurrent execution.