Skip to main content

​
Running Agents

Agents can be executed using different methods depending on your needs - synchronous, asynchronous, or streaming.

​
Synchronous Execution

The simplest way to run an agent is using the do() method, which executes synchronously and returns the result. 
from upsonic import Agent, Task

# Create agent and task
agent = Agent("openai/gpt-4o")
task = Task("What is the capital of France?")

# Execute synchronously
result = agent.do(task)
print(result)  # Output: Paris

​
Asynchronous Execution

For concurrent operations or async applications, use do_async() which returns a coroutine. 
from upsonic import Agent, Task
import asyncio

async def main():
    # Create agent and task
    agent = Agent("openai/gpt-4o")
    task = Task("Explain quantum computing in simple terms")
    
    # Execute asynchronously
    result = await agent.do_async(task)
    print(result)

# Run async function
asyncio.run(main())

​
Streaming Execution

For real-time output, use stream() to get responses as they’re generated. 
from upsonic import Agent, Task

# Create agent and task
agent = Agent("openai/gpt-4o")
task = Task("Write a short poem about coding")
    
# Stream the output
async with agent.stream(task) as result:
    async for text_chunk in result.stream_output():
        print(text_chunk, end='', flush=True)
    print()  # New line after streaming