Documentation

Examples

Explore practical examples and common use cases for AI Computer. Each example includes complete code and explanations to help you get started quickly.

Quick Example

Here's a simple example showing both basic execution and streaming:

1import asyncio
2from ai_computer import SandboxClient
3
4async def main():
5    # Initialize the client
6    client = SandboxClient()
7    
8    # Setup the client (gets token and creates sandbox)
9    setup_response = await client.setup()
10    if not setup_response.success:
11        print(f"Setup failed: {setup_response.error}")
12        return
13    
14    try:
15        # Example 1: Simple code execution
16        code = """x = 10
17y = 20
18result = x + y
19print(f"The sum is: {result}")"""
20        
21        print("\nExample 1: Simple execution")
22        print("-" * 50)
23        response = await client.execute_code(code)
24        if response.success:
25            print("Execution result:", response.data)
26        else:
27            print("Execution failed:", response.error)
28
29        # Example 2: Streaming execution
30        code = """import time
31
32for i in range(5):
33    print(f"Processing step {i + 1}")
34    time.sleep(1)  # Simulate work
35    
36result = "Calculation complete!"
37print(result)"""
38        
39        print("\nExample 2: Streaming execution")
40        print("-" * 50)
41        async for event in client.execute_code_stream(code):
42            if event.type == 'stdout':
43                print(f"Output: {event.data}")
44            elif event.type == 'stderr':
45                print(f"Error: {event.data}")
46            elif event.type == 'error':
47                print(f"Execution error: {event.data}")
48                break
49            elif event.type == 'completed':
50                print("Execution completed")
51                break
52    
53    finally:
54        # Clean up
55        await client.cleanup()
56
57if __name__ == "__main__":
58    asyncio.run(main())

Example Categories

Basic Usage

Learn the fundamentals of using AI Computer with simple examples.

  • Client initialization
  • Simple code execution
  • Response handling
  • Cleanup patterns

Streaming Output

Examples of real-time output streaming and event handling.

  • Real-time output handling
  • Event types and processing
  • Long-running processes
  • Error handling in streams

File Operations

Working with files in the sandbox environment.

  • Uploading files
  • Downloading files
  • Working with bytes
  • File operation responses

Error Handling

Learn how to handle errors and edge cases effectively.

  • Setup errors
  • Execution errors
  • Network timeouts
  • Graceful recovery

Common Patterns

Proper Setup and Cleanup

Always initialize the client and clean up resources:

1async def safe_execution():
2    client = SandboxClient()
3    
4    # Setup and check for errors
5    setup_response = await client.setup()
6    if not setup_response.success:
7        print(f"Setup failed: {setup_response.error}")
8        return
9    
10    try:
11        # Your code here
12        response = await client.execute_code("print('Hello')")
13        return response
14    finally:
15        # Always clean up
16        await client.cleanup()

Error Handling

Implement comprehensive error handling:

1async def robust_execution(code: str):
2    client = SandboxClient()
3    
4    try:
5        # Handle setup errors
6        setup_response = await client.setup()
7        if not setup_response.success:
8            return f"Setup failed: {setup_response.error}"
9            
10        # Handle execution errors
11        response = await client.execute_code(code)
12        if not response.success:
13            return f"Execution failed: {response.error}"
14            
15        return response.data['output']
16        
17    except Exception as e:
18        return f"Unexpected error: {str(e)}"
19        
20    finally:
21        await client.cleanup()

Next Steps

Choose an example category above to explore detailed examples and code samples. Each section includes complete, runnable code and explanations of key concepts.

For more information, you can also check: