Creating and Testing a RunPod Serverless Function with Local Server

This tutorial will guide you through creating a basic serverless function using RunPod's Python SDK. We'll build a function that reverses a given string, demonstrating the simplicity and flexibility of RunPod's serverless architecture.

Setting up your Serverless Function

Let's break down the process of creating our string reversal function into steps.

Import RunPod Library

First, import the RunPod library:

import runpod

Define utility function

Create a utility function to reverse the string:

def reverse_string(s):
    return s[::-1]

This function uses Python's slicing feature to efficiently reverse the input string.

Create the Handler Function

The handler function is the core of our serverless application:

def handler(job):
    print(f"string-reverser | Starting job {job['id']}")
    job_input = job['input']
    
    input_string = job_input.get('text', '')
    
    if not input_string:
        return {"error": "No input text provided"}
    
    reversed_string = reverse_string(input_string)
    
    job_output = {
        "original_text": input_string,
        "reversed_text": reversed_string
    }
    
    return job_output

This handler:

1. Logs the start of each job
2. Extracts the input string from the job data
3. Validates the input
4. Reverses the string using our utility function
5. Prepares and returns the output

Start the Serverless Function

Finally, start the RunPod serverless worker:

runpod.serverless.start({"handler": handler})

This line registers our handler function with RunPod's serverless infrastructure.

Complete code example

Here's the full code for our serverless string reversal function:

import runpod

def reverse_string(s):
    return s[::-1]

def handler(job):
    print(f"string-reverser | Starting job {job['id']}")
    job_input = job['input']
    
    input_string = job_input.get('text', '')
    
    if not input_string:
        return {"error": "No input text provided"}
    
    reversed_string = reverse_string(input_string)
    
    job_output = {
        "original_text": input_string,
        "reversed_text": reversed_string
    }
    
    return job_output

runpod.serverless.start({"handler": handler})

Testing Your Serverless Function

RunPod provides multiple ways to test your serverless function locally before deployment. We'll explore two methods: using command-line arguments and running a local test server.

Method 1: Command-line Testing

To quickly test your function using command-line arguments, use this command:

python your_script.py --test_input '{"input": {"text": "Hello, RunPod!"}}'

When you run this test, you'll see output similar to:

--- Starting Serverless Worker |  Version 1.6.2 ---
INFO   | test_input set, using test_input as job input.
DEBUG  | Retrieved local job: {'input': {'text': 'Hello, RunPod!'}, 'id': 'local_test'}
INFO   | local_test | Started.
string-reverser | Starting job local_test
DEBUG  | local_test | Handler output: {'original_text': 'Hello, RunPod!', 'reversed_text': '!doPnuR ,olleH'}
DEBUG  | local_test | run_job return: {'output': {'original_text': 'Hello, RunPod!', 'reversed_text': '!doPnuR ,olleH'}}
INFO   | Job local_test completed successfully.
INFO   | Job result: {'output': {'original_text': 'Hello, RunPod!', 'reversed_text': '!doPnuR ,olleH'}}
INFO   | Local testing complete, exiting.

This output shows the serverless worker starting, processing the job, and returning the result.

Method 2: Local Test Server

For more comprehensive testing, especially when you want to simulate HTTP requests to your serverless function, you can launch a local test server. This server provides an endpoint that you can send requests to, mimicking the behavior of a deployed serverless function.

To start the local test server, use the --rp_serve_api flag:

python your_script.py --rp_serve_api

This command starts a FastAPI server on your local machine, accessible at http://localhost:8000.

Sending Requests to the Local Server

Once your local server is running, you can send HTTP POST requests to test your function. Use tools like curl or Postman, or write scripts to automate your tests.

Example using curl:

curl -X POST http://localhost:8000/run \
     -H "Content-Type: application/json" \
     -d '{"input": {"text": "Hello, RunPod!"}}'

This will send a POST request to your local server with the input data, simulating how your function would be called in a production environment.

Understanding the Server Output

When you send a request to the local server, you'll see output in your terminal similar to:

INFO:     127.0.0.1:52686 - "POST /run HTTP/1.1" 200 OK
DEBUG    | Retrieved local job: {'input': {'text': 'Hello, RunPod!'}, 'id': 'local_test'}
INFO     | local_test | Started.
string-reverser | Starting job local_test
DEBUG    | local_test | Handler output: {'original_text': 'Hello, RunPod!', 'reversed_text': '!doPnuR ,olleH'}
DEBUG    | local_test | run_job return: {'output': {'original_text': 'Hello, RunPod!', 'reversed_text': '!doPnuR ,olleH'}}
INFO     | Job local_test completed successfully.

This output provides detailed information about how your function processes the request, which can be invaluable for debugging and optimizing your serverless function.

Conclusion

You've now created a basic serverless function using RunPod's Python SDK that reverses input strings and learned how to test it using both command-line arguments and a local test server. This example demonstrates how easy it is to deploy and validate simple text processing tasks as serverless functions.

To further explore RunPod's serverless capabilities, consider:

• Adding more complex string manipulations
• Implementing error handling for different input types
• Writing automated test scripts to cover various input scenarios
• Using the local server to integrate your function with other parts of your application during development
• Exploring RunPod's documentation for advanced features like concurrent processing or GPU acceleration

RunPod's serverless library provides a powerful foundation for building scalable, efficient text processing applications without the need to manage infrastructure.