GPT-4.1 Python quickstart using the OpenAI API



Table Of Contents

Getting your OpenAI API



Creating your OpenAI API key









OpenAI pricing

Source

W&B Weave

Getting started with GPT-4.1



Step 1: The OpenAI GPT-4.1 API key

%env OPENAI_API_KEY=KEY



Step 2: Installing OpenAI and W&B Weave

This is a good time to sign up for Weights & Biases, to save you having to interrupt your workflow in a couple minutes, when you're further along.

!pip install openai weave



Step 3: Import libraries and pass the OpenAI API key

import os
import weave
from openai import OpenAI

# Initialize Weave
weave.init('gpt-4-setup')

# Initialize OpenAI client
client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))

Step 4: Setting your GPT-4.1 prompt

Define the assistant's role. This sets up the model's identity by specifying how it should behave. For example, the input to "Who should I be, as I answer your prompt?" could be something like "a machine learning engineer learning about LLMs," guiding the model to respond accordingly.
Set the user’s task. This defines what you want the model to do. For instance, the input to "What do you want me to do?" could be a specific request like "Explain how to use Weights & Biases in my code to work more effectively with my team." which informs the model of the action it needs to take.

gpt_assistant_prompt = "You are a " + input ("Who should I be, as I answer your prompt?") 
gpt_user_prompt = input ("What do you want me to do?") 



Step 5: Generating content with GPT-4.1

@weave.op()
def generate_content(gpt_assistant_prompt: str, gpt_user_prompt: str) -> dict:
    gpt_prompt = f"{gpt_assistant_prompt} {gpt_user_prompt}"
    messages = [
        {"role": "assistant", "content": gpt_assistant_prompt},
        {"role": "user", "content": gpt_user_prompt}
    ]
    response = client.chat.completions.create(
        model="gpt-4.1",  # Ensure correct model name is used
        messages=messages,
        temperature=0.2,
        max_tokens=1000,
        frequency_penalty=0.0
    )
    response_text = response.choices[0].message.content
    tokens_used = response.usage.total_tokens
    
    return {"response": response_text, "tokens_used": tokens_used}

# Call the function
result = generate_content(gpt_assistant_prompt, gpt_user_prompt)
print(result)

temperature: A value between 0 and 1.0 that controls the randomness or creativity of the model's output. Lower values like 0.2 make the output more focused and deterministic, leading to responses that are less creative but more precise.
max_tokens: Limits the maximum number of tokens (words and parts of words) in the response. The model will generate up to 1000 tokens in its reply, balancing between verbosity and performance.
frequency_penalty: A value between -2.0 and 2.0 that adjusts the likelihood of the model repeating tokens. A value of 0.0 means there is no penalty, allowing repetition to occur naturally. Higher values would reduce repetition in the generated text.



model - the model you want to use.
message - the message being sent (mostly the prompt).
temperature - a number between 0 and 1 with higher numbers being more random. Higher numbers may be more creative, but they also make the results less predictable.
frequency_penalty - a number between -2 and 2, where higher numbers penalize new tokens based on their frequency to that point in the response. The higher the number, the lower the probability of repetition.

Viewing GPT-4.1 inputs and outputs in W&B Weave









Conclusion

Related Reading