To use the [[OpenAI API]] in Python it is necessary to load the `openai` package and initialize a variable with an [[OpenAI API key]]. The `openai.ChatCompletion()` endpoint can then be use generate a response to a [[prompt (prompt)]] using a specific [[machine learning model|model]]. To simplify the interface we will use a helper function named `get_completion()`that receives the prompt and, optionally, the model, and returns the response. ```python {pre} import openai openai.api_key = "sk-****" def get_completion(prompt, model="gpt-3.5-turbo"): messages = [{"role": "user", "content": prompt}] response = openai.ChatCompletion.create( model=model, messages=messages, temperature=0, # this is the degree of randomness of the model's output ) return response.choices[0].message["content"] ``` A simple code test ```run-python prompt = """ Translate this text into European Portuguese: <Good Morning> """ response = get_completion(prompt) print(response) ``` [[prompt injections]] < [[Hands-on LLMs]]/[[6 OpenAI API]] > [[code header]]