1

When I try to call API in my code, my code is stuck.

I think I did not hit the limits.
Could anyone help me with it?

Thank you so much!

here is my code:

def generate_answer(question, triples,flag):
if flag == ‘front’:
prompt = f"““Question: {triples}\n
{question}\n
answer?\n
“””
else:
prompt = f”"“Question: {question}\n
answer?\n
{triples}\n
“””

response = openai.ChatCompletion.create(
        model='gpt-3.5-turbo',
        messages=[{"role": "user", "content": prompt}],
        max_tokens=100,
        temperature=0
    )
response = response.choices[0].message['content'].strip()

return response
2

The code is not formatted well in the forum

The response generator is an object; you should output the selected dictionary value to a new variable.

import os, openai
openai.api_key = os.getenv("OPENAI_API_KEY")

def generate_answer(question, triples="", flag=""):
    if flag == "front":
        user = f"{triples}\n{question}"
    else:
        user = f"{question}"

    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        max_tokens=100,
        temperature=0,
        messages=[
            {"role": "system", "content": "You are a helpful AI assistant"},
            {"role": "user", "content": user}
            ]
    )
    content = response["choices"][0]["message"]["content"]
    return str(content).strip()

print(generate_answer("How big is a banana?"))

There is also no reason with the chat models to label your question as such or ask for an answer. You also should not end with whitespace, which I fixed above.