How long do I have to wait before sending a new api request? | OpenAI | Page 1

#

I seem to be getting rate limited in my python code, code attached

#

import openai

transcript = transcription

# Set up the OpenAI API key and model name
openai.api_key = "-"

# Split the transcript into chunks of 1000 words each
chunks = [transcript[i:i+1000] for i in range(0, len(transcript), 1000)]

# Initialize the accumulated response variable
response = ""

# Loop over each chunk and send it to the GPT-3 model
for chunk in chunks:
    # Send the messages to the GPT-3 model and get the response
    while True:
        try:
          chatproc = openai.ChatCompletion.create(model="gpt-3.5-turbo",messages=[{"role": "system", "content": "format the following as flashcards in the format front1:back1\nfront2:back2\nfront3:back3\n for the following"},{"role": "user", "content": f'{chunk}'}])
          chunk_response = chatproc.choices[0].message['content'].strip()
          time.sleep(10)
          break
        except openai.error.APIError as e:
            if e.status == 429:  # Too Many Requests
                retry_after = int(e.headers.get('Retry-After', '5'))
                print(f"Rate limited. Retrying after {retry_after} seconds...")
                time.sleep(retry_after)
            else:
                raise
    # Add the response to the accumulated response variable
    response += chunk_response
    time.sleep(2)

# Print the final response
print(response)

transcript is a large transcript containing over 3000 words

#

how long do I have to wait before sending another api call?

#

10 seconds doesnt seem to be enough...

#

#How long do I have to wait before sending a new api request?