callgpt

call_gpt(prompt, max_attempts=10, model='gpt-3.5-turbo-16k', max_tokens=None, verbose=True, delay_seconds=2)

Calls the OpenAI GPT API with the given prompt.

Parameters:

  • prompt (str) – The prompt to send to the GPT API.

  • max_attempts (int) – The maximum number of attempts to make if the API call fails. Defaults to 10.

  • model (str) – The GPT model to use. Defaults to “gpt-3.5-turbo-16k”.

  • max_tokens (int or None) – The maximum number of tokens to generate. If None, uses the value from the ‘.local/openai.json’ file.

  • verbose (bool) – Whether to print the GPT response. Defaults to True.

  • delay_seconds (int) – The number of seconds to wait between attempts. Defaults to 2.

Returns:

The GPT response.

Return type:

str

Raises:

Exception – If the API call fails after the maximum number of attempts.

get_decoded_token_list(input, model='gpt-3.5-turbo-16k')

Encodes the given input string into tokens using the specified model’s encoding and then decodes each token back to a string.

Parameters:

  • input (str) – The input string to encode.

  • model (str) – The name of the model whose encoding should be used. Defaults to “gpt-3.5-turbo-16k”.

Returns:

A list of decoded tokens.

Return type:

list[str]