nova-api/api/helpers/tokens.py
2023-08-01 20:19:18 +02:00

49 lines
1.5 KiB
Python

import tiktoken
def count_for_messages(messages: list, model: str='gpt-3.5-turbo-0613') -> int:
"""Return the number of tokens used by a list of messages."""
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
encoding = tiktoken.get_encoding('cl100k_base')
if model in {
'gpt-3.5-turbo-0613',
'gpt-3.5-turbo-16k-0613',
'gpt-4-0314',
'gpt-4-32k-0314',
'gpt-4-0613',
'gpt-4-32k-0613',
}:
tokens_per_message = 3
tokens_per_name = 1
elif model == 'gpt-3.5-turbo-0301':
tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
tokens_per_name = -1 # if there's a name, the role is omitted
elif 'gpt-3.5-turbo' in model:
return num_tokens_from_messages(messages, model='gpt-3.5-turbo-0613')
elif 'gpt-4' in model:
return num_tokens_from_messages(messages, model='gpt-4-0613')
else:
raise NotImplementedError(f"""num_tokens_from_messages() is not implemented for model {model}.
See https://github.com/openai/openai-python/blob/main/chatml.md
for information on how messages are converted to tokens.""")
num_tokens = 0
for message in messages:
num_tokens += tokens_per_message
for key, value in message.items():
num_tokens += len(encoding.encode(value))
if key == 'name':
num_tokens += tokens_per_name
num_tokens += 3 # every reply is primed with <|start|>assistant<|message|>
return num_tokens