python-services/Retrieve/utils/token_util.py

import tiktoken


def num_tokens_from_messages(messages, model="gpt-4o"):
    """
    Returns the number of tokens used by a list of messages.

    Args:
    messages (list): A list of messages.
    model (str): The name of the model to use for tokenization.

    Returns:
    int: The number of tokens used by the messages.
    """
    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        print("Warning: model not found. Using cl100k_base encoding.")
        encoding = tiktoken.get_encoding("cl100k_base")
    if model == "gpt-3.5-turbo":
        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0301")
    elif model == "gpt-4o":
        return num_tokens_from_messages(messages, model="gpt-4-0314")
    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 model == "gpt-4-0314":
        tokens_per_message = 3
        tokens_per_name = 1
    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


def num_tokens_from_text(text: str, model: str = "gpt-4o") -> int:
    """
    Returns the number of tokens used by a text.

    Args:
    text (str): The text to tokenize.
    model (str): The name of the model to use for tokenization.
    """
    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        print("Warning: model not found. Using cl100k_base encoding.")
        encoding = tiktoken.get_encoding("cl100k_base")
    num_tokens = 0
    if text:
        num_tokens += len(encoding.encode(text))
    return num_tokens