INNER CODE UNIT · Python
tiktoken_len
junruxiong/IncarnaMind · docs2db.py:46
def tiktoken_len(text: str):
"""Calculate the token length of a given text string using TikToken.
Args:
text (str): The text to be tokenized.
Returns:
int: The length of the tokenized text.
"""
tokens = tokenizer.encode(text, disallowed_special=())
return len(tokens)
def string2md5(text: str):
"""Convert a string to its MD5 hash.
Args: