Skip to content

Simple tokenizer

SimpleTokenizer

Bases: BaseTokenizer

Source code in griptape/tokenizers/simple_tokenizer.py 
 6
 7
 8
 9
10
11
12
13
14
@define()
class SimpleTokenizer(BaseTokenizer):
    model: str = field(init=False, kw_only=True)
    characters_per_token: int = field(kw_only=True)

    def count_tokens(self, text: str) -> int:
        num_tokens = (len(text) + self.characters_per_token - 1) // self.characters_per_token

        return num_tokens

characters_per_token: int = field(kw_only=True) class-attribute instance-attribute

model: str = field(init=False, kw_only=True) class-attribute instance-attribute

count_tokens(text)

Source code in griptape/tokenizers/simple_tokenizer.py 
11
12
13
14
def count_tokens(self, text: str) -> int:
    num_tokens = (len(text) + self.characters_per_token - 1) // self.characters_per_token

    return num_tokens