Enum TiktokenEncoding 

#[non_exhaustive]
pub enum TiktokenEncoding {
    Cl100kBase,
    O200kBase,
    P50kBase,
    R50kBase,
}

OpenAI BPE encoding family. Pick the variant matching the target model — see the crate-level docs for the model-to-encoding table.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

Cl100kBase

cl100k_base — GPT-3.5-turbo, GPT-4, GPT-4-turbo, the text-embedding-3-* family.

O200kBase

o200k_base — GPT-4o, GPT-4o-mini, o1, o3, o3-mini, o4.

P50kBase

p50k_base — GPT-3 davinci, codex.

R50kBase

r50k_base — GPT-3 ada / babbage / curie + the original GPT-2 tokenizer.

Implementations

impl TiktokenEncoding

pub const fn name(self) -> &'static str

Canonical encoding name as published by OpenAI’s tiktoken reference implementation. Surfaces on TokenCounter::encoding_name and the OTel gen_ai.tokenizer.name attribute.

Trait Implementations

impl Clone for TiktokenEncoding

fn clone(&self) -> TiktokenEncoding

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TiktokenEncoding

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Hash for TiktokenEncoding

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for TiktokenEncoding

fn eq(&self, other: &TiktokenEncoding) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for TiktokenEncoding

impl Eq for TiktokenEncoding

impl StructuralPartialEq for TiktokenEncoding