Skip to main content

Encoding

Struct Encoding 

Source
pub struct Encoding { /* private fields */ }
Expand description

WASM wrapper around a tiktoken encoding instance.

Created via get_encoding or encoding_for_model. Call .free() when done to release WASM memory.

Implementations§

Source§

impl Encoding

Source

pub fn encode(&self, text: &str) -> Vec<u32>

Encode text into token ids (returns Uint32Array in JS).

Special tokens like <|endoftext|> are treated as ordinary text. Use encodeWithSpecialTokens() to recognize them.

Source

pub fn encode_with_special_tokens(&self, text: &str) -> Vec<u32>

Encode text into token ids, recognizing special tokens.

Special tokens (e.g. <|endoftext|>) are encoded as their designated ids instead of being split into sub-word pieces.

Source

pub fn decode(&self, tokens: &[u32]) -> String

Decode token ids back to a UTF-8 string.

Uses lossy UTF-8 conversion — invalid byte sequences are replaced with U+FFFD.

Source

pub fn count(&self, text: &str) -> usize

Count tokens without building the full token id array.

Faster than encode(text).length for cases where you only need the count.

Source

pub fn count_with_special_tokens(&self, text: &str) -> usize

Count tokens, recognizing special tokens.

Like count() but special tokens (e.g. <|endoftext|>) are counted as single tokens instead of being split into sub-word pieces.

Source

pub fn vocab_size(&self) -> usize

Get the number of regular (non-special) tokens in the vocabulary.

Source

pub fn num_special_tokens(&self) -> usize

Get the number of special tokens in the vocabulary.

Source

pub fn name(&self) -> String

Get the encoding name (e.g. "cl100k_base").

Trait Implementations§

Source§

impl From<Encoding> for JsValue

Source§

fn from(value: Encoding) -> Self

Converts to this type from the input type.
Source§

impl FromWasmAbi for Encoding

Source§

type Abi = WasmPtr<WasmRefCell<Encoding>>

The Wasm ABI type that this converts from when coming back out from the ABI boundary.
Source§

unsafe fn from_abi(js: Self::Abi) -> Self

Recover a Self from Self::Abi. Read more
Source§

impl IntoWasmAbi for Encoding

Source§

type Abi = WasmPtr<WasmRefCell<Encoding>>

The Wasm ABI type that this converts into when crossing the ABI boundary.
Source§

fn into_abi(self) -> Self::Abi

Convert self into Self::Abi so that it can be sent across the wasm ABI boundary.
Source§

impl LongRefFromWasmAbi for Encoding

Source§

type Abi = WasmPtr<WasmRefCell<Encoding>>

Same as RefFromWasmAbi::Abi
Source§

type Anchor = RcRef<Encoding>

Same as RefFromWasmAbi::Anchor
Source§

unsafe fn long_ref_from_abi(js: Self::Abi) -> Self::Anchor

Same as RefFromWasmAbi::ref_from_abi
Source§

impl OptionFromWasmAbi for Encoding

Source§

fn is_none(abi: &Self::Abi) -> bool

Tests whether the argument is a “none” instance. If so it will be deserialized as None, and otherwise it will be passed to FromWasmAbi.
Source§

impl OptionIntoWasmAbi for Encoding

Source§

fn none() -> Self::Abi

Returns an ABI instance indicating “none”, which JS will interpret as the None branch of this option. Read more
Source§

impl RefFromWasmAbi for Encoding

Source§

type Abi = WasmPtr<WasmRefCell<Encoding>>

The Wasm ABI type references to Self are recovered from.
Source§

type Anchor = RcRef<Encoding>

The type that holds the reference to Self for the duration of the invocation of the function that has an &Self parameter. This is required to ensure that the lifetimes don’t persist beyond one function call, and so that they remain anonymous.
Source§

unsafe fn ref_from_abi(js: Self::Abi) -> Self::Anchor

Recover a Self::Anchor from Self::Abi. Read more
Source§

impl RefMutFromWasmAbi for Encoding

Source§

type Abi = WasmPtr<WasmRefCell<Encoding>>

Same as RefFromWasmAbi::Abi
Source§

type Anchor = RcRefMut<Encoding>

Same as RefFromWasmAbi::Anchor
Source§

unsafe fn ref_mut_from_abi(js: Self::Abi) -> Self::Anchor

Same as RefFromWasmAbi::ref_from_abi
Source§

impl SupportsConstructor for Encoding

Source§

impl SupportsInstanceProperty for Encoding

Source§

impl SupportsStaticProperty for Encoding

Source§

impl TryFromJsValue for Encoding

Source§

fn try_from_js_value(value: JsValue) -> Result<Self, JsValue>

Performs the conversion.
Source§

fn try_from_js_value_ref(value: &JsValue) -> Option<Self>

Performs the conversion.
Source§

impl VectorFromWasmAbi for Encoding

Source§

type Abi = <Box<[JsValue]> as FromWasmAbi>::Abi

Source§

unsafe fn vector_from_abi(js: Self::Abi) -> Box<[Encoding]>

Source§

impl VectorIntoWasmAbi for Encoding

Source§

impl WasmDescribe for Encoding

Source§

impl WasmDescribeVector for Encoding

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> ReturnWasmAbi for T
where T: IntoWasmAbi,

Source§

type Abi = <T as IntoWasmAbi>::Abi

Same as IntoWasmAbi::Abi
Source§

fn return_abi(self) -> <T as ReturnWasmAbi>::Abi

Same as IntoWasmAbi::into_abi, except that it may throw and never return in the case of Err.
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<S, T> Upcast<T> for S
where T: UpcastFrom<S> + ?Sized, S: ?Sized,

Source§

fn upcast(&self) -> &T
where Self: ErasableGeneric, T: Sized + ErasableGeneric<Repr = Self::Repr>,

Perform a zero-cost type-safe upcast to a wider ref type within the Wasm bindgen generics type system. Read more
Source§

fn upcast_into(self) -> T
where Self: Sized + ErasableGeneric, T: Sized + ErasableGeneric<Repr = Self::Repr>,

Perform a zero-cost type-safe upcast to a wider type within the Wasm bindgen generics type system. Read more