Skip to main content

TextProcessor

memvid_rs::ml::text

Struct TextProcessor

pub struct TextProcessor { /* private fields */ }

Expand description

Text preprocessor and tokenizer

Implementations§

impl TextProcessor

pub fn new(config: TextConfig) -> Self

Create new text processor

pub fn load_tokenizer<P: AsRef<Path>>(&mut self, model_dir: P) -> Result<()>

Load tokenizer from model directory

pub fn preprocess_text(&self, text: &str) -> String

Preprocess text (normalize, clean, etc.)

pub fn tokenize(&self, text: &str) -> Result<TokenizedText>

Tokenize text for model inference

pub fn tokenize_batch(&self, texts: &[String]) -> Result<Vec<TokenizedText>>

Tokenize multiple texts in batch

pub fn vocab_size(&self) -> Option<usize>

Get tokenizer vocabulary size

pub fn config(&self) -> &TextConfig

Get configuration

pub fn has_tokenizer(&self) -> bool

Check if real tokenizer is loaded

Auto Trait Implementations§

impl !Freeze for TextProcessor

impl RefUnwindSafe for TextProcessor

impl Send for TextProcessor

impl Sync for TextProcessor

impl Unpin for TextProcessor

impl UnsafeUnpin for TextProcessor

impl UnwindSafe for TextProcessor

Blanket Implementations§

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

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

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

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

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

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

Mutably borrows from an owned value. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

impl<T> Instrument for T

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

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

fn into(self) -> U

Calls U::from(self).

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

impl<T> IntoEither for T

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

impl<T> Pointable for T

const ALIGN: usize

The alignment of pointer.

type Init = T

The type for initializers.

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more

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

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow only if self and other return Action::Follow. Read more

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns Action::Follow if either self or other returns Action::Follow. Read more

impl<T> Same for T

type Output = T

Should always be Self

impl<SS, SP> SupersetOf<SS> for SP
where SS: SubsetOf<SP>,

fn to_subset(&self) -> Option<SS>

The inverse inclusion map: attempts to construct self from the equivalent element of its superset. Read more

fn is_in_subset(&self) -> bool

Checks if self is actually part of its subset T (and can be converted to it).

fn to_subset_unchecked(&self) -> SS

Use with care! Same as self.to_subset but without any property checks. Always succeeds.

fn from_subset(element: &SS) -> SP

The inclusion map: converts self to the equivalent element of its superset.

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

type Error = Infallible

The type returned in the event of a conversion error.

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

Performs the conversion.

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

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

The type returned in the event of a conversion error.

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

Performs the conversion.

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

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

The type returned in the event of a conversion error.

fn try_into<'async_trait>( self, ) -> Pin<Box<dyn Future<Output = Result<U, <U as TryFrom<T>>::Error>> + 'async_trait>>
where T: 'async_trait,

Performs the conversion.

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

fn vzip(self) -> V

impl<T> WithSubscriber for T

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more

impl<T> ErasedDestructor for T
where T: 'static,

impl<T> ErasedDestructor for T
where T: 'static,