Enum Modality 

pub enum Modality {
    Text,
    Image,
    Embedding,
}

Modality supported by a model for input or output.

Models can support different combinations of modalities:

• Text-only models: input_modalities: [Text], output_modalities: [Text]
• Vision models: input_modalities: [Text, Image], output_modalities: [Text]
• Embedding models: input_modalities: [Text], output_modalities: [Embedding]

Variants

Text

Text input/output - supported by all language models.

Image

Image input/output - supported by multimodal vision models.

Models with Image in input_modalities can process image URLs alongside text prompts.

Embedding

Embedding input/output - vector representations.

Used by embedding models that convert text or images into high-dimensional vector representations for semantic search.

Trait Implementations

impl Clone for Modality

fn clone(&self) -> Modality

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Modality

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

Formats the value using the given formatter.

impl PartialEq for Modality

fn eq(&self, other: &Modality) -> 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 Eq for Modality

impl StructuralPartialEq for Modality