Skip to main content

MultimodalPromptPrefixer

Trait MultimodalPromptPrefixer 

Source
pub trait MultimodalPromptPrefixer: Send + Sync {
    // Provided methods
    fn prefix_image(&self, _image_indices: Vec<usize>, prompt: &str) -> String { ... }
    fn prefix_audio(&self, _audio_indexes: Vec<usize>, prompt: &str) -> String { ... }
    fn prefix_video(&self, _video_indexes: Vec<usize>, prompt: &str) -> String { ... }
}
Expand description

Prepend a vision tag appropriate for the model to the prompt. Image indexing is assumed that start at 0.

Provided Methods§

Source

fn prefix_image(&self, _image_indices: Vec<usize>, prompt: &str) -> String

Prefix for inclusion in messages (may do nothing if the chat template handles it).

Source

fn prefix_audio(&self, _audio_indexes: Vec<usize>, prompt: &str) -> String

Prefix for inclusion in messages (may do nothing if the chat template handles it).

Source

fn prefix_video(&self, _video_indexes: Vec<usize>, prompt: &str) -> String

Prefix for inclusion in messages (may do nothing if the chat template handles it).

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§