Skip to main content

Module engine

Module engine 

Source
Expand description

One trait per task, many engines per trait.

An engine is a named, swappable implementation of a task — exactly the role a codec plays in ffmpeg. Engines are registered in an crate::registry::EngineRegistry and selected by name.

Structs§

AsrOptions
DepthOptions
Options for a depth run.
DepthOutput
Image → objects (Diana). What a depth engine returns: a dense map plus what is needed to place it back on the source image.
DetectOptions
Detection options (Diana).
EngineInfo
Metadata every engine exposes for discovery (ffai engines).
OcrOptions
TtsOptions
VlmOptions
Options for a VLM call (Argus).
VlmPrompt
An ordered, interleaved multimodal prompt — text <img> text <img> text.

Enums§

Decoding
How a VLM decoder picks each next token.
EngineStatus
Honesty marker shown in ffai engines — stubs are visible, not hidden.
Task
The tasks FFai knows about (the “stream types” of the toolkit).
VlmPart
One piece of a multimodal prompt.

Traits§

AsrEngine
Speech → text (Mercury).
DepthEngine
Monocular depth estimation.
DetectEngine
OcrEngine
Image → text (Carmenta).
TtsEngine
Text → speech (Mercury).
VlmEngine
Image/video → description (Argus).