Struct VLMVideoEmbedder 

pub struct VLMVideoEmbedder(/* private fields */);

VLM Video Embedder functionality, to compute embeddings for video search.

Implementations

impl VLMVideoEmbedder

pub fn new() -> Self

pub fn compute_embeddings( &mut self, clip_data: &ClipData, compute_single_unit_only: bool, ) -> Result<Option<VideoEmbedding>, Error>

Compute video embeddings on data collected using VLMVideoCollection.

Depending on the size of the collected data, this can be compute-heavy. The user can optionally set compute_single_unit_only to compute only a single part of the video embeddings. When compute_single_unit_only is set, this needs to be called in a loop with the same arguments. The return value will inform the user whether all units were computed: it returns None when a single unit was successfully computed (but not everything), and the resulting embeddings when all embeddings have been computed.

Arguments

• clip_data: The data collected using VLMVideoCollection::start_clip and VLMVideoCollection::end_clip.
• compute_single_unit_only: Can be set to do a partial computation of the embeddings. If set, this needs to be called in a loop, see above.

Errors

• Error::ClipNotYetStarted when an empty clip is provided
• Error::InvalidClipData when the clip data is invalid

Trait Implementations

impl Debug for VLMVideoEmbedder

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

Formats the value using the given formatter.