org.llm4s.llmconnect.utils

Utilities for splitting text, audio, and video data into fixed-size overlapping chunks.

Each chunking method produces a sequence of windows with configurable size and overlap, suitable for embedding pipelines and multimodal processing.

Selects an embedding model configuration based on input modality.

Text modality selection is intentionally disallowed here; callers should load text embedding models through their typed config layer. Image, audio, and video modalities are resolved from the supplied LocalEmbeddingModels config.