llm4s-core/org.llm4s/org.llm4s.llmconnect/org.llm4s.llmconnect.utils/ModelSelector

ModelSelector

org.llm4s.llmconnect.utils.ModelSelector

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.

Attributes

Graph
Supertypes: class Object

trait Matchable

class Any
Self type: ModelSelector.type

Members list

Value members

Concrete methods

Select a local embedding model by modality.

Text modality returns an error since text model selection is configuration-driven. Image, audio, and video modalities resolve against the supplied local-model configuration and look up dimensions from the ModelDimensionRegistry.

Value parameters

localModels: local model configuration containing model names per modality
modality: the input modality to select a model for

Attributes

Returns: the resolved EmbeddingModelConfig or an error

In this article

Generated with