Interface EmbeddingConfig

Configuration for the embedding model used to encode memory content and document chunks into dense vectors.

interface EmbeddingConfig {
    provider: string;
    model?: string;
    dimensions?: number;
}

Properties

provider: string

Embedding provider identifier.

'openai' | 'cohere' | 'local'

model?: string

Model name to use for generating embeddings. When omitted the provider's default model is used.

'text-embedding-3-small'

dimensions?: number

Dimensionality of produced vectors. Must match the dimensionality expected by the configured vector store.