Interface MultimodalSearchResult

A single result from a multimodal search query.

Extends the base vector store result with modality-specific fields so the caller knows what kind of content matched and can render it appropriately.

interface MultimodalSearchResult {
    id: string;
    content: string;
    score: number;
    modality: ContentModality;
    metadata?: Record<string, unknown>;
}

Properties

id: string

Unique document ID in the vector store.

content: string

The text content that was embedded and matched. For images: the vision LLM description. For audio: the STT transcript. For text: the original text chunk.

score: number

Cosine similarity score between the query and this result. Higher is more relevant (typically 0.0 to 1.0).

modality: ContentModality

The content modality of this result. Indicates whether the match came from text, image description, or audio transcript.

metadata?: Record<string, unknown>

Any metadata attached during indexing. May include source URLs, file names, timestamps, etc.