Interface MultimodalIndexerConfig

Configuration for the MultimodalIndexer.

Example

const config: MultimodalIndexerConfig = {
  defaultCollection: 'knowledge-base',
  imageDescriptionPrompt: 'Describe this image for use in a search index.',
};
interface MultimodalIndexerConfig {
    defaultCollection?: string;
    imageDescriptionPrompt?: string;
}

Properties

defaultCollection? imageDescriptionPrompt?

Properties

Optional defaultCollection

defaultCollection?: string

Default vector store collection name for indexed content.

Default

'multimodal'

Optional imageDescriptionPrompt

imageDescriptionPrompt?: string

Custom prompt template for the vision LLM when describing images. If omitted, a sensible default prompt is used.

Settings

Member Visibility

Theme

On This Page

defaultCollectionimageDescriptionPrompt