Interface: MultimodalSearchOptions

Defined in: packages/agentos/src/rag/multimodal/types.ts:166

Options for cross-modal search.

Example

const results = await indexer.search('cats playing', {
  topK: 10,
  modalities: ['image', 'text'],
  collection: 'user-content',
});

Properties

collection?

optional collection: string

Defined in: packages/agentos/src/rag/multimodal/types.ts:183

Vector store collection to search in.

Default

'multimodal'

---

hyde?

optional hyde: object

Defined in: packages/agentos/src/rag/multimodal/types.ts:203

HyDE (Hypothetical Document Embedding) configuration for this search.

When enabled, a hypothetical answer is generated from the query via LLM and embedded instead of the raw query. This produces embeddings that are semantically closer to stored document representations, improving recall for vague or exploratory queries.

Requires a HydeRetriever to be set on the indexer via MultimodalIndexer.setHydeRetriever.

enabled?

optional enabled: boolean

Whether to use HyDE for this search.

Default

false

hypothesis?

optional hypothesis: string

Pre-generated hypothesis text (skips the LLM call).

Example

const results = await indexer.search('architecture diagram', {
  hyde: { enabled: true },
});

---

modalities?

optional modalities: ContentModality[]

Defined in: packages/agentos/src/rag/multimodal/types.ts:177

Filter results to specific modalities. If omitted or empty, all modalities are searched.

---

topK?

optional topK: number

Defined in: packages/agentos/src/rag/multimodal/types.ts:171

Maximum number of results to return.

Default

5