Weaviate Knowledge Cards

Unlock the power of vector search. Our guides will help you conquer vector embeddings and build better AI applications.

Knowledge Cards / Multimodal RAG / Multimodal RAG

Multimodal RAG

Multimodal RAG involves retrieving from a multimodal knowledge base and then generation using a large multimodal model by generating text or images grounded in the retrieved context, which can include images, text, audio, and other modalities.