Multi-Vector Retriever for RAG on tables, text, and images

The text discusses the development of a Multi-Vector Retriever for enabling Retrieval Augmented Generation (RAG) across diverse data types such as images, text, and tables. Three new cookbooks are released to demonstrate the application of this retriever on documents containing mixed content types. The main idea is to decouple documents used for answer synthesis from references used for retrieval. This approach can be applied to various data types including tables or images to support RAG. The text also presents three general approaches for multimodal RAG that utilize the multi-vector retriever concept, which will be featured in future cookbooks.