Multimodal Search & Agent-Friendly Docs

Multimodal search: Search across video (≤120s clips), audio (≤80s clips), and images alongside text in a single query
Cross-modal reranking for multimodal collections alongside the text reranker
Better recall on short or ambiguous queries
ARN-based indexing for S3
Agent-friendly documentation: llms.txt, structured API reference for LLMs