How JoyCastle Accelerated a 100k+ Ad Asset Library with Amazon Nova Multimodal Embeddings

JoyCastle faced a growing ad‑asset library that slowed creative production, so it built an AI‑powered management system using Amazon Nova Multimodal Embeddings, achieving unified semantic search, automatic video segmentation, 96.7% recall and a 73.3% top‑2 precision while reducing manual labeling effort.

AWSAmazon NovaAsset Management

0 likes · 13 min read

How JoyCastle Accelerated a 100k+ Ad Asset Library with Amazon Nova Multimodal Embeddings

AI Explorer

Mar 11, 2026 · Artificial Intelligence

Gemini Embedding 2: Google’s First Native Multimodal Embedding Model

Google’s Gemini Embedding 2 introduces a native multimodal embedding model that maps text, images, video, audio, and documents into a single vector space, offers three configurable dimensions, achieves state‑of‑the‑art benchmarks across modalities, and enables cross‑modal search, RAG, and seamless integration with major vector databases.

AI modelsGemini EmbeddingMatryoshka representation

0 likes · 8 min read

Gemini Embedding 2: Google’s First Native Multimodal Embedding Model

Amazon Cloud Developers

Oct 29, 2025 · Artificial Intelligence

How Amazon Nova’s Multimodal Embedding Model Handles All Modalities in One Go

Amazon Nova, a new multimodal embedding model now available on Amazon Bedrock, unifies text, document, image, video, and audio into a single semantic space, offering up to 8000‑token context, multiple output dimensions, and detailed Python examples for embedding generation, storage, and cross‑modal search.

AWS BedrockAmazon NovaPython SDK

0 likes · 19 min read

How Amazon Nova’s Multimodal Embedding Model Handles All Modalities in One Go

AI Frontier Lectures

May 21, 2025 · Artificial Intelligence

New BGE Vector Models Set SOTA in Code and Multimodal Retrieval – What Makes Them So Powerful?

Three newly released BGE vector models—BGE‑Code‑v1, BGE‑VL‑v1.5, and BGE‑VL‑Screenshot—deliver state‑of‑the‑art performance on code, multimodal, and visual document retrieval benchmarks, are open‑source on Hugging Face and GitHub, and aim to boost retrieval‑augmented applications across languages and modalities.

AI modelsBGECode search

0 likes · 8 min read

New BGE Vector Models Set SOTA in Code and Multimodal Retrieval – What Makes Them So Powerful?