Multimodal search

Models 5

Gen 3

jina embeddings v5 omni

By Jina AI

jina-embeddings-v5-omni is Jina AI’s multimodal embedding model suite for text, image, audio, video, and PDFs. It extends Jina’s v5 text embedding models into one shared semantic space while preserving identical text embeddings, so existing text indexes do not need rebuilding.

🔍Multimodal search 🔍Information retrieval 📂Content categorization 🔍Conceptual search

NewMultimodal

Released 2mo ago
Gen 7

Embed 4

By Cohere

Multimodal embedding model aimed at enterprise search and retrieval over multimodal data.

🔍Multimodal search

Text

Released 4mo ago
Gen 4

Molmo 2

By Ai2

Molmo 2 is AI2’s open 4B/7B/8B multimodal model for images and video, delivering state-of-the-art grounded video QA, pointing and tracking that return coordinates and timestamps for events instead of text-only answers.

🎥Videos 📝Writing 📷Images 🔍Multimodal search

Text

Released 6mo ago
Gen 3 Voyage

Voyage multimodal 3

By Voyage AI

Multimodal embedding model that vectorizes interleaved text and images through a unified transformer encoder. Supports screenshots of PDFs, slides, tables, and figures without complex document parsing. Unlike CLIP-based models, eliminates the modality gap, enabling accurate mixed-modality retrieval across text and visual content.

🔎Semantic search 🔍Multimodal search 🔍Image search

Multimodal

Released 1y ago
Gen 7 Command

Command R Plus

By Caldera Labs

Command R+ is a higher-capability variant of Command R with stronger reasoning and coding while keeping the same retrieval-centric interface.

💻Coding 🔍Multimodal search 🛍️E-commerce websites

Text

Released 2y ago

Search

Multimodal search

Related Tasks✕

Models 5

Repositories 6

Go to section

Search

Multimodal search

Related Tasks✕

Models 5

Repositories 6

Help

People also viewed

Task Options

Create AI Tools

Mini Tool

Vibe code an AI Tool

Choose listing type: