Knowledge & Data · Model asset

Contrastive Image-Text Encoder

Model assetKnowledge & DataKnowledge & Dataarc:ContrastiveImageTextEncoder

A pair of text and image encoders trained jointly with contrastive loss so matching text-image pairs map to nearby vectors in one shared space.

Responsibility. Maps text and images into a shared embedding space.

Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

Inference Server Ch2.7

is optimized by lifecycle

Engine Builder Ch2.7

Quantitative guidance

As stated by the sources; verify before use.

CLIP produces 512-dimensional text and image vectors (Ch2.7).

Classification

Patterns: Contrastive learningZero-shot classification
Technologies: CLIPOpenCLIPNV Embed

Sources

Ch2.7: T. Nguyen, "Multimodal RAG Approaches," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 2.7. ISBN: 9798244538229.