Nomic AI Releases Nomic Embed Vision v1 and Nomic Embed Vision v1.5: CLIP-like Vision Models that Can be Used Alongside their Popular Text Embedding Models

Nomic AI has released Nomic Embed Vision v1 and v1.5, which provide high-quality vision embeddings that integrate with Nomic's text embedding models. The unified multimodal latent space outperforms competitors like OpenAI CLIP and excels in image and text tasks.