nomic-embed-vision-v1.5 is an image embedding model that produces high-quality vector representations of visual content. It is designed to work alongside Nomic's text embedding models in multimodal retrieval and analysis systems. The model can be used with Transformers and supports custom code execution.
Nomic Embed Vision is an Other AI project. It focuses on generating high-quality vector embeddings from images for retrieval and similarity tasks. It is built as an open-source project for developers building multimodal AI applications. The project is open source (Apache-2.0). It ships for API and embeddable surfaces.
Behind Nomic Embed Vision is Nomic AI, based in the United States, and it first shipped in 2024. The project is developed in the open on GitHub with 800 stars. It operates in a well-populated space: PulseGate tracks 5 similar projects. Among its 3 catalogued features are image embeddings, feature extraction, and multimodal compatibility.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do