jina-clip-v2 is an open-weight multimodal model that generates aligned embeddings for images and text. It can be used locally through libraries such as Transformers, Sentence Transformers, and Transformers.js for semantic search, retrieval, and similarity applications.
In the Embeddings & retrieval space, Jina Clip takes a focused approach. It focuses on generating aligned image and text embeddings for semantic search and retrieval. Jina Clip is an open-source project aimed at machine learning developers and researchers. The project is open source (BSD-3-Clause). Jina Clip is available on the web, the command line, and API, and it can be self-hosted.
It is developed by Jina AI, and it first shipped in 2022. The project is developed in the open on GitHub with 24.8k stars and 61 commits in the last 90 days. Key capabilities include image embeddings, text embeddings, and cross-modal retrieval.
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