Jina-CLIP-v1 is a multimodal model that produces aligned embeddings for both text and images. It supports feature extraction, sentence similarity, and cross-modal retrieval tasks. The model is available through Transformers, ONNX, and Transformers.js and is designed for production embedding use cases.
In the Embeddings & retrieval space, Jina Clip takes a focused approach. It focuses on creating unified embeddings for both text and images to enable cross-modal retrieval and similarity tasks. It is built as an open-source project for developers and researchers. Jina Clip is open source under the Apache-2.0 license. It runs on the web, the command line, and API.
Jina AI builds and maintains Jina Clip, and it first shipped in 2023. Development happens publicly on GitHub with 16.2k stars and 16 commits in the last 90 days.
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