Jina code embeddings is an open-weight 0.5-billion-parameter model that converts source code and text into embeddings. Developers and ML engineers can run it with Transformers or sentence-transformers for semantic code search, retrieval, and similarity applications.
Jina Code Embeddings 0.5b is a Foundation models & chat project. It focuses on generating semantic vector representations of source code for search, retrieval, and code similarity tasks. It is built as an open-source project for developers and machine learning engineers. Jina Code Embeddings 0.5b is open source under the BSD-3-Clause license. It runs on the web, the command line, and API, and it can be self-hosted.
Behind Jina Code Embeddings 0.5b is Jina AI, and it first shipped in 2022. Development happens publicly on GitHub with 24.8k stars and 52 commits in the last 90 days. PulseGate's similarity index places it among 6 comparable projects. Among its 6 catalogued features are code embeddings, feature extraction, and transformers support.
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