CodeRankEmbed is a 137-million-parameter bi-encoder that generates embeddings for source code and text. Developers can run it locally with Sentence Transformers for code retrieval, semantic search, and similarity analysis.
In the Embeddings & retrieval space, CodeRankEmbed takes a focused approach. It focuses on retrieving and comparing relevant code using semantic embeddings. CodeRankEmbed is an open-source project aimed at developers and machine learning engineers. The project is open source (Apache-2.0). It runs on the web and API, and it can be self-hosted.
Nomic AI builds and maintains CodeRankEmbed, and it first shipped in 2024. Development happens publicly on GitHub with 56 stars. Key capabilities include code embeddings, code retrieval, and semantic similarity.
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