Redis langcache-embed-v1 is a sentence similarity model hosted on Hugging Face. It produces embeddings that can be compared to measure semantic similarity between sentences.
The model is loaded through the sentence-transformers library. Example code creates a SentenceTransformer instance from the repository identifier, encodes a list of sentences into embedding vectors, and computes a similarity matrix among them. Its architecture draws on papers referenced by arXiv identifiers 2504.02268 and 1908.10084. It supports multiple export formats including ONNX, Safetensors, and OpenVINO, and it was trained with OnlineContrastiveLoss.
The model card labels the task explicitly as sentence similarity and lists sentence-transformers as the compatible framework. It forms part of the LangCache project associated with Redis. A note on the page flags the model as outdated and directs users to a newer v3-small variant that offers better inference speed and a smaller footprint.
The repository is maintained under the Redis organization on Hugging Face, where it has received 15 likes and 52 followers. No pricing, licensing terms, or additional deployment options beyond the listed libraries and inference providers appear in the model card.
Langcache Embed is a Foundation models & chat product. It focuses on creating fast and accurate embeddings for caching and retrieval of language data. Langcache Embed is an open-source project aimed at developers. The project is open source (Apache-2.0). Langcache Embed is available on the web, the command line, embeddable surfaces, and API.
It is developed by Redis, and the product first shipped in 2019. The project is developed in the open on GitHub with 18.9k stars and 96 commits in the last 90 days. Among its 3 catalogued features are Text Embeddings, Semantic Similarity, and Sentence Encoding.
Latest indexed changes and source events
redis/langcache-embed-v1 verified by the PulseGate indexer
Other apps tracked under the same category.
