Contriever is an unsupervised dense information retrieval model trained with contrastive learning. Developers and researchers can load its weights locally through Hugging Face Transformers for semantic search and retrieval applications.
Contriever is an Other AI project. It focuses on finding semantically relevant documents without relying on exact keyword matches. It is built as an open-source project for machine learning engineers and researchers. Contriever is open source under the Open Source license. Contriever is available on the web, the command line, and API, and it can be self-hosted.
Behind Contriever is AI at Meta, and it first shipped in 2022. The GitHub repository has been archived. Key capabilities include dense retrieval, semantic search, and unsupervised training.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match