AIRust★ 1,009
anush008/fastembed-rs
FAST FASTEMBED-RS IN RUST
fastembed-rs — a Rust library for local creation of vector embeddings and their reranking. It has 1009 stars on GitHub, it is suitable for RAG, search and rerank models.
// KEY FEATURES
- Generates embeddings on CPU without GPU, using BERT, SBERT and similar models.
- Performs search reranking via cross‑encoder for better RAG.
- Provides a simple API for integration with LangChain, LlamaIndex and other RAG frameworks.
- Works offline: computations are local, data never leaves the device.
#embeddings#fastembed#rag#reranker#reranking#retrieval#retrieval-augmented-generation#vector-search
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram