huggingface/text-embeddings-inference
A Rust-based high-performance inference server for deploying open-source text embeddings and sequence classification models.
Velocity · 7d
+5.0
★ / day
Trend
→steady
star history
Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. It provides high-performance extraction for popular embedding models including FlagEmbedding, Ember, GTE, and E5. Built in Rust for speed, TEI offers features like batching, quantization support, and distributed tracing for production deployments.