I embedded 685M public texts in 32 minutes (on 8x A100
Rust, TensorRT). Fast self-hosted embedding engine for search, RAG, and reindexing workloads on NVIDIA GPUs. Built in Rust + TensorRT for teams that care about scale, cost, and control. Quick note on how it works and how I've done my batch embedding engine IgniteMS.
셀프 호스팅오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Ion
github.coma Rust/Tokio powered JavaScript runtime for embedders
Rag Framework
github.com🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform
High-Performance Engine for Multi-Vector Search
Minigraf
github.comAn embedded, bi-temporal graph database in Rust
SeekStorm
github.comopen-source sub-millisecond search in Rust