EmbedAnything
RAG & RetrievalA minimalist, high‑performance Rust embedding pipeline for multimodal data (text, image, audio, PDFs) that streams embeddings directly to a vector database.
Features
- No PyTorch dependency – low‑memory, easy cloud deployment
- Highly modular with one‑line vector DB adapter selection
- Supports Candle, ONNX, and cloud models for dense/sparse/late‑interaction embeddings
- Multimodal ingestion (text, images, audio, PDFs) with built‑in chunking methods
- GPU acceleration and pre‑built Docker image (`starlightsearch/embedanything-server`)
Recent releases
View all 1 releases →Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
