GH Repository · StarlightSearch
EmbedAnything
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
- stars
- 1,307
- 30-day movement
- +10/day
- Related entries
- 60
- Connections
- 1
Rustlocalhacktoberfestproduction-readylarge-language-modelssearchmachine-learningindexingpythonpipelineinformation-retrievalaidockervector-databaserustcloudonnxruntimehigh-performanceinferencegenerative-airagserver
EmbedAnything is a Rust-based tool for embedding inference, ingestion, and indexing, exposed through a Python interface and Docker toolchain. It targets RAG pipelines, using ONNX Runtime for model execution and offering server and local deployment options.
You want a memory-safe, production-oriented embedding and indexing pipeline without leaving the Python ecosystem.
Use it to
- Generate embeddings for RAG pipelines
- Ingest and index documents into a vector database
- Run embedding inference locally via ONNX Runtime
- Deploy an embedding server in Docker
For Developers building RAG and search systems
- Role
- rag
- Language
- Rust
- Licence
- Apache-2.0
- Forks
- 142
- Open issues
- 20
- Last push
- 2026-08-12
- Latest release
- v0.1.20 · 2024-07-12
topicsembeddingsragrustindexingvector-databaseinference