Glossary

This glossary describes essential terms and concepts to help you understand Elasticsearch and its related technologies.

ONNX (Open Neural Network Exchange)

An open standard that represents machine learning models as portable computational graphs, enabling deployment across different frameworks and hardware without retraining. ONNX Runtime, the primary execution engine, optimizes inference through hardware specific execution providers supporting CPU, GPU and specialized accelerators like NPUs. Exporting embedding models to ONNX is a common production optimization, often reducing inference latency significantly compared to native framework execution.

Out-of-Domain

Data or evaluation scenarios that differ from a model's training distribution. Out-of-domain performance is a stronger measure of generalization and more representative of real-world usage, where queries, documents and content types are rarely anticipated during training. A model that degrades significantly out-of-domain is likely overfitting to its training distribution.

최첨단 검색 환경을 구축할 준비가 되셨나요?

충분히 고급화된 검색은 한 사람의 노력만으로는 달성할 수 없습니다. Elasticsearch는 여러분과 마찬가지로 검색에 대한 열정을 가진 데이터 과학자, ML 운영팀, 엔지니어 등 많은 사람들이 지원합니다. 서로 연결하고 협력하여 원하는 결과를 얻을 수 있는 마법 같은 검색 환경을 구축해 보세요.

직접 사용해 보세요