Relevance workbench
In this workbench, you can compare our Elastic Learned Sparse Encoder model (with or without RRF) and traditional textual search using BM25.
Start comparing different hybrid search techniques using TMDB's movies dataset as sample data. Or fork the code and ingest your own data to try it on your own!
Try these queries to get started:
- "The matrix"
- "Movies in Space"
- "Superhero animated movies"
Notice how some queries work great for both search techniques. For example, 'The Matrix' performs well with both models. However, for queries like "Superhero animated movies", the Elastic Learned Sparse Encoder model outperforms BM25. This can be attributed to the semantic search capabilities of the model.
Explore similar demos
Search
Create AI search with Elastic Agent Builder and Workflows
Watch a live demo of Elastic Agent Builder transforming traditional search into a conversational AI application in minutes. Learn how to integrate large language models (LLMs), including configuring an Azure OpenAI model, for production-ready search without a full application rebuild.
검색
2분 만에 알아보는 Elasticsearch
이 데모에서는 데이터를 색인 및 임베딩하는 것부터 Retrieval-Augmented Generation(RAG)을 통해 대규모 언어 모델의 기반을 구축하는 것에 이르기까지, Elasticsearch가 프로덕션에 사용할 수 있는 생성형 AI 및 AI 기반 검색 애플리케이션을 어떻게 지원하는지 보여줍니다. 개발자가 원시 데이터에서 완전한 기능을 갖춘 생성형 AI 검색 경험으로 빠르게 전환하는 방법을 알아볼 수 있습니다.
Observability
See Elastic Observability in action: 2-minute quick demo
Watch this short, two-minute demo to discover key capabilities and real-world use cases. From metrics and logs to traces and beyond, see how Elastic empowers teams to gain actionable insights and keep their environments running smoothly.
