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
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.
Search
Elasticsearch in 2 minutes
In this demo, we show how Elasticsearch enables production‑ready GenAI and AI‑powered search applications, from indexing and embedding your data to grounding large language models with retrieval augmented generation (RAG). You'll see how developers can go from raw data to a fully functional GenAI search experience — fast.
