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
Platform
Elasticsearch: Ingest to Insights
From zero to start, explore this 15 minute lab to master the basics and get started quickly on Elasticsearch. Learn how to ingest and parse your data with precision, explore patterns, and create interactive visualizations.
Observability
Get value from logs
Observability 101: Lesson 1 of 4 — Learn the basics of logs and how to derive value by leveraging KQL and ES|QL, creating visualizations and anomaly detection jobs. By the end of this 15 minute Elastic Observability lab, you’ll be able to ask a question about your logs and return an answer.
Observability
Ingesting logs, metrics, and traces with OpenTelemetry
Observability 101: Lesson 2 of 4 — Get started with Elastic Observability by onboarding logs, metrics and traces using Elastic Distribution for OpenTelemetry (EDOT). In this 15 minute lab, use the opentelemetry (otel) collector to provide structure and definition to logs.
