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
Uptime Overview
React to availability issues across your apps and services before they affect users.
Security
Accelerate data onboarding with Elastic AI Import
Elastic’s Automatic Import feature saves analysts from the lengthy process of building custom data parsers, allowing them to instead focus on threat hunting and improve their organization’s security posture. In this demo, see how Elastic AI Import feature can process both supported or unsupported log sources, normalizing and enriching them for analysts.
Search
Intro to MCP with Elasticsearch MCP Server
This hands-on workshop introduces the Model-Context Protocol (MCP) server, which orchestrates AI workflows via modular tools. Explore how the MCP Client interacts with the MCP Server, utilizing Elasticsearch to facilitate intelligent search, and enable the creation of structured, extensible AI systems.