Elasticsearch is a distributed engine from Elastic for searching and analysing data that also works as a vector database, combining keyword search, vector search and filters in one system.
In plain words
Elasticsearch is used for full-text search and for searching logs and documents. It can also store embeddings and find the vectors most similar to a query. The useful part for AI apps is that one query can mix vector similarity with classic keyword search, filters and aggregations. That makes it an option for the retrieval step of RAG, alongside its uses for logs, metrics and security data.
A quick example
Imagine a help centre with thousands of articles already indexed in Elasticsearch for keyword search. The team adds an embedding for each article. Now a question such as "my card was charged twice" can match an article titled "duplicate payments" by meaning, while filters still restrict results to the user's country.
Where you'll meet it
- Retrieval for RAG and semantic search.
- Full-text search in websites and apps.
- Logs, metrics and security monitoring.
Related
Sources
- DocsVector search in Elasticsearch, Elastic Docs · read 29 Sept 2026
- Docselastic/elasticsearch, Elastic (GitHub) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.