Skip to Content
Relevan Beta is here 🎉
ResourcesCompareRelevan vs Elasticsearch

Relevan vs Elasticsearch

Elasticsearch is the search engine from Elastic. You can run it yourself, or use Elastic Cloud in a hosted or serverless form. Your team owns the relevance work. Relevan is a managed search engine that tunes the retrieval of each index for you.

The facts about Elasticsearch come from the public pages of Elastic, as of October 2026. The sources are at the end of this page.

Summary

ElasticsearchRelevan
ApproachSearch infrastructureRelevance tuning for each index
Who runs the clusterYour team, or Elastic CloudRelevan
Who tunes relevanceYour teamRelevan
Learned rankingLearning To Rank, from version 8.12, on some subscription levelsAn optional reranking model for each index
Click and feedback dataYour team builds and runs the pipelineAn API, with logging and storage
PricingResource-based (hosted), usage-based (serverless), or a license based on nodes and RAM (self-managed)Monthly plans, from a free plan

What Elasticsearch does

  • Elasticsearch gives full-text search, vector search, hybrid search, filters, and aggregations.
  • Learning To Rank uses a trained model as a second-stage reranker of the results from a first-stage query. It came in version 8.12, and it is only on some subscription levels.
  • The model trains on a judgment list. The Elastic documentation says that a team can make a judgment list by hand, or build it from clicks or conversions.
  • The Behavioral Analytics feature, which collected search events, was discontinued in Elastic 9.0.0.
  • Elastic Cloud has hosted and serverless forms on AWS, Google Cloud, and Azure.

What Relevan does

Relevan is a managed search engine for your own records, such as products, profiles, and documents. You send JSON records and a mapping. Relevan runs the OpenSearch index, and agents search it through an HTTP API.

  • Each search response tells the agent why each result matched, and suggests what to try next.
  • Relevan tunes retrieval and ranking for each index. Compare Relevan with other search tools explains what Relevan tunes, and when.
  • The feedback endpoint records clicks, LLM judgments, and conversions for each search.
  • Relevan prices by plan, from a free plan. See pricing.

The main difference

Elasticsearch gives you a strong engine, and your team writes the queries, tunes them, and trains any model. Relevan sets the field weights, the BM25 parameters, and hybrid retrieval for each index. It can also add a reranking model for each index.

Click and feedback data

To train a ranking model on Elasticsearch, your team builds and runs the path for click and feedback data. These are the parts:

  1. A log of each search, with a query ID, the results, and the position of each result.
  2. An endpoint or a client library that collects clicks, judgments, and conversions.
  3. A stream or a queue that carries the events, with buffering, retries, and alarms.
  4. Storage, partitioned by customer, index, and date.
  5. A retention policy, and the removal of personal data.
  6. A join of each event to the search that it is about.
  7. A weight for each event type. A click is weaker evidence than a conversion.
  8. A job that turns events into judgment lists, with a correction for position bias.
  9. Training, evaluation, and deployment of the model, and a new run when the data or the mapping changes.

Relevan supplies parts 1 to 4 and part 6 through its API, and the retention window of part 5. Each search response has a query ID, and the feedback endpoint takes events that refer to it. Relevan logs the searches and the events, and stores them by organization, index, date, and event type. Relevan keeps these events for 13 months by default. Click and feedback data gives the details, and the part that is not automatic today.

When to choose Elasticsearch

  • You have a team that can tune relevance and train ranking models.
  • You already use Elastic for logs, observability, or security, and you want one platform.
  • You need features that Relevan does not expose, such as custom analyzers or aggregations of your own design.
  • You must run the engine on premises, or in a cloud that Relevan does not use.

When to choose Relevan

  • You do not want to run a cluster or buy a subscription level for learned ranking.
  • You do not have a team to build the click and feedback pipeline.
  • You want each index tuned to its own documents and queries.
  • Your agents need an explanation of each match and a suggestion for the next search.

Sources

Read on October 29, 2026:

Last updated on
Relevan vs ChromaRelevan vs Mixedbread