You are looking at preliminary documentation for a future release. Not what you want? See the current release documentation.
Elastic Docs ›Elasticsearch Guide [master] ›Search your data
« Tutorial: Using Cohere with Elasticsearch Learning To Rank »

Retrieversedit

This functionality is in technical preview and may be changed or removed in a future release. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features.

A retriever is an abstraction that was added to the Search API in 8.14.0. This abstraction enables the configuration of multi-stage retrieval pipelines within a single _search call. This simplifies your search application logic, because you no longer need to configure complex searches via multiple Elasticsearch calls or implement additional client-side logic to combine results from different queries.

This document provides a general overview of the retriever abstraction. For implementation details, including notable restrictions, check out the reference documentation in the _search API docs.

Retriever typesedit

Retrievers come in various types, each tailored for different search operations. The following retrievers are currently available:

  • Standard Retriever. Returns top documents from a traditional query. Mimics a traditional query but in the context of a retriever framework. This ensures backward compatibility as existing _search requests remain supported. That way you can transition to the new abstraction at your own pace without mixing syntaxes.
  • kNN Retriever. Returns top documents from a knn search, in the context of a retriever framework.

  • RRF Retriever. Combines and ranks multiple first-stage retrievers using the reciprocal rank fusion (RRF) algorithm. Allows you to combine multiple result sets with different relevance indicators into a single result set. An RRF retriever is a compound retriever, where its filter element is propagated to its sub retrievers.

    Sub retrievers may not use elements that are restricted by having a compound retriever as part of the retriever tree. See the RRF documentation for detailed examples and information on how to use the RRF retriever.

Stay tuned for more retriever types in future releases!

What makes retrievers useful?edit

Here’s an overview of what makes retrievers useful and how they differ from regular queries.

  1. Simplified user experience. Retrievers simplify the user experience by allowing entire retrieval pipelines to be configured in a single API call. This maintains backward compatibility with traditional query elements by automatically translating them to the appropriate retriever.
  2. Structured retrieval. Retrievers provide a more structured way to define search operations. They allow searches to be described using a "retriever tree", a hierarchical structure that clarifies the sequence and logic of operations, making complex searches more understandable and manageable.
  3. Composability and flexibility. Retrievers enable flexible composability, allowing you to build pipelines and seamlessly integrate different retrieval strategies into these pipelines. Retrievers make it easy to test out different retrieval strategy combinations.
  4. Compound operations. A retriever can have sub retrievers. This allows complex nested searches where the results of one retriever feed into another, supporting sophisticated querying strategies that might involve multiple stages or criteria.
  5. Retrieval as a first-class concept. Unlike traditional queries, where the query is a part of a larger search API call, retrievers are designed as standalone entities that can be combined or used in isolation. This enables a more modular and flexible approach to constructing searches.
  6. Enhanced control over document scoring and ranking. Retrievers allow for more explicit control over how documents are scored and filtered. For instance, you can specify minimum score thresholds, apply complex filters without affecting scoring, and use parameters like terminate_after for performance optimizations.
  7. Integration with existing Elasticsearch functionalities. Even though retrievers can be used instead of existing _search API syntax (like the query and knn), they are designed to integrate seamlessly with things like pagination (search_after) and sorting. They also maintain compatibility with aggregation operations by treating the combination of all leaf retrievers as should clauses in a boolean query.
  8. Cleaner separation of concerns. When using compound retrievers, only the query element is allowed, which enforces a cleaner separation of concerns and prevents the complexity that might arise from overly nested or interdependent configurations.

Exampleedit

The following example demonstrates how using retrievers simplify the composability of queries for RRF ranking.

GET example-index/_search
{
  "retriever": {
    "rrf": {
      "retrievers": [
        {
          "standard": {
            "query": {
              "text_expansion": {
                "vector.tokens": {
                  "model_id": ".elser_model_2",
                  "model_text": "What blue shoes are on sale?"
                }
              }
            }
          }
        },
        {
          "standard": {
            "query": {
              "match": {
                "text": "blue shoes sale"
              }
            }
          }
        }
      ]
    }
  }
}

This example demonstrates how you can combine different retrieval strategies into a single retriever pipeline.

Compare to RRF with sub_searches approach:

Expand for example 
GET example-index/_search
{
  "sub_searches":[
    {
      "query":{
        "match":{
          "text":"blue shoes sale"
        }
      }
    },
    {
      "query":{
        "text_expansion":{
          "vector.tokens":{
            "model_id":".elser_model_2",
            "model_text":"What blue shoes are on sale?"
          }
        }
      }
    }
  ],
  "rank":{
    "rrf":{
      "window_size":50,
      "rank_constant":20
    }
  }
}

Glossaryedit

Here are some important terms:

  • Retrieval Pipeline. Defines the entire retrieval and ranking logic to produce top hits.
  • Retriever Tree. A hierarchical structure that defines how retrievers interact.
  • First-stage Retriever. Returns an initial set of candidate documents.
  • Compound Retriever. Builds on one or more retrievers, enhancing document retrieval and ranking logic.
  • Combiners. Compound retrievers that merge top hits from multiple sub-retrievers.

Retrievers in actionedit

The Search Playground builds Elasticsearch queries using the retriever abstraction. It automatically detects the fields and types in your index and builds a retriever tree based on your selections.

You can use the Playground to experiment with different retriever configurations and see how they affect search results.

Refer to the Playground documentation for more information.

« Tutorial: Using Cohere with Elasticsearch Learning To Rank »