Reciprocal rank fusion

edit

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

Reciprocal rank fusion (RRF) is a method for combining multiple result sets with different relevance indicators into a single result set. RRF requires no tuning, and the different relevance indicators do not have to be related to each other to achieve high-quality results.

RRF uses the following formula to determine the score for ranking each document:

score = 0.0
for q in queries:
    if d in result(q):
        score += 1.0 / ( k + rank( result(q), d ) )
return score

# where
# k is a ranking constant
# q is a query in the set of queries
# d is a document in the result set of q
# result(q) is the result set of q
# rank( result(q), d ) is d's rank within the result(q) starting from 1

Reciprocal rank fusion API

edit

You can use RRF as part of a search to combine and rank documents using separate sets of top documents (result sets) from a combination of child retrievers using an RRF retriever. A minimum of two child retrievers is required for ranking.

An RRF retriever is an optional object defined as part of a search request’s retriever parameter. The RRF retriever object contains the following parameters:

retrievers

(Required, array of retriever objects)

A list of child retrievers to specify which sets of returned top documents will have the RRF formula applied to them. Each child retriever carries an equal weight as part of the RRF formula. Two or more child retrievers are required.

rank_constant

(Optional, integer)

This value determines how much influence documents in individual result sets per query have over the final ranked result set. A higher value indicates that lower ranked documents have more influence. This value must be greater than or equal to 1. Defaults to 60.

window_size

(Optional, integer)

This value determines the size of the individual result sets per query. A higher value will improve result relevance at the cost of performance. The final ranked result set is pruned down to the search request’s size. window_size must be greater than or equal to size and greater than or equal to 1. Defaults to the size parameter.

An example request using RRF:

GET example-index/_search
{
    "retriever": {
        "rrf": { 
            "retrievers": [
                {
                    "standard": { 
                        "query": {
                            "term": {
                                "text": "shoes"
                            }
                        }
                    }
                },
                {
                    "knn": { 
                        "field": "vector",
                        "query_vector": [1.25, 2, 3.5],
                        "k": 50,
                        "num_candidates": 100
                    }
                }
            ],
            "window_size": 50,
            "rank_constant": 20
        }
    }
}

In the above example, we execute the knn and standard retrievers independently of each other. Then we use the rrf retriever to combine the results.

First, we execute the kNN search specified by the knn retriever to get its global top 50 results.

Second, we execute the query specified by the standard retriever to get its global top 50 results.

Then, on a coordinating node, we combine the kNN search top documents with the query top documents and rank them based on the RRF formula using parameters from the rrf retriever to get the combined top documents using the default size of 10.

Note that if k from a knn search is larger than window_size, the results are truncated to window_size. If k is smaller than window_size, the results are k size.

Reciprocal rank fusion supported features

edit

The rrf retriever supports:

The rrf retriever does not currently support:

Using unsupported features as part of a search with an rrf retriever results in an exception.

Reciprocal rank fusion using multiple standard retrievers

edit

The rrf retriever provides a way to combine and rank multiple standard retrievers. A primary use case is combining top documents from a traditional BM25 query and an ELSER query to achieve improved relevance.

An example request using RRF with multiple standard retrievers:

GET example-index/_search
{
    "retriever": {
        "rrf": { 
            "retrievers": [
                {
                    "standard": { 
                        "query": {
                            "term": {
                                "text": "blue shoes sale"
                            }
                        }
                    }
                },
                {
                    "standard": { 
                        "query": {
                            "text_expansion":{
                                "ml.tokens":{
                                    "model_id":"my_elser_model",
                                    "model_text":"What blue shoes are on sale?"
                                }
                            }
                        }
                    }
                }
            ],
            "window_size": 50,
            "rank_constant": 20
        }
    }
}

In the above example, we execute each of the two standard retrievers independently of each other. Then we use the rrf retriever to combine the results.

First we run the standard retriever specifying a term query for blue shoes sales using the standard BM25 scoring algorithm.

Next we run the standard retriever specifying a text expansion query for What blue shoes are on sale? using our ELSER scoring algorithm.

The rrf retriever allows us to combine the two top documents sets generated by completely independent scoring algorithms with equal weighting.

Not only does this remove the need to figure out what the appropriate weighting is using linear combination, but RRF is also shown to give improved relevance over either query individually.

Reciprocal rank fusion using sub searches

edit

RRF using sub searches is no longer supported. Use the retriever API instead. See using multiple standard retrievers for an example.

Reciprocal rank fusion full example

edit

We begin by creating a mapping for an index with a text field, a vector field, and an integer field along with indexing several documents. For this example we are going to use a vector with only a single dimension to make the ranking easier to explain.

PUT example-index
{
    "mappings": {
        "properties": {
            "text" : {
                "type" : "text"
            },
            "vector": {
                "type": "dense_vector",
                "dims": 1,
                "index": true,
                "similarity": "l2_norm"
            },
            "integer" : {
                "type" : "integer"
            }
        }
    }
}

PUT example-index/_doc/1
{
    "text" : "rrf",
    "vector" : [5],
    "integer": 1
}

PUT example-index/_doc/2
{
    "text" : "rrf rrf",
    "vector" : [4],
    "integer": 2
}

PUT example-index/_doc/3
{
    "text" : "rrf rrf rrf",
    "vector" : [3],
    "integer": 1
}

PUT example-index/_doc/4
{
    "text" : "rrf rrf rrf rrf",
    "integer": 2
}

PUT example-index/_doc/5
{
    "vector" : [0],
    "integer": 1
}

POST example-index/_refresh

We now execute a search using an rrf retriever with a standard retriever specifying a BM25 query, a knn retriever specifying a kNN search, and a terms aggregation.

GET example-index/_search
{
    "retriever": {
        "rrf": {
            "retrievers": [
                {
                    "standard": {
                        "query": {
                            "term": {
                                "text": "rrf"
                            }
                        }
                    }
                },
                {
                    "knn": {
                        "field": "vector",
                        "query_vector": [3],
                        "k": 5,
                        "num_candidates": 5
                    }
                }
            ],
            "window_size": 5,
            "rank_constant": 1
        }
    },
    "size": 3,
    "aggs": {
        "int_count": {
            "terms": {
                "field": "integer"
            }
        }
    }
}

And we receive the response with ranked hits and the terms aggregation result. Note that _score is null, and we instead use _rank to show our top-ranked documents.

{
    "took": ...,
    "timed_out" : false,
    "_shards" : {
        "total" : 1,
        "successful" : 1,
        "skipped" : 0,
        "failed" : 0
    },
    "hits" : {
        "total" : {
            "value" : 5,
            "relation" : "eq"
        },
        "max_score" : null,
        "hits" : [
            {
                "_index" : "example-index",
                "_id" : "3",
                "_score" : null,
                "_rank" : 1,
                "_source" : {
                    "integer" : 1,
                    "vector" : [
                        3
                    ],
                    "text" : "rrf rrf rrf"
                }
            },
            {
                "_index" : "example-index",
                "_id" : "2",
                "_score" : null,
                "_rank" : 2,
                "_source" : {
                    "integer" : 2,
                    "vector" : [
                        4
                    ],
                    "text" : "rrf rrf"
                }
            },
            {
                "_index" : "example-index",
                "_id" : "4",
                "_score" : null,
                "_rank" : 3,
                "_source" : {
                    "integer" : 2,
                    "text" : "rrf rrf rrf rrf"
                }
            }
        ]
    },
    "aggregations" : {
        "int_count" : {
            "doc_count_error_upper_bound" : 0,
            "sum_other_doc_count" : 0,
            "buckets" : [
                {
                    "key" : 1,
                    "doc_count" : 3
                },
                {
                    "key" : 2,
                    "doc_count" : 2
                }
            ]
        }
    }
}

Let’s break down how these hits were ranked. We start by running the standard retriever specifying a query and the knn retriever specifying a kNN search separately to collect what their individual hits are.

First, we look at the hits for the query from the standard retriever.

"hits" : [
    {
        "_index" : "example-index",
        "_id" : "4",
        "_score" : 0.16152832,              
        "_source" : {
            "integer" : 2,
            "text" : "rrf rrf rrf rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "3",                        
        "_score" : 0.15876243,
        "_source" : {
            "integer" : 1,
            "vector" : [3],
            "text" : "rrf rrf rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "2",                        
        "_score" : 0.15350538,
        "_source" : {
            "integer" : 2,
            "vector" : [4],
            "text" : "rrf rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "1",                        
        "_score" : 0.13963442,
        "_source" : {
            "integer" : 1,
            "vector" : [5],
            "text" : "rrf"
        }
    }
]

rank 1, _id 4

rank 2, _id 3

rank 3, _id 2

rank 4, _id 1

Note that our first hit doesn’t have a value for the vector field. Now, we look at the results for the kNN search from the knn retriever.

"hits" : [
    {
        "_index" : "example-index",
        "_id" : "3",                   
        "_score" : 1.0,
        "_source" : {
            "integer" : 1,
            "vector" : [3],
            "text" : "rrf rrf rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "2",                   
        "_score" : 0.5,
        "_source" : {
            "integer" : 2,
            "vector" : [4],
            "text" : "rrf rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "1",                   
        "_score" : 0.2,
        "_source" : {
            "integer" : 1,
            "vector" : [5],
            "text" : "rrf"
        }
    },
    {
        "_index" : "example-index",
        "_id" : "5",                   
        "_score" : 0.1,
        "_source" : {
            "integer" : 1,
            "vector" : [0]
        }
    }
]

rank 1, _id 3

rank 2, _id 2

rank 3, _id 1

rank 4, _id 5

We can now take the two individually ranked result sets and apply the RRF formula to them using parameters from the rrf retriever to get our final ranking.

# doc  | query     | knn       | score
_id: 1 = 1.0/(1+4) + 1.0/(1+3) = 0.4500
_id: 2 = 1.0/(1+3) + 1.0/(1+2) = 0.5833
_id: 3 = 1.0/(1+2) + 1.0/(1+1) = 0.8333
_id: 4 = 1.0/(1+1)             = 0.5000
_id: 5 =             1.0/(1+4) = 0.2000

We rank the documents based on the RRF formula with a window_size of 5 truncating the bottom 2 docs in our RRF result set with a size of 3. We end with _id: 3 as _rank: 1, _id: 2 as _rank: 2, and _id: 4 as _rank: 3. This ranking matches the result set from the original RRF search as expected.

Pagination in RRF

edit

When using rrf you can paginate through the results using the from parameter. As the final ranking is solely dependent on the original query ranks, to ensure consistency when paginating, we have to make sure that while from changes, the order of what we have already seen remains intact. To that end, we’re using a fixed window_size as the whole available result set upon which we can paginate. This essentially means that if:

  • from + sizewindow_size : we could get results[from: from+size] documents back from the final rrf ranked result set
  • from + size > window_size : we would get 0 results back, as the request would fall outside the available window_size-sized result set.

An important thing to note here is that since window_size is all the results that we’ll get to see from the individual query components, pagination guarantees consistency, i.e. no documents are skipped or duplicated in multiple pages, iff window_size remains the same. If window_size changes, then the order of the results might change as well, even for the same ranks.

To illustrate all of the above, let’s consider the following simplified example where we have two queries, queryA and queryB and their ranked documents:

     |  queryA   |  queryB    |
_id: |  1        |  5         |
_id: |  2        |  4         |
_id: |  3        |  3         |
_id: |  4        |  1         |
_id: |           |  2         |

For window_size=5 we would get to see all documents from both queryA and queryB. Assuming a rank_constant=1, the rrf scores would be:

# doc   | queryA     | queryB       | score
_id: 1 =  1.0/(1+1)  + 1.0/(1+4)      = 0.7
_id: 2 =  1.0/(1+2)  + 1.0/(1+5)      = 0.5
_id: 3 =  1.0/(1+3)  + 1.0/(1+3)      = 0.5
_id: 4 =  1.0/(1+4)  + 1.0/(1+2)      = 0.533
_id: 5 =    0        + 1.0/(1+1)      = 0.5

So the final ranked result set would be [1, 4, 2, 3, 5] and we would paginate over that, since window_size == len(results). In this scenario, we would have:

  • from=0, size=2 would return documents [1, 4] with ranks [1, 2]
  • from=2, size=2 would return documents [2, 3] with ranks [3, 4]
  • from=4, size=2 would return document [5] with rank [5]
  • from=6, size=2 would return an empty result set as it there are no more results to iterate over

Now, if we had a window_size=2, we would only get to see [1, 2] and [5, 4] documents for queries queryA and queryB respectively. Working out the math, we would see that the results would now be slightly different, because we would have no knowledge of the documents in positions [3: end] for either query.

# doc   | queryA     | queryB         | score
_id: 1 =  1.0/(1+1)  + 0              = 0.5
_id: 2 =  1.0/(1+2)  + 0              = 0.33
_id: 4 =    0        + 1.0/(1+2)      = 0.33
_id: 5 =    0        + 1.0/(1+1)      = 0.5

The final ranked result set would be [1, 5, 2, 4], and we would be able to paginate on the top window_size results, i.e. [1, 5]. So for the same params as above, we would now have:

  • from=0, size=2 would return [1, 5] with ranks [1, 2]
  • from=2, size=2 would return an empty result set as it would fall outside the available window_size results.