Is there a way to combine default BM25 score of Elasticsearch and Dense Vectors similarity

Elastic Stack Elasticsearch
1

Hello everyone!

I would like to combine the BM25 score computed by Elasticsearch and
The cosine similarity of dense vectors.

I read the following post

It would be nice if I could somehow use the BM25 score in the "script".
Is there a way to do something like that?

Thank you in advance

2

Hello,
script gives you flexibility to combine textual scores with any other computations the way you like.
For example, the following query uses a linear combination of BM25 score from query: message:elasticsearch with a vector cosine similarity.

{
  "query": {
    "script_score": {
      "query": {
        "match": {
          "message": "elasticsearch"
        }
      },
      "script": {
        "source": "_score + cosineSimilarity(params.query_vector, 'my_dense_vector')",
        "params": {
          "query_vector": [4, 3.4,-0.2]
        }
      }
    }
  }
}
1 Like
3

Thank you very much

4

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.