더 나은 바이너리 정량화(BBQ)를 사용 사례에 구현하는 방법

PUT _inference/text_embedding/my_e5_model
{
  "service": "elasticsearch",
  "service_settings": {
    "num_threads": 1,
    "model_id": ".multilingual-e5-small",
    "adaptive_allocations": {
      "enabled": true,
      "min_number_of_allocations": 1
    }
  }
}

POST _inference/text_embedding/my_e5_model
{
  "input": "my awesome piece of text"
}

POST _ml/trained_models/.multilingual-e5-small/deployment/_start

PUT bbq-my-byte-quantized-index
{
  "mappings": {
    "properties": {
      "my_field": {
        "type": "text"
      },
      "my_vector": {
        "type": "dense_vector",
        "dims": 384,
        "index_options": {
          "type": "bbq_hnsw"
        }
      }
    }
  }
}

PUT _ingest/pipeline/my_inference_pipeline
{
  "processors": [
    {
      "inference": {
        "model_id": "my_e5_model",
        "input_output": [
          {
            "input_field": "my_field",
            "output_field": "my_vector"
          }
        ]
      }
    }
  ]
}

POST _ingest/pipeline/my_inference_pipeline/_simulate
{
  "docs": [
    {
      "_source": {
        "my_field": "my awesome text field"
      }
    }
  ]
}

PUT bbq-my-byte-quantized-index/_doc/1?pipeline=my_inference_pipeline
{
    "my_field": "my awesome text field"
}

PUT bbq-my-byte-quantized-index/_doc/2?pipeline=my_inference_pipeline
{
    "my_field": "some other sentence"
}

GET bbq-my-byte-quantized-index/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "knn": {
            "field": "my_vector",
            "query_vector_builder": {
              "text_embedding": {
                "model_id": "my_e5_model",
                "model_text": "my awesome search field"
              }
            },
            "k": 10,
            "num_candidates": 100
          }
        }
      ]
    }
  },
  "_source": [
    "my_field"
  ]
}

GET bbq-my-byte-quantized-index/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "knn": {
            "field": "my_vector",
            "query_vector_builder": {
              "text_embedding": {
                "model_id": "my_e5_model",
                "model_text": "my awesome search field"
              }
            },
            "rescore_vector": {
              "oversample": 3
            },
            "k": 10,
            "num_candidates": 100
          }
        }
      ]
    }
  },
  "_source": [
    "my_field"
  ]
}

PUT my-raw-vector-index
{
  "mappings": {
    "properties": {
      "my_field": {
        "type": "text"
      },
      "my_vector": {
        "type": "dense_vector",
        "dims": 384,
        "index_options": {
          "type": "hnsw"
        }
      }
    }
  }
}

PUT my-raw-vector-index/_doc/1?pipeline=my_inference_pipeline
{
    "my_field": "my awesome text field"
}

PUT my-raw-vector-index/_doc/2?pipeline=my_inference_pipeline
{
    "my_field": "some other sentence"
}

GET my-raw-vector-index/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "knn": {
            "field": "my_vector",
            "query_vector_builder": {
              "text_embedding": {
                "model_id": "my_e5_model",
                "model_text": "my awesome search field"
              }
            },
            "k": 10,
            "num_candidates": 100
          }
        }
      ]
    }
  },
  "_source": [
    "my_field"
  ]
}