OpenSearch-Docs-Cn/_query-dsl/specialized/neural-sparse.md

layout, title, parent, grand_parent, nav_order

layout	title	parent	grand_parent	nav_order
default	Neural sparse	Specialized queries	Query DSL	55

Neural sparse query

Introduced 2.11 {: .label .label-purple }

Use the neural_sparse query for vector field search in sparse neural search.

Request fields

Include the following request fields in the neural_sparse query:

"neural_sparse": {
  "<vector_field>": {
    "query_text": "<query_text>",
    "model_id": "<model_id>",
    "max_token_score": "<max_token_score>"
  }
}

The top-level vector_field specifies the vector field against which to run a search query. The following table lists the other neural_sparse query fields.

Field | Data type | Required/Optional | Description :--- | :--- | :--- query_text | String | Required | The query text from which to generate vector embeddings. model_id | String | Required | The ID of the sparse encoding model or tokenizer model that will be used to generate vector embeddings from the query text. The model must be deployed in OpenSearch before it can be used in sparse neural search. For more information, see Using custom models within OpenSearch and Semantic search. max_token_score | Float | Optional | The theoretical upper bound of the score for all tokens in the vocabulary (required for performance optimization). For OpenSearch-provided pretrained sparse embedding models, we recommend setting max_token_score to 2 for amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1 and to 3.5 for amazon/neural-sparse/opensearch-neural-sparse-encoding-v1.

Example request

GET my-nlp-index/_search
{
  "query": {
    "neural_sparse": {
      "passage_embedding": {
        "query_text": "Hi world",
        "model_id": "aP2Q8ooBpBj3wT4HVS8a",
        "max_token_score": 2
      }
    }
  }
}

{% include copy-curl.html %}