The semantic_text field type automatically generates embeddings for text content using an inference endpoint.

The semantic_text field type specifies an inference endpoint identifier that will be used to generate embeddings. You can create the inference endpoint by using the Create inference API. This field type and the semantic query type make it simpler to perform semantic search on your data.

Using semantic_text, you won’t need to specify how to generate embeddings for your data, or how to index it. The inference endpoint automatically determines the embedding generation, indexing, and query to use.

PUT my-index-000001
{
  "mappings": {
    "properties": {
      "inference_field": {
        "type": "semantic_text",
        "inference_id": "my-elser-endpoint"
      }
    }
  }
}

Parameters for semantic_text fieldsedit

Inference endpoint validationedit

The inference_id will not be validated when the mapping is created, but when documents are ingested into the index. When the first document is indexed, the inference_id will be used to generate underlying indexing structures for the field.

Automatic text chunkingedit

Inference endpoints have a limit on the amount of text they can process. To allow for large amounts of text to be used in semantic search, semantic_text automatically generates smaller passages if needed, called chunks.

Each chunk will include the text subpassage and the corresponding embedding generated from it. When querying, the individual passages will be automatically searched for each document, and the most relevant passage will be used to compute a score.

semantic_text structureedit

Once a document is ingested, a semantic_text field will have the following structure:

"inference_field": {
  "text": "these are not the droids you're looking for", 
  "inference": {
    "inference_id": "my-elser-endpoint", 
    "model_settings": { 
      "task_type": "sparse_embedding"
    },
    "chunks": [ 
      {
        "text": "these are not the droids you're looking for",
        "embeddings": {
          (...)
        }
      }
    ]
  }
}

Refer to this tutorial to learn more about semantic search using semantic_text and the semantic query.

Customizing semantic_text indexingedit

semantic_text uses defaults for indexing data based on the inference endpoint specified. It enables you to quickstart your semantic search by providing automatic inference and a dedicated query so you don’t need to provide further details.

In case you want to customize data indexing, use the sparse_vector or dense_vector field types and create an ingest pipeline with an inference processor to generate the embeddings. This tutorial walks you through the process.

Updates to semantic_text fieldsedit

Updates that use scripts are not supported when the index contains a semantic_text field.

copy_to supportedit

The semantic_text field type can be the target of copy_to fields. This means you can use a single semantic_text field to collect the values of other fields for semantic search. Each value has its embeddings calculated separately; each field value is a separate set of chunk(s) in the resulting embeddings.

This imposes a restriction on bulk updates to documents with semantic_text. In bulk requests, all fields that are copied to a semantic_text field must have a value to ensure every embedding is calculated correctly.