The Neural Search plugin is an experimental feature. For updates on the progress of the Neural Search plugin, or if you want to leave feedback that could help improve the feature, join the discussion in the [Neural Search forum](https://forum.opensearch.org/t/feedback-neural-search-plugin-experimental-release/11501).
The OpenSearch Neural Search plugin enables the integration of machine learning (ML) language models into your search workloads. During ingestion and search, the Neural Search plugin transforms text into vectors. Then, Neural Search uses the transformed vectors in vector-based search.
The Neural Search plugin comes bundled with OpenSearch. For more information, see [Managing plugins](({{site.url}}{{site.baseurl}}/opensearch/install/plugins#managing-plugins)).
In order to ingest vectorized documents, you need to create a Neural Search _pipeline_. A pipeline consists of a series of processors that manipulate documents during ingestion, allowing the documents to be vectorized. The following API operation creates a Neural Search pipeline:
In the pipeline request body, The `text_embedding` processor, the only processor supported by Neural Search, converts a document's text to vector embeddings. `text_embedding` uses `field_map`s to determine what fields from which to generate vector embeddings and also which field to store the embedding.
model_id | string | The ID of the model that will be used in the embedding interface. The model must be indexed in OpenSearch before it can be used in Neural Search. For more information, see [Model Serving Framework]
In order to use the text embedding processor defined in your pipelines, create an index with mapping data that aligns with the maps specified in your pipeline. For example, the `output_fields` defined in the `field_map` field of your processor request must map to the k-NN vector fields with a dimension that matches the model. Similarly, the `text_fields` defined in your processor should map to the `text_fields` in your index.
The following example request creates an index that attaches to a Neural Search pipeline. Because the index maps to k-NN vector fields, the index setting field `index-knn` is set to `true`. Furthermore, `mapping` settings use [k-NN method definitions](https://opensearch.org/docs/latest/search-plugins/knn/knn-index/#method-definitions) to match the maps defined in the Neural Search pipeline.
Document ingestion is managed by OpenSearch's [Ingest API](https://opensearch.org/docs/latest/api-reference/ingest-apis/index/), similarly to other OpenSearch indexes. For example, you can ingest a document that contains the `passage_text: "Hello world"` with a simple POST method:
With the text_embedding processor in place through a Neural Search pipeline, the example indexes "Hello world" as a `text_field` and converts "Hello world" into an associated k-NN vector field.
If you want to use a language model to convert a text query into a k-NN vector query, use the `neural` query fields in your query. The neural query request fields can be used in both the [Search API](https://opensearch.org/docs/latest/search-plugins/knn/api/#search-model) and [Query DSL](https://opensearch.org/docs/latest/opensearch/query-dsl/index/).
vector_field | string | The vector field against which to run a search query.
query_text | string | The query text from which to produce queries.
model_id | string | The ID of the model that will be used in the embedding interface. The model must be indexed in OpenSearch before it can be used in Neural Search.
k | integer | The number of results the k-NN search returns.
