Class InferenceService
java.lang.Object
org.elasticsearch.xpack.esql.inference.InferenceService
-
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final StringValue of theX-Elastic-Product-Use-Caseheader for ESQL requests. -
Constructor Summary
ConstructorsConstructorDescriptionInferenceService(Client client, ClusterService clusterService) Creates a new inference service with the given client. -
Method Summary
Modifier and TypeMethodDescriptionvoidexecuteEmbeddingInference(EmbeddingAction.Request request, ActionListener<InferenceAction.Response> listener) Executes an embedding inference request.voidexecuteInference(InferenceAction.Request request, ActionListener<InferenceAction.Response> listener) Executes a plain inference request.voidexecuteRerankInference(RerankAction.Request request, ActionListener<InferenceAction.Response> listener) Executes a rerank inference request.Returns the settings for ES|QL inference features.voidresolveInferenceIds(List<String> inferenceIds, ActionListener<InferenceResolution> listener) Resolves a list of inference deployment IDs to their metadata.
-
Field Details
-
ESQL_PRODUCT_USE_CASE
Value of theX-Elastic-Product-Use-Caseheader for ESQL requests.- See Also:
-
-
Constructor Details
-
InferenceService
Creates a new inference service with the given client.- Parameters:
client- the Elasticsearch client for inference operationsclusterService- used to read and update inference settings
-
-
Method Details
-
inferenceSettings
Returns the settings for ES|QL inference features.- Returns:
- the inference settings
-
resolveInferenceIds
public void resolveInferenceIds(List<String> inferenceIds, ActionListener<InferenceResolution> listener) Resolves a list of inference deployment IDs to their metadata.- Parameters:
inferenceIds- List of inference deployment IDs to resolvelistener- Callback to receive the resolution results
-
executeInference
public void executeInference(InferenceAction.Request request, ActionListener<InferenceAction.Response> listener) Executes a plain inference request.- Parameters:
request- the inference request to executelistener- the listener to notify upon completion
-
executeEmbeddingInference
public void executeEmbeddingInference(EmbeddingAction.Request request, ActionListener<InferenceAction.Response> listener) Executes an embedding inference request.- Parameters:
request- the embedding request to executelistener- the listener to notify upon completion
-
executeRerankInference
public void executeRerankInference(RerankAction.Request request, ActionListener<InferenceAction.Response> listener) Executes a rerank inference request.- Parameters:
request- the rerank request to executelistener- the listener to notify upon completion
-
threadPool
-
threadContext
-