stack es inference cli namespace

elastic stack es inference --help
		

Elasticsearch inference API commands

chat-completion-unified

Perform chat completion inference on the service.

completion

Perform completion inference on the service.

delete

Delete an inference endpoint.

delete-region-policy

Delete the inference region policy.

embedding

Perform dense embedding inference on the service.

get

Get an inference endpoint.

get-region-policy

Get the inference region policy.

inference

Perform inference on the service.

put

Create an inference endpoint.

put-ai21

Create a AI21 inference endpoint.

put-alibabacloud

Create an AlibabaCloud AI Search inference endpoint.

put-amazonbedrock

Create an Amazon Bedrock inference endpoint.

put-amazonsagemaker

Create an Amazon SageMaker inference endpoint.

put-anthropic

Create an Anthropic inference endpoint.

put-azureaistudio

Create an Azure AI studio inference endpoint.

put-azureopenai

Create an Azure OpenAI inference endpoint.

put-cohere

Create a Cohere inference endpoint.

put-contextualai

Create an Contextual AI inference endpoint.

put-custom

Create a custom inference endpoint.

put-deepseek

Create a DeepSeek inference endpoint.

put-elasticsearch

Create an Elasticsearch inference endpoint.

put-elser

Create an ELSER inference endpoint.

put-fireworksai

Create a Fireworks AI inference endpoint.

put-googleaistudio

Create an Google AI Studio inference endpoint.

put-googlevertexai

Create a Google Vertex AI inference endpoint.

put-groq

Create a Groq inference endpoint.

put-hugging-face

Create a Hugging Face inference endpoint.

put-jinaai

Create an JinaAI inference endpoint.

put-llama

Create a Llama inference endpoint.

put-mistral

Create a Mistral inference endpoint.

put-nvidia

Create an Nvidia inference endpoint.

put-openai

Create an OpenAI inference endpoint.

put-openshift-ai

Create an OpenShift AI inference endpoint.

put-region-policy

Create or update the inference region policy.

put-voyageai

Create a VoyageAI inference endpoint.

put-watsonx

Create a Watsonx inference endpoint.

rerank

Perform reranking inference on the service.

sparse-embedding

Perform sparse embedding inference on the service.

stream-completion

Perform streaming completion inference on the service.

text-embedding

Perform text embedding inference on the service.

update

Update an inference endpoint.