Loading

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.
embedding

Perform dense embedding inference on the service.
get

Get an inference endpoint.
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-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.