From c134c0704d74ce8ca2b93a1e7ebd39a7a522d6a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Istv=C3=A1n=20Zolt=C3=A1n=20Szab=C3=B3?= Date: Wed, 7 May 2025 09:45:42 +0200 Subject: [PATCH] Removes erroneous flavour text from PUT inference API pages. (#4357) --- specification/inference/put/PutRequest.ts | 5 ----- .../inference/put_alibabacloud/PutAlibabaCloudRequest.ts | 6 ------ .../put_amazonbedrock/PutAmazonBedrockRequest.ts | 6 ------ .../inference/put_anthropic/PutAnthropicRequest.ts | 6 ------ .../put_azureaistudio/PutAzureAiStudioRequest.ts | 6 ------ .../inference/put_azureopenai/PutAzureOpenAiRequest.ts | 6 ------ specification/inference/put_cohere/PutCohereRequest.ts | 6 ------ .../put_googleaistudio/PutGoogleAiStudioRequest.ts | 6 ------ .../put_googlevertexai/PutGoogleVertexAiRequest.ts | 6 ------ .../inference/put_hugging_face/PutHuggingFaceRequest.ts | 6 ------ specification/inference/put_jinaai/PutJinaAiRequest.ts | 6 ------ specification/inference/put_mistral/PutMistralRequest.ts | 6 ------ specification/inference/put_openai/PutOpenAiRequest.ts | 8 +------- specification/inference/put_watsonx/PutWatsonxRequest.ts | 6 ------ 14 files changed, 1 insertion(+), 84 deletions(-) diff --git a/specification/inference/put/PutRequest.ts b/specification/inference/put/PutRequest.ts index 0706189d1b..05a04d04fd 100644 --- a/specification/inference/put/PutRequest.ts +++ b/specification/inference/put/PutRequest.ts @@ -24,11 +24,6 @@ import { Id } from '@_types/common' /** * Create an inference endpoint. - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * * IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. * For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts index 1a6276a850..6ef98ec2bb 100644 --- a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts +++ b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create an AlibabaCloud AI Search inference endpoint. * * Create an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_alibabacloud * @availability stack since=8.16.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts index f755f67532..17d8060953 100644 --- a/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts +++ b/specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts @@ -34,12 +34,6 @@ import { Id } from '@_types/common' * * >info * > You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_amazonbedrock * @availability stack since=8.12.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_anthropic/PutAnthropicRequest.ts b/specification/inference/put_anthropic/PutAnthropicRequest.ts index b77de42084..81011d07eb 100644 --- a/specification/inference/put_anthropic/PutAnthropicRequest.ts +++ b/specification/inference/put_anthropic/PutAnthropicRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create an Anthropic inference endpoint. * * Create an inference endpoint to perform an inference task with the `anthropic` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_anthropic * @availability stack since=8.16.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts index 0938b0e320..3c6ff0b4fe 100644 --- a/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts +++ b/specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create an Azure AI studio inference endpoint. * * Create an inference endpoint to perform an inference task with the `azureaistudio` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_azureaistudio * @availability stack since=8.14.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts index 37094a09c7..be2eba4cf3 100644 --- a/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts +++ b/specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts @@ -38,12 +38,6 @@ import { Id } from '@_types/common' * * [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-35) * * The list of embeddings models that you can choose from in your deployment can be found in the [Azure models documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#embeddings). - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_azureopenai * @availability stack since=8.14.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_cohere/PutCohereRequest.ts b/specification/inference/put_cohere/PutCohereRequest.ts index 7ede852c87..bc2cd24f70 100644 --- a/specification/inference/put_cohere/PutCohereRequest.ts +++ b/specification/inference/put_cohere/PutCohereRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create a Cohere inference endpoint. * * Create an inference endpoint to perform an inference task with the `cohere` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_cohere * @availability stack since=8.13.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts index 87a43555e1..49e17099a0 100644 --- a/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts +++ b/specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts @@ -30,12 +30,6 @@ import { Id } from '@_types/common' * Create an Google AI Studio inference endpoint. * * Create an inference endpoint to perform an inference task with the `googleaistudio` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_googleaistudio * @availability stack since=8.15.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts index 17276aa4eb..ce3acca432 100644 --- a/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts +++ b/specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create a Google Vertex AI inference endpoint. * * Create an inference endpoint to perform an inference task with the `googlevertexai` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_googlevertexai * @availability stack since=8.15.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts index c32861e39d..8229d3c32e 100644 --- a/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts +++ b/specification/inference/put_hugging_face/PutHuggingFaceRequest.ts @@ -44,12 +44,6 @@ import { Id } from '@_types/common' * * `e5-small-v2` * * `multilingual-e5-base` * * `multilingual-e5-small` - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_hugging_face * @availability stack since=8.12.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_jinaai/PutJinaAiRequest.ts b/specification/inference/put_jinaai/PutJinaAiRequest.ts index 68cca23146..aa2da9f63a 100644 --- a/specification/inference/put_jinaai/PutJinaAiRequest.ts +++ b/specification/inference/put_jinaai/PutJinaAiRequest.ts @@ -34,12 +34,6 @@ import { Id } from '@_types/common' * * To review the available `rerank` models, refer to . * To review the available `text_embedding` models, refer to the . - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_jinaai * @availability stack since=8.18.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_mistral/PutMistralRequest.ts b/specification/inference/put_mistral/PutMistralRequest.ts index 5bd69fd21d..835e35eb25 100644 --- a/specification/inference/put_mistral/PutMistralRequest.ts +++ b/specification/inference/put_mistral/PutMistralRequest.ts @@ -30,12 +30,6 @@ import { Id } from '@_types/common' * Create a Mistral inference endpoint. * * Creates an inference endpoint to perform an inference task with the `mistral` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_mistral * @availability stack since=8.15.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_openai/PutOpenAiRequest.ts b/specification/inference/put_openai/PutOpenAiRequest.ts index e5079daeae..54d1201276 100644 --- a/specification/inference/put_openai/PutOpenAiRequest.ts +++ b/specification/inference/put_openai/PutOpenAiRequest.ts @@ -30,13 +30,7 @@ import { Id } from '@_types/common' /** * Create an OpenAI inference endpoint. * - * Create an inference endpoint to perform an inference task with the `openai` service. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. + * Create an inference endpoint to perform an inference task with the `openai` service or `openai` compatible APIs. * @rest_spec_name inference.put_openai * @availability stack since=8.12.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public diff --git a/specification/inference/put_watsonx/PutWatsonxRequest.ts b/specification/inference/put_watsonx/PutWatsonxRequest.ts index 3718ee1c94..0ed72f91aa 100644 --- a/specification/inference/put_watsonx/PutWatsonxRequest.ts +++ b/specification/inference/put_watsonx/PutWatsonxRequest.ts @@ -31,12 +31,6 @@ import { Id } from '@_types/common' * Create an inference endpoint to perform an inference task with the `watsonxai` service. * You need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service. * You can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform. - * - * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. - * After creating the endpoint, wait for the model deployment to complete before using it. - * To verify the deployment status, use the get trained model statistics API. - * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. - * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. * @rest_spec_name inference.put_watsonx * @availability stack since=8.16.0 stability=stable visibility=public * @availability serverless stability=stable visibility=public