@elastic/schemas 0.5.1 → 0.6.0

package/src/es/json/inference.put_amazonbedrock.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonbedrock","description":"Create an Amazon Bedrock inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazonbedrock` service.\n\n>info\n> You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys.","x-api":{"id":"inference.put_amazonbedrock","name":"put-amazonbedrock","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{amazonbedrock_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{amazonbedrock_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `chat_completion` and `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockServiceType","description":"The type of service supported for the specified task type. In this case, `amazonbedrock`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `amazonbedrock` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonbedrock_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","amazonbedrock_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonbedrock","description":"Create an Amazon Bedrock inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazonbedrock` service.\n\n>info\n> 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.","x-api":{"id":"inference.put_amazonbedrock","name":"put-amazonbedrock","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{amazonbedrock_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{amazonbedrock_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `chat_completion` and `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockServiceType","description":"The type of service supported for the specified task type. In this case, `amazonbedrock`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `amazonbedrock` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonBedrockTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonbedrock_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","amazonbedrock_inference_id","service","service_settings"]}

package/src/es/json/inference.put_amazonsagemaker.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonsagemaker","description":"Create an Amazon SageMaker inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazon_sagemaker` service.","x-api":{"id":"inference.put_amazonsagemaker","name":"put-amazonsagemaker","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{amazonsagemaker_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{amazonsagemaker_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.1.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` or `text_embedding` task types.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerServiceType","description":"The type of service supported for the specified task type. In this case, `amazon_sagemaker`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `amazon_sagemaker` service and `service_settings.api` you specified.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type and `service_settings.api` you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeAmazonSageMaker","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonsagemaker_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","amazonsagemaker_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonsagemaker","description":"Create an Amazon SageMaker inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazon_sagemaker` service.","x-api":{"id":"inference.put_amazonsagemaker","name":"put-amazonsagemaker","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{amazonsagemaker_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{amazonsagemaker_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.1.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` or `text_embedding` task types.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerServiceType","description":"The type of service supported for the specified task type. In this case, `amazon_sagemaker`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `amazon_sagemaker` service and `service_settings.api` you specified.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AmazonSageMakerTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type and `service_settings.api` you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeAmazonSageMaker","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonsagemaker_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","amazonsagemaker_inference_id","service","service_settings"]}

package/src/es/json/inference.put_anthropic.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_anthropic","description":"Create an Anthropic inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `anthropic` service.","x-api":{"id":"inference.put_anthropic","name":"put-anthropic","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{anthropic_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{anthropic_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.16.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicServiceType","description":"The type of service supported for the specified task type. In this case, `anthropic`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `anthropic` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicTaskType","description":"The task type.\nThe valid task types for the model to perform are `completion` and `chat_completion`.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"anthropic_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","anthropic_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_anthropic","description":"Create an Anthropic inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `anthropic` service.","x-api":{"id":"inference.put_anthropic","name":"put-anthropic","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{anthropic_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{anthropic_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.16.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicServiceType","description":"The type of service supported for the specified task type. In this case, `anthropic`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `anthropic` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AnthropicTaskType","description":"The task type.\nThe valid task types for the model to perform are `completion` and `chat_completion`.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"anthropic_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","anthropic_inference_id","service","service_settings"]}

package/src/es/json/inference.put_azureaistudio.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureaistudio","description":"Create an Azure AI studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureaistudio` service.","x-api":{"id":"inference.put_azureaistudio","name":"put-azureaistudio","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{azureaistudio_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{azureaistudio_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.14.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` or `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioServiceType","description":"The type of service supported for the specified task type. In this case, `azureaistudio`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `azureaistudio` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"azureaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","azureaistudio_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureaistudio","description":"Create an Azure AI studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureaistudio` service.","x-api":{"id":"inference.put_azureaistudio","name":"put-azureaistudio","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{azureaistudio_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{azureaistudio_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.14.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` or `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioServiceType","description":"The type of service supported for the specified task type. In this case, `azureaistudio`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `azureaistudio` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AzureAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"azureaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","azureaistudio_inference_id","service","service_settings"]}

package/src/es/json/inference.put_azureopenai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureopenai","description":"Create an Azure OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureopenai` service.\n\nThe list of chat completion models that you can choose from in your Azure OpenAI deployment include:\n\n* [GPT-4 and GPT-4 Turbo models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-4-and-gpt-4-turbo-models)\n* [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-35)\n\nThe list of embeddings models that you can choose from in your deployment can be found in the [Azure models documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#embeddings).","x-api":{"id":"inference.put_azureopenai","name":"put-azureopenai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{azureopenai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{azureopenai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.14.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` and `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAIServiceType","description":"The type of service supported for the specified task type. In this case, `azureopenai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `azureopenai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAITaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"azureopenai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","azureopenai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureopenai","description":"Create an Azure OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureopenai` service.\n\nThe list of chat completion models that you can choose from in your Azure OpenAI deployment include:\n\n* [GPT-4 and GPT-4 Turbo models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-4-and-gpt-4-turbo-models)\n* [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-35)\n\nThe 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).","x-api":{"id":"inference.put_azureopenai","name":"put-azureopenai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{azureopenai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{azureopenai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.14.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` and `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAIServiceType","description":"The type of service supported for the specified task type. In this case, `azureopenai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `azureopenai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AzureOpenAITaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"azureopenai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","azureopenai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_cohere.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_cohere","description":"Create a Cohere inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `cohere` service.","x-api":{"id":"inference.put_cohere","name":"put-cohere","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{cohere_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{cohere_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.13.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` or `completion` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__CohereServiceType","description":"The type of service supported for the specified task type. In this case, `cohere`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CohereServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `cohere` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CohereTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__CohereTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"cohere_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","cohere_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_cohere","description":"Create a Cohere inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `cohere` service.","x-api":{"id":"inference.put_cohere","name":"put-cohere","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{cohere_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{cohere_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.13.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` or `completion` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__CohereServiceType","description":"The type of service supported for the specified task type. In this case, `cohere`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CohereServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `cohere` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CohereTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__CohereTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"cohere_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","cohere_inference_id","service","service_settings"]}

package/src/es/json/inference.put_contextualai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_contextualai","description":"Create an Contextual AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `contexualai` service.\n\nTo review the available `rerank` models, refer to <https://docs.contextual.ai/api-reference/rerank/rerank#body-model>.","x-api":{"id":"inference.put_contextualai","name":"put-contextualai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{contextualai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{contextualai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.2.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAIServiceType","description":"The type of service supported for the specified task type. In this case, `contextualai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `contextualai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeContextualAI","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"contextualai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","contextualai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_contextualai","description":"Create an Contextual AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `contexualai` service.\n\nTo review the available `rerank` models, refer to <https://docs.contextual.ai/api-reference/rerank/rerank#body-model>.","x-api":{"id":"inference.put_contextualai","name":"put-contextualai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{contextualai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{contextualai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.2.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAIServiceType","description":"The type of service supported for the specified task type. In this case, `contextualai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `contextualai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ContextualAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeContextualAI","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"contextualai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","contextualai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_custom.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","description":"Create a custom inference endpoint.\n\nThe custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations.\nThe custom service gives you the ability to define the headers, url, query parameters, request body, and secrets.\nThe custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key.\nTemplates are portions of a string that start with `${` and end with `}`.\nThe parameters `secret_parameters` and `task_settings` are checked for keys for template replacement. Template replacement is supported in the `request`, `headers`, `url`, and `query_parameters`.\nIf the definition (key) is not found for a template, an error message is returned.\nIn case of an endpoint definition like the following:\n```\nPUT _inference/text_embedding/test-text-embedding\n{\n  \"service\": \"custom\",\n  \"service_settings\": {\n     \"secret_parameters\": {\n          \"api_key\": \"<some api key>\"\n     },\n     \"url\": \"...endpoints.huggingface.cloud/v1/embeddings\",\n     \"headers\": {\n         \"Authorization\": \"Bearer ${api_key}\",\n         \"Content-Type\": \"application/json\"\n     },\n     \"request\": \"{\\\"input\\\": ${input}}\",\n     \"response\": {\n         \"json_parser\": {\n             \"text_embeddings\":\"$.data[*].embedding[*]\"\n         }\n     }\n  }\n}\n```\nTo replace `${api_key}` the `secret_parameters` and `task_settings` are checked for a key named `api_key`.\n\n> info\n> Templates should not be surrounded by quotes.\n\nPre-defined templates:\n* `${input}` refers to the array of input strings that comes from the `input` field of the subsequent inference requests.\n* `${input_type}` refers to the input type translation values.\n* `${query}` refers to the query field used specifically for reranking tasks.\n* `${top_n}` refers to the `top_n` field available when performing rerank requests.\n* `${return_documents}` refers to the `return_documents` field available when performing rerank requests.","x-api":{"id":"inference.put_custom","name":"put-custom","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{custom_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{custom_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.19.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` or `text_embedding` task types.\nNot applicable to the `rerank` or `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__CustomServiceType","description":"The type of service supported for the specified task type. In this case, `custom`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CustomServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `custom` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CustomTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__CustomTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"custom_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","custom_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","description":"Create a custom inference endpoint.\n\nThe custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations.\nThe custom service gives you the ability to define the headers, url, query parameters, request body, and secrets.\nThe custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key.\nTemplates are portions of a string that start with `${` and end with `}`.\nThe parameters `secret_parameters` and `task_settings` are checked for keys for template replacement. Template replacement is supported in the `request`, `headers`, `url`, and `query_parameters`.\nIf the definition (key) is not found for a template, an error message is returned.\nIn case of an endpoint definition like the following:\n```\nPUT _inference/text_embedding/test-text-embedding\n{\n  \"service\": \"custom\",\n  \"service_settings\": {\n     \"secret_parameters\": {\n          \"api_key\": \"<some api key>\"\n     },\n     \"url\": \"...endpoints.huggingface.cloud/v1/embeddings\",\n     \"headers\": {\n         \"Authorization\": \"Bearer ${api_key}\",\n         \"Content-Type\": \"application/json\"\n     },\n     \"request\": \"{\\\"input\\\": ${input}}\",\n     \"response\": {\n         \"json_parser\": {\n             \"text_embeddings\":\"$.data[*].embedding[*]\"\n         }\n     }\n  }\n}\n```\nTo replace `${api_key}` the `secret_parameters` and `task_settings` are checked for a key named `api_key`.\n\n> info\n> Templates should not be surrounded by quotes.\n\nPre-defined templates:\n* `${input}` refers to the array of input strings that comes from the `input` field of the subsequent inference requests.\n* `${input_type}` refers to the input type translation values.\n* `${query}` refers to the query field used specifically for reranking tasks.\n* `${top_n}` refers to the `top_n` field available when performing rerank requests.\n* `${return_documents}` refers to the `return_documents` field available when performing rerank requests.","x-api":{"id":"inference.put_custom","name":"put-custom","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{custom_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{custom_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.19.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` or `text_embedding` task types.\nNot applicable to the `rerank` or `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__CustomServiceType","description":"The type of service supported for the specified task type. In this case, `custom`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CustomServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `custom` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__CustomTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__CustomTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"custom_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","custom_inference_id","service","service_settings"]}

package/src/es/json/inference.put_deepseek.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_deepseek","description":"Create a DeepSeek inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `deepseek` service.","x-api":{"id":"inference.put_deepseek","name":"put-deepseek","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{deepseek_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{deepseek_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.1.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__DeepSeekServiceType","description":"The type of service supported for the specified task type. In this case, `deepseek`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__DeepSeekServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `deepseek` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeDeepSeek","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"deepseek_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","deepseek_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_deepseek","description":"Create a DeepSeek inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `deepseek` service.","x-api":{"id":"inference.put_deepseek","name":"put-deepseek","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{deepseek_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{deepseek_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.1.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__DeepSeekServiceType","description":"The type of service supported for the specified task type. In this case, `deepseek`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__DeepSeekServiceSettings","description":"Settings used to install the inference model.\nThese settings are specific to the `deepseek` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskTypeDeepSeek","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"deepseek_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","deepseek_inference_id","service","service_settings"]}

package/src/es/json/inference.put_elasticsearch.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elasticsearch","description":"Create an Elasticsearch inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elasticsearch` service.\n\n> info\n> Your Elasticsearch deployment contains preconfigured ELSER and E5 inference endpoints, you only need to create the enpoints using the API if you want to customize the settings.\n\nIf you use the ELSER or the E5 model through the `elasticsearch` service, the API request will automatically download and deploy the model if it isn't downloaded yet.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_elasticsearch","name":"put-elasticsearch","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{elasticsearch_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{elasticsearch_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.13.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` and `text_embedding` task types.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchServiceType","description":"The type of service supported for the specified task type. In this case, `elasticsearch`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `elasticsearch` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elasticsearch_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.\nThe must not match the `model_id`.","x-found-in":"path"}},"required":["task_type","elasticsearch_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elasticsearch","description":"Create an Elasticsearch inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elasticsearch` service.\n\n> info\n> Your Elasticsearch deployment contains preconfigured ELSER and E5 inference endpoints, you only need to create the enpoints using the API if you want to customize the settings.\n\nIf you use the ELSER or the E5 model through the `elasticsearch` service, the API request will automatically download and deploy the model if it isn't downloaded yet.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_elasticsearch","name":"put-elasticsearch","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{elasticsearch_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{elasticsearch_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.13.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` and `text_embedding` task types.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchServiceType","description":"The type of service supported for the specified task type. In this case, `elasticsearch`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `elasticsearch` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__ElasticsearchTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elasticsearch_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.\nThe must not match the `model_id`.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","elasticsearch_inference_id","service","service_settings"]}

package/src/es/json/inference.put_elser.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elser","description":"Create an ELSER inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elser` service.\nYou can also deploy ELSER by using the Elasticsearch inference integration.\n\n> info\n> Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.\n\nThe API request will automatically download and deploy the ELSER model if it isn't already downloaded.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_elser","name":"put-elser","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{elser_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{elser_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.11.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"x-deprecated":{"since":"8.16.0","description":"The elser service is deprecated and will be removed in a future release. Use the Elasticsearch inference integration instead, with model_id included in the service_settings."},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nNote that for ELSER endpoints, the max_chunk_size may not exceed `300`.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ElserServiceType","description":"The type of service supported for the specified task type. In this case, `elser`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElserServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `elser` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__ElserTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elser_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","elser_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elser","description":"Create an ELSER inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elser` service.\nYou can also deploy ELSER by using the Elasticsearch inference integration.\n\n> info\n> Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.\n\nThe API request will automatically download and deploy the ELSER model if it isn't already downloaded.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_elser","name":"put-elser","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{elser_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{elser_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.11.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"x-deprecated":{"since":"8.16.0","description":"The elser service is deprecated and will be removed in a future release. Use the Elasticsearch inference integration instead, with model_id included in the service_settings."},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nNote that for ELSER endpoints, the max_chunk_size may not exceed `300`.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__ElserServiceType","description":"The type of service supported for the specified task type. In this case, `elser`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__ElserServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `elser` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__ElserTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elser_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","elser_inference_id","service","service_settings"]}

package/src/es/json/inference.put_fireworksai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_fireworksai","description":"Create a Fireworks AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `fireworksai` service.","x-api":{"id":"inference.put_fireworksai","name":"put-fireworksai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{fireworksai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{fireworksai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.4.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAIServiceType","description":"The type of service supported for the specified task type. In this case, `fireworksai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `fireworksai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAITaskSettings","description":"Settings to configure the inference task.\nApplies only to the `completion` or `chat_completion` task types.\nNot applicable to the `text_embedding` task type.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"fireworksai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","fireworksai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_fireworksai","description":"Create a Fireworks AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `fireworksai` service.","x-api":{"id":"inference.put_fireworksai","name":"put-fireworksai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{fireworksai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{fireworksai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.4.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAIServiceType","description":"The type of service supported for the specified task type. In this case, `fireworksai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `fireworksai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAITaskSettings","description":"Settings to configure the inference task.\nApplies only to the `completion` or `chat_completion` task types.\nNot applicable to the `text_embedding` task type.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__FireworksAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"fireworksai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","fireworksai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_googleaistudio.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googleaistudio","description":"Create an Google AI Studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googleaistudio` service.","x-api":{"id":"inference.put_googleaistudio","name":"put-googleaistudio","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{googleaistudio_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{googleaistudio_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiServiceType","description":"The type of service supported for the specified task type. In this case, `googleaistudio`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiStudioServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `googleaistudio` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googleaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","googleaistudio_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googleaistudio","description":"Create an Google AI Studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googleaistudio` service.","x-api":{"id":"inference.put_googleaistudio","name":"put-googleaistudio","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{googleaistudio_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{googleaistudio_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiServiceType","description":"The type of service supported for the specified task type. In this case, `googleaistudio`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiStudioServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `googleaistudio` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googleaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","googleaistudio_inference_id","service","service_settings"]}

package/src/es/json/inference.put_googlevertexai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googlevertexai","description":"Create a Google Vertex AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googlevertexai` service.","x-api":{"id":"inference.put_googlevertexai","name":"put-googlevertexai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{googlevertexai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{googlevertexai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAIServiceType","description":"The type of service supported for the specified task type. In this case, `googlevertexai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `googlevertexai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googlevertexai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","googlevertexai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googlevertexai","description":"Create a Google Vertex AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googlevertexai` service.","x-api":{"id":"inference.put_googlevertexai","name":"put-googlevertexai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{googlevertexai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{googlevertexai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAIServiceType","description":"The type of service supported for the specified task type. In this case, `googlevertexai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `googlevertexai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GoogleVertexAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googlevertexai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","googlevertexai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_groq.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_groq","description":"Create a Groq inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `groq` service.","x-api":{"id":"inference.put_groq","name":"put-groq","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{groq_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{groq_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GroqServiceType","description":"The type of service supported for the specified task type. In this case, `groq`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GroqServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `groq` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GroqTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"groq_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","groq_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_groq","description":"Create a Groq inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `groq` service.","x-api":{"id":"inference.put_groq","name":"put-groq","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{groq_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{groq_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__GroqServiceType","description":"The type of service supported for the specified task type. In this case, `groq`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__GroqServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `groq` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__GroqTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"groq_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","groq_inference_id","service","service_settings"]}

package/src/es/json/inference.put_hugging_face.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_hugging_face","description":"Create a Hugging Face inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `hugging_face` service.\nSupported tasks include: `text_embedding`, `completion`, and `chat_completion`.\n\nTo configure the endpoint, first visit the Hugging Face Inference Endpoints page and create a new endpoint.\nSelect a model that supports the task you intend to use.\n\nFor Elastic's `text_embedding` task:\nThe selected model must support the `Sentence Embeddings` task. On the new endpoint creation page, select the `Sentence Embeddings` task under the `Advanced Configuration` section.\nAfter the endpoint has initialized, copy the generated endpoint URL.\nRecommended models for `text_embedding` task:\n\n* `all-MiniLM-L6-v2`\n* `all-MiniLM-L12-v2`\n* `all-mpnet-base-v2`\n* `e5-base-v2`\n* `e5-small-v2`\n* `multilingual-e5-base`\n* `multilingual-e5-small`\n\nFor Elastic's `chat_completion` and `completion` tasks:\nThe selected model must support the `Text Generation` task and expose OpenAI API. HuggingFace supports both serverless and dedicated endpoints for `Text Generation`. When creating dedicated endpoint select the `Text Generation` task.\nAfter the endpoint is initialized (for dedicated) or ready (for serverless), ensure it supports the OpenAI API and includes `/v1/chat/completions` part in URL. Then, copy the full endpoint URL for use.\nRecommended models for `chat_completion` and `completion` tasks:\n\n* `Mistral-7B-Instruct-v0.2`\n* `QwQ-32B`\n* `Phi-3-mini-128k-instruct`\n\nFor Elastic's `rerank` task:\nThe selected model must support the `sentence-ranking` task and expose OpenAI API.\nHuggingFace supports only dedicated (not serverless) endpoints for `Rerank` so far.\nAfter the endpoint is initialized, copy the full endpoint URL for use.\nTested models for `rerank` task:\n\n* `bge-reranker-base`\n* `jina-reranker-v1-turbo-en-GGUF`","x-api":{"id":"inference.put_hugging_face","name":"put-hugging-face","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{huggingface_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{huggingface_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceServiceType","description":"The type of service supported for the specified task type. In this case, `hugging_face`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `hugging_face` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"huggingface_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","huggingface_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_hugging_face","description":"Create a Hugging Face inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `hugging_face` service.\nSupported tasks include: `text_embedding`, `completion`, and `chat_completion`.\n\nTo configure the endpoint, first visit the Hugging Face Inference Endpoints page and create a new endpoint.\nSelect a model that supports the task you intend to use.\n\nFor Elastic's `text_embedding` task:\nThe selected model must support the `Sentence Embeddings` task. On the new endpoint creation page, select the `Sentence Embeddings` task under the `Advanced Configuration` section.\nAfter the endpoint has initialized, copy the generated endpoint URL.\nRecommended models for `text_embedding` task:\n\n* `all-MiniLM-L6-v2`\n* `all-MiniLM-L12-v2`\n* `all-mpnet-base-v2`\n* `e5-base-v2`\n* `e5-small-v2`\n* `multilingual-e5-base`\n* `multilingual-e5-small`\n\nFor Elastic's `chat_completion` and `completion` tasks:\nThe selected model must support the `Text Generation` task and expose OpenAI API. HuggingFace supports both serverless and dedicated endpoints for `Text Generation`. When creating dedicated endpoint select the `Text Generation` task.\nAfter the endpoint is initialized (for dedicated) or ready (for serverless), ensure it supports the OpenAI API and includes `/v1/chat/completions` part in URL. Then, copy the full endpoint URL for use.\nRecommended models for `chat_completion` and `completion` tasks:\n\n* `Mistral-7B-Instruct-v0.2`\n* `QwQ-32B`\n* `Phi-3-mini-128k-instruct`\n\nFor Elastic's `rerank` task:\nThe selected model must support the `sentence-ranking` task and expose OpenAI API.\nHuggingFace supports only dedicated (not serverless) endpoints for `Rerank` so far.\nAfter the endpoint is initialized, copy the full endpoint URL for use.\nTested models for `rerank` task:\n\n* `bge-reranker-base`\n* `jina-reranker-v1-turbo-en-GGUF`","x-api":{"id":"inference.put_hugging_face","name":"put-hugging-face","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{huggingface_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{huggingface_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceServiceType","description":"The type of service supported for the specified task type. In this case, `hugging_face`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `hugging_face` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__HuggingFaceTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"huggingface_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","huggingface_inference_id","service","service_settings"]}

package/src/es/json/inference.put_jinaai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_jinaai","description":"Create an JinaAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `jinaai` service.\n\nTo review the available `rerank` models, refer to <https://jina.ai/reranker>.\nTo review the available `embedding` and `text_embedding` models, refer to <https://jina.ai/embeddings/>.","x-api":{"id":"inference.put_jinaai","name":"put-jinaai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{jinaai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{jinaai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.18.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `embedding` and text_embedding` task types.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAIServiceType","description":"The type of service supported for the specified task type. In this case, `jinaai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `jinaai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"jinaai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","jinaai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_jinaai","description":"Create an JinaAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `jinaai` service.\n\nTo review the available `rerank` models, refer to <https://jina.ai/reranker>.\nTo review the available `embedding` and `text_embedding` models, refer to <https://jina.ai/embeddings/>.","x-api":{"id":"inference.put_jinaai","name":"put-jinaai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{jinaai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{jinaai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.18.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `embedding` and text_embedding` task types.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAIServiceType","description":"The type of service supported for the specified task type. In this case, `jinaai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `jinaai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__JinaAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"jinaai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","jinaai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_llama.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_llama","description":"Create a Llama inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `llama` service.","x-api":{"id":"inference.put_llama","name":"put-llama","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{llama_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{llama_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.2.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaServiceType","description":"The type of service supported for the specified task type. In this case, `llama`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `llama` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"llama_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","llama_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_llama","description":"Create a Llama inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `llama` service.","x-api":{"id":"inference.put_llama","name":"put-llama","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{llama_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{llama_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.2.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaServiceType","description":"The type of service supported for the specified task type. In this case, `llama`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `llama` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__LlamaTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"llama_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","llama_inference_id","service","service_settings"]}

package/src/es/json/inference.put_mistral.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_mistral","description":"Create a Mistral inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `mistral` service.","x-api":{"id":"inference.put_mistral","name":"put-mistral","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{mistral_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{mistral_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__MistralServiceType","description":"The type of service supported for the specified task type. In this case, `mistral`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__MistralServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `mistral` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__MistralTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"mistral_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","mistral_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_mistral","description":"Create a Mistral inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `mistral` service.","x-api":{"id":"inference.put_mistral","name":"put-mistral","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{mistral_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{mistral_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.15.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__MistralServiceType","description":"The type of service supported for the specified task type. In this case, `mistral`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__MistralServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `mistral` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__MistralTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"mistral_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","mistral_inference_id","service","service_settings"]}

package/src/es/json/inference.put_nvidia.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_nvidia","description":"Create an Nvidia inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `nvidia` service.","x-api":{"id":"inference.put_nvidia","name":"put-nvidia","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{nvidia_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{nvidia_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaServiceType","description":"The type of service supported for the specified task type. In this case, `nvidia`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `nvidia` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaTaskSettings","description":"Settings to configure the inference task.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaTaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"nvidia_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","nvidia_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_nvidia","description":"Create an Nvidia inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `nvidia` service.","x-api":{"id":"inference.put_nvidia","name":"put-nvidia","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{nvidia_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{nvidia_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaServiceType","description":"The type of service supported for the specified task type. In this case, `nvidia`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `nvidia` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaTaskSettings","description":"Settings to configure the inference task.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__NvidiaTaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"nvidia_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","nvidia_inference_id","service","service_settings"]}

package/src/es/json/inference.put_openai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_openai","description":"Create an OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openai` service or `openai` compatible APIs.","x-api":{"id":"inference.put_openai","name":"put-openai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{openai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{openai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAIServiceType","description":"The type of service supported for the specified task type. In this case, `openai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `openai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAITaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"openai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","openai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_openai","description":"Create an OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openai` service or `openai` compatible APIs.","x-api":{"id":"inference.put_openai","name":"put-openai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{openai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{openai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.12.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAIServiceType","description":"The type of service supported for the specified task type. In this case, `openai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `openai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__OpenAITaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"openai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","openai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_openshift_ai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_openshift_ai","description":"Create an OpenShift AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openshift_ai` service.","x-api":{"id":"inference.put_openshift_ai","name":"put-openshift-ai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{openshiftai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{openshiftai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiServiceType","description":"The type of service supported for the specified task type. In this case, `openshift_ai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `openshift_ai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiTaskSettings","description":"Settings to configure the inference task.\nApplies only to the `rerank` task type.\nNot applicable to the `text_embedding`, `completion`, or `chat_completion` task types.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiTaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"openshiftai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","openshiftai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_openshift_ai","description":"Create an OpenShift AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openshift_ai` service.","x-api":{"id":"inference.put_openshift_ai","name":"put-openshift-ai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{openshiftai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{openshiftai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.3.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion`, or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiServiceType","description":"The type of service supported for the specified task type. In this case, `openshift_ai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `openshift_ai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiTaskSettings","description":"Settings to configure the inference task.\nApplies only to the `rerank` task type.\nNot applicable to the `text_embedding`, `completion`, or `chat_completion` task types.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__OpenShiftAiTaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"openshiftai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","openshiftai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_region_policy.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_region_policy","description":"Create or update the inference region policy.\n\nThe region policy restricts inference to a set of allowed geographic areas or cloud service provider regions.","x-api":{"id":"inference.put_region_policy","name":"put-region-policy","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/_region_policy","x-urls":[{"path":"/_inference/_region_policy","methods":["PUT"]}],"x-destructive":true,"x-availability":{"stack":{"since":"9.5.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"force":{"type":"boolean","description":"If `true`, the region policy is applied even if it would deny access to inference endpoints that are currently in use by ingest pipeline or indices.","x-found-in":"query"},"region_policy":{"$ref":"./inference._types.json#/$defs/inference._types__RegionPolicy","description":"The region policy configuration.","x-found-in":"body"}},"required":["region_policy"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_region_policy","description":"Create or update the inference region policy.\n\nThe region policy restricts inference to a set of allowed geographic areas or cloud service provider regions.","x-api":{"id":"inference.put_region_policy","name":"put-region-policy","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/_region_policy","x-urls":[{"path":"/_inference/_region_policy","methods":["PUT"]}],"x-destructive":true,"x-availability":{"stack":{"since":"9.5.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"force":{"type":"boolean","description":"If `true`, the region policy is applied even if it would deny access to inference endpoints that are currently in use by ingest pipeline or indices.","x-found-in":"query"},"region_policy":{"$ref":"./inference._types.json#/$defs/inference._types__RegionPolicy","description":"The region policy configuration.","x-found-in":"body"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["region_policy"]}

package/src/es/json/inference.put_voyageai.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_voyageai","description":"Create a VoyageAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `voyageai` service.\n\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_voyageai","name":"put-voyageai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{voyageai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{voyageai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.19.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAIServiceType","description":"The type of service supported for the specified task type. In this case, `voyageai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `voyageai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"voyageai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","voyageai_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_voyageai","description":"Create a VoyageAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `voyageai` service.\n\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.","x-api":{"id":"inference.put_voyageai","name":"put-voyageai","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{voyageai_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{voyageai_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.19.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank` task type.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAIServiceType","description":"The type of service supported for the specified task type. In this case, `voyageai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAIServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `voyageai` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAITaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__VoyageAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"voyageai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","voyageai_inference_id","service","service_settings"]}

package/src/es/json/inference.put_watsonx.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_watsonx","description":"Create a Watsonx inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `watsonxai` service.\nYou need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service.\nYou can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.","x-api":{"id":"inference.put_watsonx","name":"put-watsonx","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{watsonx_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{watsonx_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.16.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxServiceType","description":"The type of service supported for the specified task type. In this case, `watsonxai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `watsonxai` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"watsonx_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","watsonx_inference_id","service","service_settings"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_watsonx","description":"Create a Watsonx inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `watsonxai` service.\nYou need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service.\nYou can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.","x-api":{"id":"inference.put_watsonx","name":"put-watsonx","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{watsonx_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{watsonx_inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.16.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.","x-found-in":"query"},"chunking_settings":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `text_embedding` task type.\nNot applicable to the `rerank`, `completion` or `chat_completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxServiceType","description":"The type of service supported for the specified task type. In this case, `watsonxai`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `watsonxai` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__WatsonxTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"watsonx_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"},"error_trace":{"type":"boolean","description":"When set to `true` Elasticsearch will include the full stack trace of errors\nwhen they occur.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"filter_path":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Comma-separated list of filters in dot notation which reduce the response\nreturned by Elasticsearch.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"human":{"type":"boolean","description":"When set to `true` will return statistics in a format suitable for humans.\nFor example `\"exists_time\": \"1h\"` for humans and\n`\"exists_time_in_millis\": 3600000` for computers. When disabled the human\nreadable values will be omitted. This makes sense for responses being consumed\nonly by machines.","x-found-in":"query","x-behavior":"CommonQueryParameters"},"pretty":{"type":"boolean","description":"If set to `true` the returned JSON will be \"pretty-formatted\". Only use\nthis option for debugging only.","x-found-in":"query","x-behavior":"CommonQueryParameters"}},"required":["task_type","watsonx_inference_id","service","service_settings"]}