@elastic/schemas 0.4.5 → 0.5.1

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.chat_completion_unified","type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference request to complete.","x-found-in":"query"},"chat_completion_request":{"$ref":"./inference._types.json#/$defs/inference._types__RequestChatCompletion","x-found-in":"body"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"],"description":"Perform chat completion inference on the service.\n\nThe chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation.\nIt only works with the `chat_completion` task type.\n\nNOTE: The `chat_completion` task type is only available within the _stream API and only supports streaming.\nThe Chat completion inference API and the Stream inference API differ in their response structure and capabilities.\nThe Chat completion inference API provides more comprehensive customization options through more fields and function calling support.\nTo determine whether a given inference service supports this task type, please see the page for that service."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.chat_completion_unified","description":"Perform chat completion inference on the service.\n\nThe chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation.\nIt only works with the `chat_completion` task type.\n\nNOTE: The `chat_completion` task type is only available within the _stream API and only supports streaming.\nThe Chat completion inference API and the Stream inference API differ in their response structure and capabilities.\nThe Chat completion inference API provides more comprehensive customization options through more fields and function calling support.\nTo determine whether a given inference service supports this task type, please see the page for that service.","x-api":{"id":"inference.chat_completion_unified","name":"chat-completion-unified","namespace":"inference"},"x-method":"POST","x-path":"/_inference/chat_completion/{inference_id}/_stream","x-urls":[{"path":"/_inference/chat_completion/{inference_id}/_stream","methods":["POST"]}],"x-destructive":true,"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 request to complete.","x-found-in":"query"},"chat_completion_request":{"$ref":"./inference._types.json#/$defs/inference._types__RequestChatCompletion","x-found-in":"body","x-body-root":true},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"]}

package/src/es/json/inference.chat_completion_unified.response.json

@@ -1 +1 @@
-{"type":"string","description":"base64-encoded binary","$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.chat_completion_unified"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.chat_completion_unified","description":"base64-encoded binary","x-api":{"id":"inference.chat_completion_unified","name":"chat-completion-unified","namespace":"inference"},"type":"string"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.completion","type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference request to complete.","x-found-in":"query"},"input":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Inference input.\nEither a string or an array of strings.","x-found-in":"body"},"task_settings":{"description":"Task settings for the individual inference request. These settings are specific to the <task_type> you specified and override the task settings specified when initializing the service.","x-found-in":"body"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id","input"],"description":"Perform completion inference on the service.\n\nGet responses for completion tasks.\nThis API works only with the completion task type.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.\n\nThis API requires the `monitor_inference` cluster privilege (the built-in `inference_admin` and `inference_user` roles grant this privilege)."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.completion","description":"Perform completion inference on the service.\n\nGet responses for completion tasks.\nThis API works only with the completion task type.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.\n\nThis API requires the `monitor_inference` cluster privilege (the built-in `inference_admin` and `inference_user` roles grant this privilege).","x-api":{"id":"inference.completion","name":"completion","namespace":"inference"},"x-method":"POST","x-path":"/_inference/completion/{inference_id}","x-urls":[{"path":"/_inference/completion/{inference_id}","methods":["POST"]}],"x-destructive":true,"x-availability":{"stack":{"since":"8.11.0","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 request to complete.","x-found-in":"query"},"input":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Inference input.\nEither a string or an array of strings.","x-found-in":"body"},"task_settings":{"description":"Task settings for the individual inference request. These settings are specific to the <task_type> you specified and override the task settings specified when initializing the service.","x-found-in":"body"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id","input"]}

package/src/es/json/inference.completion.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.completion","$ref":"./inference._types.json#/$defs/inference._types__CompletionInferenceResult"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.completion","x-api":{"id":"inference.completion","name":"completion","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__CompletionInferenceResult"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete","type":"object","properties":{"dry_run":{"type":"boolean","description":"When true, checks the semantic_text fields and inference processors that reference the endpoint and returns them in a list, but does not delete the endpoint.","x-found-in":"query"},"force":{"type":"boolean","description":"When true, the inference endpoint is forcefully deleted even if it is still being used by ingest processors or semantic text fields.","x-found-in":"query"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference identifier.","x-found-in":"path"}},"required":["inference_id"],"description":"Delete an inference endpoint.\n\nThis API requires the manage_inference cluster privilege (the built-in `inference_admin` role grants this privilege)."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete","description":"Delete an inference endpoint.\n\nThis API requires the manage_inference cluster privilege (the built-in `inference_admin` role grants this privilege).","x-api":{"id":"inference.delete","name":"delete","namespace":"inference"},"x-method":"DELETE","x-path":"/_inference/{task_type}/{inference_id}","x-urls":[{"path":"/_inference/{inference_id}","methods":["DELETE"]},{"path":"/_inference/{task_type}/{inference_id}","methods":["DELETE"]}],"x-destructive":true,"x-availability":{"stack":{"since":"8.11.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"dry_run":{"type":"boolean","description":"When true, checks the semantic_text fields and inference processors that reference the endpoint and returns them in a list, but does not delete the endpoint.","x-found-in":"query"},"force":{"type":"boolean","description":"When true, the inference endpoint is forcefully deleted even if it is still being used by ingest processors or semantic text fields.","x-found-in":"query"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference identifier.","x-found-in":"path"}},"required":["inference_id"]}

package/src/es/json/inference.delete.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete","$ref":"./inference._types.json#/$defs/inference._types__DeleteInferenceEndpointResult"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete","x-api":{"id":"inference.delete","name":"delete","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__DeleteInferenceEndpointResult"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete_region_policy","type":"object","properties":{},"description":"Delete the inference region policy."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete_region_policy","description":"Delete the inference region policy.","x-api":{"id":"inference.delete_region_policy","name":"delete-region-policy","namespace":"inference"},"x-method":"DELETE","x-path":"/_inference/_region_policy","x-urls":[{"path":"/_inference/_region_policy","methods":["DELETE"]}],"x-destructive":true,"x-availability":{"stack":{"since":"9.5.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{}}

package/src/es/json/inference.delete_region_policy.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete_region_policy","$ref":"./_types.json#/$defs/_types__AcknowledgedResponseBase"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.delete_region_policy","x-api":{"id":"inference.delete_region_policy","name":"delete-region-policy","namespace":"inference"},"$ref":"./_types.json#/$defs/_types__AcknowledgedResponseBase"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.embedding","type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference request to complete.","x-found-in":"query"},"embedding":{"$ref":"./inference._types.json#/$defs/inference._types__RequestEmbedding","x-found-in":"body"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"],"description":"Perform dense embedding inference on the service."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.embedding","description":"Perform dense embedding inference on the service.","x-api":{"id":"inference.embedding","name":"embedding","namespace":"inference"},"x-method":"POST","x-path":"/_inference/embedding/{inference_id}","x-urls":[{"path":"/_inference/embedding/{inference_id}","methods":["POST"]}],"x-destructive":true,"x-availability":{"stack":{"since":"9.4.0","stability":"experimental","visibility":"public"},"serverless":{"stability":"experimental","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference request to complete.","x-found-in":"query"},"embedding":{"$ref":"./inference._types.json#/$defs/inference._types__RequestEmbedding","x-found-in":"body","x-body-root":true},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"]}

package/src/es/json/inference.embedding.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.embedding","$ref":"./inference._types.json#/$defs/inference._types__EmbeddingInferenceResult"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.embedding","x-api":{"id":"inference.embedding","name":"embedding","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__EmbeddingInferenceResult"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get","type":"object","properties":{"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type of the endpoint to return","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference Id of the endpoint to return. Using `_all` or `*` will return all endpoints with the specified\n`task_type` if one is specified, or all endpoints for all task types if no `task_type` is specified","x-found-in":"path"}},"description":"Get an inference endpoint.\n\nThis API requires the `monitor_inference` cluster privilege (the built-in `inference_admin` and `inference_user` roles grant this privilege)."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get","description":"Get an inference endpoint.\n\nThis API requires the `monitor_inference` cluster privilege (the built-in `inference_admin` and `inference_user` roles grant this privilege).","x-api":{"id":"inference.get","name":"get","namespace":"inference"},"x-method":"GET","x-path":"/_inference/{task_type}/{inference_id}","x-urls":[{"path":"/_inference","methods":["GET"]},{"path":"/_inference/{inference_id}","methods":["GET"]},{"path":"/_inference/{task_type}/{inference_id}","methods":["GET"]},{"path":"/_inference/{task_type}/_all","methods":["GET"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.11.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type of the endpoint to return","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference Id of the endpoint to return. Using `_all` or `*` will return all endpoints with the specified\n`task_type` if one is specified, or all endpoints for all task types if no `task_type` is specified","x-found-in":"path"}}}

package/src/es/json/inference.get.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get","type":"object","properties":{"endpoints":{"type":"array","items":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfo"}}},"required":["endpoints"]}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get","x-api":{"id":"inference.get","name":"get","namespace":"inference"},"type":"object","properties":{"endpoints":{"type":"array","items":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfo"}}},"required":["endpoints"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get_region_policy","type":"object","properties":{},"description":"Get the inference region policy."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get_region_policy","description":"Get the inference region policy.","x-api":{"id":"inference.get_region_policy","name":"get-region-policy","namespace":"inference"},"x-method":"GET","x-path":"/_inference/_region_policy","x-urls":[{"path":"/_inference/_region_policy","methods":["GET"]}],"x-destructive":false,"x-availability":{"stack":{"since":"9.5.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{}}

package/src/es/json/inference.get_region_policy.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get_region_policy","$ref":"./inference._types.json#/$defs/inference._types__RegionPolicyDoc"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.get_region_policy","x-api":{"id":"inference.get_region_policy","name":"get-region-policy","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__RegionPolicyDoc"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.inference","type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"The amount of time to wait for the inference request to complete.","x-found-in":"query"},"query":{"type":"string","description":"The query input, which is required only for the `rerank` task.\nIt is not required for other tasks.","x-found-in":"body"},"input":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"The text on which you want to perform the inference task.\nIt can be a single string or an array.\n\n> info\n> Inference endpoints for the `completion` task type currently only support a single string as input.","x-found-in":"body"},"input_type":{"type":"string","description":"Specifies the input data type for the embedding model. The `input_type` parameter only applies to Inference Endpoints with the `embedding` or `text_embedding` task type. Possible values include:\n* `SEARCH`\n* `INGEST`\n* `CLASSIFICATION`\n* `CLUSTERING`\nNot all services support all values. Unsupported values will trigger a validation exception.\nAccepted values depend on the configured inference service, refer to the relevant service-specific documentation for more info.\n\n> info\n> The `input_type` parameter specified on the root level of the request body will take precedence over the `input_type` parameter specified in `task_settings`.","x-found-in":"body"},"task_settings":{"description":"Task settings for the individual inference request.\nThese settings are specific to the task type you specified and override the task settings specified when initializing the service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The type of inference task that the model performs.","x-found-in":"path"},"inference_id":{"type":"string","description":"The unique identifier for the inference endpoint.","x-found-in":"path"}},"required":["inference_id","input"],"description":"Perform inference on the service.\n\nThis API enables you to use machine learning models to perform specific tasks on data that you provide as an input.\nIt returns a response with the results of the tasks.\nThe inference endpoint you use can perform one specific task that has been defined when the endpoint was created with the create inference API.\n\nFor details about using this API with a service, such as Amazon Bedrock, Anthropic, or HuggingFace, refer to the service-specific documentation.\n\n> info\n> The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.inference","description":"Perform inference on the service.\n\nThis API enables you to use machine learning models to perform specific tasks on data that you provide as an input.\nIt returns a response with the results of the tasks.\nThe inference endpoint you use can perform one specific task that has been defined when the endpoint was created with the create inference API.\n\nFor details about using this API with a service, such as Amazon Bedrock, Anthropic, or HuggingFace, refer to the service-specific documentation.\n\n> info\n> The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.","x-api":{"id":"inference.inference","name":"inference","namespace":"inference"},"x-method":"POST","x-path":"/_inference/{task_type}/{inference_id}","x-urls":[{"path":"/_inference/{inference_id}","methods":["POST"]},{"path":"/_inference/{task_type}/{inference_id}","methods":["POST"]}],"x-destructive":true,"x-availability":{"stack":{"since":"8.11.0","stability":"stable","visibility":"public"},"serverless":{"stability":"stable","visibility":"public"}},"type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"The amount of time to wait for the inference request to complete.","x-found-in":"query"},"query":{"type":"string","description":"The query input, which is required only for the `rerank` task.\nIt is not required for other tasks.","x-found-in":"body"},"input":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"The text on which you want to perform the inference task.\nIt can be a single string or an array.\n\n> info\n> Inference endpoints for the `completion` task type currently only support a single string as input.","x-found-in":"body"},"input_type":{"type":"string","description":"Specifies the input data type for the embedding model. The `input_type` parameter only applies to Inference Endpoints with the `embedding` or `text_embedding` task type. Possible values include:\n* `SEARCH`\n* `INGEST`\n* `CLASSIFICATION`\n* `CLUSTERING`\nNot all services support all values. Unsupported values will trigger a validation exception.\nAccepted values depend on the configured inference service, refer to the relevant service-specific documentation for more info.\n\n> info\n> The `input_type` parameter specified on the root level of the request body will take precedence over the `input_type` parameter specified in `task_settings`.","x-found-in":"body"},"task_settings":{"description":"Task settings for the individual inference request.\nThese settings are specific to the task type you specified and override the task settings specified when initializing the service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The type of inference task that the model performs.","x-found-in":"path"},"inference_id":{"type":"string","description":"The unique identifier for the inference endpoint.","x-found-in":"path"}},"required":["inference_id","input"]}

package/src/es/json/inference.inference.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.inference","$ref":"./inference._types.json#/$defs/inference._types__InferenceResult"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.inference","x-api":{"id":"inference.inference","name":"inference","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceResult"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put","type":"object","properties":{"timeout":{"$ref":"./_types.json#/$defs/_types__Duration","description":"Specifies the amount of time to wait for the inference endpoint to be created.\nThe default depends on the task type: 120s for `completion` and `chat_completion`, and 30s for all other task types.","x-found-in":"query"},"inference_config":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpoint","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type. Refer to the integration list in the API description for the available task types.","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"],"description":"Create an inference endpoint.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.\nFor built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.\nHowever, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.\n\nThe following integrations are available through the inference API. You can find the available task types next to the integration name:\n* AI21 (`chat_completion`, `completion`)\n* AlibabaCloud AI Search (`completion`, `rerank`, `sparse_embedding`, `text_embedding`)\n* Amazon Bedrock (`chat_completion`, `completion`, `text_embedding`)\n* Amazon SageMaker (`chat_completion`, `completion`, `rerank`, `sparse_embedding`, `text_embedding`)\n* Anthropic (`chat_completion`, `completion`)\n* Azure AI Studio (`completion`, `rerank`, `text_embedding`)\n* Azure OpenAI (`chat_completion`, `completion`, `text_embedding`)\n* Cohere (`completion`, `rerank`, `text_embedding`)\n* DeepSeek (`chat_completion`, `completion`)\n* Elasticsearch (`rerank`, `sparse_embedding`, `text_embedding` - this service is for built-in models and models uploaded through Eland)\n* ELSER (`sparse_embedding`)\n* Fireworks AI (`chat_completion`, `completion`, `text_embedding`)\n* Google AI Studio (`completion`, `text_embedding`)\n* Google Vertex AI (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* Groq (`chat_completion`)\n* Hugging Face (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* JinaAI (`embedding`, `rerank`, `text_embedding`)\n* Llama (`chat_completion`, `completion`, `text_embedding`)\n* Mistral (`chat_completion`, `completion`, `text_embedding`)\n* Nvidia (`chat_completion`, `completion`, `text_embedding`, `rerank`)\n* OpenAI (`chat_completion`, `completion`, `text_embedding`)\n* OpenShift AI (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* VoyageAI (`rerank`, `text_embedding`)\n* Watsonx (`chat_completion`, `completion`, `rerank`, `text_embedding`)"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put","description":"Create an inference endpoint.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.\nFor built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.\nHowever, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.\n\nThe following integrations are available through the inference API. You can find the available task types next to the integration name:\n* AI21 (`chat_completion`, `completion`)\n* AlibabaCloud AI Search (`completion`, `rerank`, `sparse_embedding`, `text_embedding`)\n* Amazon Bedrock (`chat_completion`, `completion`, `text_embedding`)\n* Amazon SageMaker (`chat_completion`, `completion`, `rerank`, `sparse_embedding`, `text_embedding`)\n* Anthropic (`chat_completion`, `completion`)\n* Azure AI Studio (`completion`, `rerank`, `text_embedding`)\n* Azure OpenAI (`chat_completion`, `completion`, `text_embedding`)\n* Cohere (`completion`, `rerank`, `text_embedding`)\n* DeepSeek (`chat_completion`, `completion`)\n* Elasticsearch (`rerank`, `sparse_embedding`, `text_embedding` - this service is for built-in models and models uploaded through Eland)\n* ELSER (`sparse_embedding`)\n* Fireworks AI (`chat_completion`, `completion`, `text_embedding`)\n* Google AI Studio (`completion`, `text_embedding`)\n* Google Vertex AI (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* Groq (`chat_completion`)\n* Hugging Face (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* JinaAI (`embedding`, `rerank`, `text_embedding`)\n* Llama (`chat_completion`, `completion`, `text_embedding`)\n* Mistral (`chat_completion`, `completion`, `text_embedding`)\n* Nvidia (`chat_completion`, `completion`, `text_embedding`, `rerank`)\n* OpenAI (`chat_completion`, `completion`, `text_embedding`)\n* OpenShift AI (`chat_completion`, `completion`, `rerank`, `text_embedding`)\n* VoyageAI (`rerank`, `text_embedding`)\n* Watsonx (`chat_completion`, `completion`, `rerank`, `text_embedding`)","x-api":{"id":"inference.put","name":"put","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{inference_id}","x-urls":[{"path":"/_inference/{inference_id}","methods":["PUT"]},{"path":"/_inference/{task_type}/{inference_id}","methods":["PUT"]}],"x-destructive":false,"x-availability":{"stack":{"since":"8.11.0","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.\nThe default depends on the task type: 120s for `completion` and `chat_completion`, and 30s for all other task types.","x-found-in":"query"},"inference_config":{"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpoint","x-found-in":"body","x-body-root":true},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__TaskType","description":"The task type. Refer to the integration list in the API description for the available task types.","x-found-in":"path"},"inference_id":{"type":"string","description":"The inference Id","x-found-in":"path"}},"required":["inference_id"]}

package/src/es/json/inference.put.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfo"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put","x-api":{"id":"inference.put","name":"put","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfo"}

package/src/es/json/inference.put_ai21.request.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_ai21","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__Ai21ServiceType","description":"The type of service supported for the specified task type. In this case, `ai21`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__Ai21ServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `ai21` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__Ai21TaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"ai21_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","ai21_inference_id","service","service_settings"],"description":"Create a AI21 inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `ai21` service."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_ai21","description":"Create a AI21 inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `ai21` service.","x-api":{"id":"inference.put_ai21","name":"put-ai21","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{ai21_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{ai21_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__Ai21ServiceType","description":"The type of service supported for the specified task type. In this case, `ai21`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__Ai21ServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `ai21` service.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__Ai21TaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"ai21_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","ai21_inference_id","service","service_settings"]}

package/src/es/json/inference.put_ai21.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_ai21","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAi21"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_ai21","x-api":{"id":"inference.put_ai21","name":"put-ai21","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAi21"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_alibabacloud","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__InferenceChunkingSettings","description":"The chunking configuration object.\nApplies only to the `sparse_embedding` or `text_embedding` task types.\nNot applicable to the `rerank` or `completion` task types.","x-found-in":"body"},"service":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudServiceType","description":"The type of service supported for the specified task type. In this case, `alibabacloud-ai-search`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `alibabacloud-ai-search` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudTaskSettings","description":"Settings to configure the inference task.\nThese settings are specific to the task type you specified.","x-found-in":"body"},"task_type":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"alibabacloud_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","alibabacloud_inference_id","service","service_settings"],"description":"Create an AlibabaCloud AI Search inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_alibabacloud","description":"Create an AlibabaCloud AI Search inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.","x-api":{"id":"inference.put_alibabacloud","name":"put-alibabacloud","namespace":"inference"},"x-method":"PUT","x-path":"/_inference/{task_type}/{alibabacloud_inference_id}","x-urls":[{"path":"/_inference/{task_type}/{alibabacloud_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 `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__AlibabaCloudServiceType","description":"The type of service supported for the specified task type. In this case, `alibabacloud-ai-search`.","x-found-in":"body"},"service_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudServiceSettings","description":"Settings used to install the inference model. These settings are specific to the `alibabacloud-ai-search` service.","x-found-in":"body"},"task_settings":{"$ref":"./inference._types.json#/$defs/inference._types__AlibabaCloudTaskSettings","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__AlibabaCloudTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"alibabacloud_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","alibabacloud_inference_id","service","service_settings"]}

package/src/es/json/inference.put_alibabacloud.response.json

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_alibabacloud","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAlibabaCloudAI"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_alibabacloud","x-api":{"id":"inference.put_alibabacloud","name":"put-alibabacloud","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAlibabaCloudAI"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonbedrock","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__AmazonBedrockTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonbedrock_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","amazonbedrock_inference_id","service","service_settings"],"description":"Create an Amazon Bedrock inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazonbedrock` service.\n\n>info\n> You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonbedrock","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAmazonBedrock"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonbedrock","x-api":{"id":"inference.put_amazonbedrock","name":"put-amazonbedrock","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAmazonBedrock"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonsagemaker","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__TaskTypeAmazonSageMaker","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"amazonsagemaker_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","amazonsagemaker_inference_id","service","service_settings"],"description":"Create an Amazon SageMaker inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `amazon_sagemaker` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonsagemaker","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAmazonSageMaker"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_amazonsagemaker","x-api":{"id":"inference.put_amazonsagemaker","name":"put-amazonsagemaker","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAmazonSageMaker"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_anthropic","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__AnthropicTaskType","description":"The task type.\nThe valid task types for the model to perform are `completion` and `chat_completion`.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"anthropic_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","anthropic_inference_id","service","service_settings"],"description":"Create an Anthropic inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `anthropic` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_anthropic","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAnthropic"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_anthropic","x-api":{"id":"inference.put_anthropic","name":"put-anthropic","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAnthropic"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureaistudio","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__AzureAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"azureaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","azureaistudio_inference_id","service","service_settings"],"description":"Create an Azure AI studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureaistudio` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureaistudio","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAzureAIStudio"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureaistudio","x-api":{"id":"inference.put_azureaistudio","name":"put-azureaistudio","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAzureAIStudio"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureopenai","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__AzureOpenAITaskType","description":"The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.","x-found-in":"path"},"azureopenai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","azureopenai_inference_id","service","service_settings"],"description":"Create an Azure OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `azureopenai` service.\n\nThe list of chat completion models that you can choose from in your Azure OpenAI deployment include:\n\n* [GPT-4 and GPT-4 Turbo models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-4-and-gpt-4-turbo-models)\n* [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-35)\n\nThe list of embeddings models that you can choose from in your deployment can be found in the [Azure models documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#embeddings)."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureopenai","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAzureOpenAI"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_azureopenai","x-api":{"id":"inference.put_azureopenai","name":"put-azureopenai","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoAzureOpenAI"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_cohere","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__CohereTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"cohere_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","cohere_inference_id","service","service_settings"],"description":"Create a Cohere inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `cohere` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_cohere","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoCohere"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_cohere","x-api":{"id":"inference.put_cohere","name":"put-cohere","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoCohere"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_contextualai","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__TaskTypeContextualAI","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"contextualai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","contextualai_inference_id","service","service_settings"],"description":"Create an Contextual AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `contexualai` service.\n\nTo review the available `rerank` models, refer to <https://docs.contextual.ai/api-reference/rerank/rerank#body-model>."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_contextualai","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoContextualAi"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_contextualai","x-api":{"id":"inference.put_contextualai","name":"put-contextualai","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoContextualAi"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","type":"object","properties":{"chunking_settings":{"$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#/$defs/inference._types__CustomTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"custom_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","custom_inference_id","service","service_settings"],"description":"Create a custom inference endpoint.\n\nThe custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations.\nThe custom service gives you the ability to define the headers, url, query parameters, request body, and secrets.\nThe custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key.\nTemplates are portions of a string that start with `${` 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."}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","description":"Create a custom inference endpoint.\n\nThe custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations.\nThe custom service gives you the ability to define the headers, url, query parameters, request body, and secrets.\nThe custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key.\nTemplates are portions of a string that start with `${` 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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoCustom"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_custom","x-api":{"id":"inference.put_custom","name":"put-custom","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoCustom"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_deepseek","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__TaskTypeDeepSeek","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"deepseek_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","deepseek_inference_id","service","service_settings"],"description":"Create a DeepSeek inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `deepseek` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_deepseek","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoDeepSeek"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_deepseek","x-api":{"id":"inference.put_deepseek","name":"put-deepseek","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoDeepSeek"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elasticsearch","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__ElasticsearchTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elasticsearch_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.\nThe must not match the `model_id`.","x-found-in":"path"}},"required":["task_type","elasticsearch_inference_id","service","service_settings"],"description":"Create an Elasticsearch inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elasticsearch` service.\n\n> info\n> Your Elasticsearch deployment contains preconfigured ELSER and E5 inference endpoints, you only need to create the enpoints using the API if you want to customize the settings.\n\nIf you use the ELSER or the E5 model through the `elasticsearch` service, the API request will automatically download and deploy the model if it isn't downloaded yet.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elasticsearch","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoElasticsearch"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elasticsearch","x-api":{"id":"inference.put_elasticsearch","name":"put-elasticsearch","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoElasticsearch"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elser","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__ElserTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"elser_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","elser_inference_id","service","service_settings"],"description":"Create an ELSER inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `elser` service.\nYou can also deploy ELSER by using the Elasticsearch inference integration.\n\n> info\n> Your Elasticsearch deployment contains a preconfigured ELSER inference endpoint, you only need to create the enpoint using the API if you want to customize the settings.\n\nThe API request will automatically download and deploy the ELSER model if it isn't already downloaded.\n\n> info\n> You might see a 502 bad gateway error in the response when using the Kibana Console. This error usually just reflects a timeout, while the model downloads in the background. You can check the download progress in the Machine Learning UI. If using the Python client, you can set the timeout parameter to a higher value.\n\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elser","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoELSER"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_elser","x-api":{"id":"inference.put_elser","name":"put-elser","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoELSER"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_fireworksai","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__FireworksAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"fireworksai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","fireworksai_inference_id","service","service_settings"],"description":"Create a Fireworks AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `fireworksai` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_fireworksai","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoFireworksAI"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_fireworksai","x-api":{"id":"inference.put_fireworksai","name":"put-fireworksai","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoFireworksAI"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googleaistudio","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__GoogleAiStudioTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googleaistudio_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","googleaistudio_inference_id","service","service_settings"],"description":"Create an Google AI Studio inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googleaistudio` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googleaistudio","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGoogleAIStudio"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googleaistudio","x-api":{"id":"inference.put_googleaistudio","name":"put-googleaistudio","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGoogleAIStudio"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googlevertexai","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__GoogleVertexAITaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"googlevertexai_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","googlevertexai_inference_id","service","service_settings"],"description":"Create a Google Vertex AI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `googlevertexai` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googlevertexai","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGoogleVertexAI"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_googlevertexai","x-api":{"id":"inference.put_googlevertexai","name":"put-googlevertexai","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGoogleVertexAI"}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_groq","type":"object","properties":{"timeout":{"$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#/$defs/inference._types__GroqTaskType","description":"The type of the inference task that the model will perform.","x-found-in":"path"},"groq_inference_id":{"type":"string","description":"The unique identifier of the inference endpoint.","x-found-in":"path"}},"required":["task_type","groq_inference_id","service","service_settings"],"description":"Create a Groq inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `groq` service."}
+{"$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"]}

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

@@ -1 +1 @@
-{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_groq","$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGroq"}
+{"$schema":"https://json-schema.org/draft/2020-12/schema","title":"inference.put_groq","x-api":{"id":"inference.put_groq","name":"put-groq","namespace":"inference"},"$ref":"./inference._types.json#/$defs/inference._types__InferenceEndpointInfoGroq"}