diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json index f0e72fea77..c1b571220a 100644 --- a/output/openapi/elasticsearch-openapi.json +++ b/output/openapi/elasticsearch-openapi.json @@ -17841,6 +17841,102 @@ "x-state": "Added in 9.0.0" } }, + "/_inference/{task_type}/{alibabacloud_inference_id}": { + "put": { + "tags": [ + "inference" + ], + "summary": "Create an AlibabaCloud AI Search inference endpoint", + "description": "Create an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "operationId": "inference-put-alibabacloud", + "parameters": [ + { + "in": "path", + "name": "task_type", + "description": "The type of the inference task that the model will perform.", + "required": true, + "deprecated": false, + "schema": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudTaskType" + }, + "style": "simple" + }, + { + "in": "path", + "name": "alibabacloud_inference_id", + "description": "The unique identifier of the inference endpoint.", + "required": true, + "deprecated": false, + "schema": { + "$ref": "#/components/schemas/_types:Id" + }, + "style": "simple" + } + ], + "requestBody": { + "content": { + "application/json": { + "schema": { + "type": "object", + "properties": { + "chunking_settings": { + "$ref": "#/components/schemas/inference._types:InferenceChunkingSettings" + }, + "service": { + "$ref": "#/components/schemas/inference.put_alibabacloud:ServiceType" + }, + "service_settings": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudServiceSettings" + }, + "task_settings": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudTaskSettings" + } + }, + "required": [ + "service", + "service_settings" + ] + }, + "examples": { + "PutAlibabaCloudRequestExample1": { + "summary": "A completion task", + "description": "Run `PUT _inference/completion/alibabacloud_ai_search_completion` to create an inference endpoint that performs a completion task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"host\" : \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-qwen-turbo\",\n \"workspace\" : \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample2": { + "summary": "A rerank task", + "description": "Run `PUT _inference/rerank/alibabacloud_ai_search_rerank` to create an inference endpoint that performs a rerank task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-bge-reranker-larger\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample3": { + "summary": "A sparse embedding task", + "description": "Run `PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse` to create an inference endpoint that performs perform a sparse embedding task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-sparse-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample4": { + "summary": "A text embedding task", + "description": "Run `PUT _inference/text_embedding/alibabacloud_ai_search_embeddings` to create an inference endpoint that performs a text embedding task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + } + } + } + } + }, + "responses": { + "200": { + "description": "", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo" + } + } + } + } + }, + "x-state": "Added in 8.16.0" + } + }, "/_inference/{task_type}/{eis_inference_id}": { "put": { "tags": [ @@ -77143,31 +77239,52 @@ "inference._types:ServiceSettings": { "type": "object" }, - "inference.put_eis:EisTaskType": { + "inference.put_alibabacloud:AlibabaCloudTaskType": { "type": "string", "enum": [ - "chat_completion" + "completion", + "rerank", + "space_embedding", + "text_embedding" ] }, - "inference.put_eis:ServiceType": { + "inference.put_alibabacloud:ServiceType": { "type": "string", "enum": [ - "elastic" + "alibabacloud-ai-search" ] }, - "inference.put_eis:EisServiceSettings": { + "inference.put_alibabacloud:AlibabaCloudServiceSettings": { "type": "object", "properties": { - "model_id": { - "description": "The name of the model to use for the inference task.", + "api_key": { + "description": "A valid API key for the AlibabaCloud AI Search API.", + "type": "string" + }, + "host": { + "externalDocs": { + "url": "https://opensearch.console.aliyun.com/cn-shanghai/rag/api-key" + }, + "description": "The name of the host address used for the inference task.\nYou can find the host address in the API keys section of the documentation.", "type": "string" }, "rate_limit": { "$ref": "#/components/schemas/inference._types:RateLimitSetting" + }, + "service_id": { + "description": "The name of the model service to use for the inference task.\nThe following service IDs are available for the `completion` task:\n\n* `ops-qwen-turbo`\n* `qwen-turbo`\n* `qwen-plus`\n* `qwen-max ÷ qwen-max-longcontext`\n\nThe following service ID is available for the `rerank` task:\n\n* `ops-bge-reranker-larger`\n\nThe following service ID is available for the `sparse_embedding` task:\n\n* `ops-text-sparse-embedding-001`\n\nThe following service IDs are available for the `text_embedding` task:\n\n`ops-text-embedding-001`\n`ops-text-embedding-zh-001`\n`ops-text-embedding-en-001`\n`ops-text-embedding-002`", + "type": "string" + }, + "workspace": { + "description": "The name of the workspace used for the inference task.", + "type": "string" } }, "required": [ - "model_id" + "api_key", + "host", + "service_id", + "workspace" ] }, "inference._types:RateLimitSetting": { @@ -77179,6 +77296,46 @@ } } }, + "inference.put_alibabacloud:AlibabaCloudTaskSettings": { + "type": "object", + "properties": { + "input_type": { + "description": "For a `sparse_embedding` or `text_embedding` task, specify the type of input passed to the model.\nValid values are:\n\n* `ingest` for storing document embeddings in a vector database.\n* `search` for storing embeddings of search queries run against a vector database to find relevant documents.", + "type": "string" + }, + "return_token": { + "description": "For a `sparse_embedding` task, it affects whether the token name will be returned in the response.\nIt defaults to `false`, which means only the token ID will be returned in the response.", + "type": "boolean" + } + } + }, + "inference.put_eis:EisTaskType": { + "type": "string", + "enum": [ + "chat_completion" + ] + }, + "inference.put_eis:ServiceType": { + "type": "string", + "enum": [ + "elastic" + ] + }, + "inference.put_eis:EisServiceSettings": { + "type": "object", + "properties": { + "model_id": { + "description": "The name of the model to use for the inference task.", + "type": "string" + }, + "rate_limit": { + "$ref": "#/components/schemas/inference._types:RateLimitSetting" + } + }, + "required": [ + "model_id" + ] + }, "inference.put_hugging_face:HuggingFaceTaskType": { "type": "string", "enum": [ diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json index b66fa9db0b..bd05933bf3 100644 --- a/output/openapi/elasticsearch-serverless-openapi.json +++ b/output/openapi/elasticsearch-serverless-openapi.json @@ -9807,6 +9807,102 @@ "x-state": "Added in 9.0.0" } }, + "/_inference/{task_type}/{alibabacloud_inference_id}": { + "put": { + "tags": [ + "inference" + ], + "summary": "Create an AlibabaCloud AI Search inference endpoint", + "description": "Create an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.", + "operationId": "inference-put-alibabacloud", + "parameters": [ + { + "in": "path", + "name": "task_type", + "description": "The type of the inference task that the model will perform.", + "required": true, + "deprecated": false, + "schema": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudTaskType" + }, + "style": "simple" + }, + { + "in": "path", + "name": "alibabacloud_inference_id", + "description": "The unique identifier of the inference endpoint.", + "required": true, + "deprecated": false, + "schema": { + "$ref": "#/components/schemas/_types:Id" + }, + "style": "simple" + } + ], + "requestBody": { + "content": { + "application/json": { + "schema": { + "type": "object", + "properties": { + "chunking_settings": { + "$ref": "#/components/schemas/inference._types:InferenceChunkingSettings" + }, + "service": { + "$ref": "#/components/schemas/inference.put_alibabacloud:ServiceType" + }, + "service_settings": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudServiceSettings" + }, + "task_settings": { + "$ref": "#/components/schemas/inference.put_alibabacloud:AlibabaCloudTaskSettings" + } + }, + "required": [ + "service", + "service_settings" + ] + }, + "examples": { + "PutAlibabaCloudRequestExample1": { + "summary": "A completion task", + "description": "Run `PUT _inference/completion/alibabacloud_ai_search_completion` to create an inference endpoint that performs a completion task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"host\" : \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-qwen-turbo\",\n \"workspace\" : \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample2": { + "summary": "A rerank task", + "description": "Run `PUT _inference/rerank/alibabacloud_ai_search_rerank` to create an inference endpoint that performs a rerank task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-bge-reranker-larger\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample3": { + "summary": "A sparse embedding task", + "description": "Run `PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse` to create an inference endpoint that performs perform a sparse embedding task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-sparse-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample4": { + "summary": "A text embedding task", + "description": "Run `PUT _inference/text_embedding/alibabacloud_ai_search_embeddings` to create an inference endpoint that performs a text embedding task.", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + } + } + } + } + }, + "responses": { + "200": { + "description": "", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo" + } + } + } + } + }, + "x-state": "Added in 8.16.0" + } + }, "/_inference/{task_type}/{eis_inference_id}": { "put": { "tags": [ @@ -48473,31 +48569,52 @@ "inference._types:ServiceSettings": { "type": "object" }, - "inference.put_eis:EisTaskType": { + "inference.put_alibabacloud:AlibabaCloudTaskType": { "type": "string", "enum": [ - "chat_completion" + "completion", + "rerank", + "space_embedding", + "text_embedding" ] }, - "inference.put_eis:ServiceType": { + "inference.put_alibabacloud:ServiceType": { "type": "string", "enum": [ - "elastic" + "alibabacloud-ai-search" ] }, - "inference.put_eis:EisServiceSettings": { + "inference.put_alibabacloud:AlibabaCloudServiceSettings": { "type": "object", "properties": { - "model_id": { - "description": "The name of the model to use for the inference task.", + "api_key": { + "description": "A valid API key for the AlibabaCloud AI Search API.", + "type": "string" + }, + "host": { + "externalDocs": { + "url": "https://opensearch.console.aliyun.com/cn-shanghai/rag/api-key" + }, + "description": "The name of the host address used for the inference task.\nYou can find the host address in the API keys section of the documentation.", "type": "string" }, "rate_limit": { "$ref": "#/components/schemas/inference._types:RateLimitSetting" + }, + "service_id": { + "description": "The name of the model service to use for the inference task.\nThe following service IDs are available for the `completion` task:\n\n* `ops-qwen-turbo`\n* `qwen-turbo`\n* `qwen-plus`\n* `qwen-max ÷ qwen-max-longcontext`\n\nThe following service ID is available for the `rerank` task:\n\n* `ops-bge-reranker-larger`\n\nThe following service ID is available for the `sparse_embedding` task:\n\n* `ops-text-sparse-embedding-001`\n\nThe following service IDs are available for the `text_embedding` task:\n\n`ops-text-embedding-001`\n`ops-text-embedding-zh-001`\n`ops-text-embedding-en-001`\n`ops-text-embedding-002`", + "type": "string" + }, + "workspace": { + "description": "The name of the workspace used for the inference task.", + "type": "string" } }, "required": [ - "model_id" + "api_key", + "host", + "service_id", + "workspace" ] }, "inference._types:RateLimitSetting": { @@ -48509,6 +48626,46 @@ } } }, + "inference.put_alibabacloud:AlibabaCloudTaskSettings": { + "type": "object", + "properties": { + "input_type": { + "description": "For a `sparse_embedding` or `text_embedding` task, specify the type of input passed to the model.\nValid values are:\n\n* `ingest` for storing document embeddings in a vector database.\n* `search` for storing embeddings of search queries run against a vector database to find relevant documents.", + "type": "string" + }, + "return_token": { + "description": "For a `sparse_embedding` task, it affects whether the token name will be returned in the response.\nIt defaults to `false`, which means only the token ID will be returned in the response.", + "type": "boolean" + } + } + }, + "inference.put_eis:EisTaskType": { + "type": "string", + "enum": [ + "chat_completion" + ] + }, + "inference.put_eis:ServiceType": { + "type": "string", + "enum": [ + "elastic" + ] + }, + "inference.put_eis:EisServiceSettings": { + "type": "object", + "properties": { + "model_id": { + "description": "The name of the model to use for the inference task.", + "type": "string" + }, + "rate_limit": { + "$ref": "#/components/schemas/inference._types:RateLimitSetting" + } + }, + "required": [ + "model_id" + ] + }, "inference.put_hugging_face:HuggingFaceTaskType": { "type": "string", "enum": [ diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json index b1ca244d77..f061b01363 100644 --- a/output/schema/schema-serverless.json +++ b/output/schema/schema-serverless.json @@ -4758,6 +4758,51 @@ } ] }, + { + "availability": { + "serverless": { + "stability": "stable", + "visibility": "public" + }, + "stack": { + "since": "8.16.0", + "stability": "stable", + "visibility": "public" + } + }, + "description": "Create an AlibabaCloud AI Search inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "docId": "inference-api-put-alibabacloud", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-alibabacloud-ai-search.html", + "name": "inference.put_alibabacloud", + "privileges": { + "cluster": [ + "manage_inference" + ] + }, + "request": { + "name": "Request", + "namespace": "inference.put_alibabacloud" + }, + "requestBodyRequired": false, + "requestMediaType": [ + "application/json" + ], + "response": { + "name": "Response", + "namespace": "inference.put_alibabacloud" + }, + "responseMediaType": [ + "application/json" + ], + "urls": [ + { + "methods": [ + "PUT" + ], + "path": "/_inference/{task_type}/{alibabacloud_inference_id}" + } + ] + }, { "availability": { "serverless": { @@ -27588,32 +27633,82 @@ "kind": "properties", "properties": [ { - "description": "The type of service supported for the specified task type. In this case, `elastic`.", +<<<<<<< HEAD +======= + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + } + } + }, + { + "description": "The type of service supported for the specified task type. In this case, `alibabacloud-ai-search`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_eis" + "namespace": "inference.put_alibabacloud" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.", + "description": "Settings used to install the inference model. These settings are specific to the `alibabacloud-ai-search` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "EisServiceSettings", - "namespace": "inference.put_eis" + "name": "AlibabaCloudServiceSettings", + "namespace": "inference.put_alibabacloud" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AlibabaCloudTaskSettings", + "namespace": "inference.put_alibabacloud" } } } ] }, - "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", + "description": "Create an AlibabaCloud AI Search inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "examples": { + "PutAlibabaCloudRequestExample1": { + "description": "Run `PUT _inference/completion/alibabacloud_ai_search_completion` to create an inference endpoint that performs a completion task.", + "summary": "A completion task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"host\" : \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-qwen-turbo\",\n \"workspace\" : \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample2": { + "description": "Run `PUT _inference/rerank/alibabacloud_ai_search_rerank` to create an inference endpoint that performs a rerank task.", + "summary": "A rerank task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-bge-reranker-larger\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample3": { + "description": "Run `PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse` to create an inference endpoint that performs perform a sparse embedding task.", + "summary": "A sparse embedding task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-sparse-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample4": { + "description": "Run `PUT _inference/text_embedding/alibabacloud_ai_search_embeddings` to create an inference endpoint that performs a text embedding task.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + } + }, "inherits": { "type": { "name": "RequestBase", @@ -27623,24 +27718,24 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_eis" + "namespace": "inference.put_alibabacloud" }, "path": [ { - "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.", + "description": "The type of the inference task that the model will perform.", "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "EisTaskType", - "namespace": "inference.put_eis" + "name": "AlibabaCloudTaskType", + "namespace": "inference.put_alibabacloud" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "eis_inference_id", + "name": "alibabacloud_inference_id", "required": true, "type": { "kind": "instance_of", @@ -27652,7 +27747,7 @@ } ], "query": [], - "specLocation": "inference/put_eis/PutEisRequest.ts#L24-L62" + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L27-L80" }, { "body": { @@ -27668,9 +27763,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_eis" + "namespace": "inference.put_alibabacloud" }, - "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24" + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -27694,37 +27789,54 @@ } }, { - "description": "The type of service supported for the specified task type. In this case, `hugging_face`.", + "description": "The type of service supported for the specified task type. In this case, `amazonbedrock`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_hugging_face" + "namespace": "inference.put_amazonbedrock" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `hugging_face` service.", + "description": "Settings used to install the inference model. These settings are specific to the `amazonbedrock` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "HuggingFaceServiceSettings", - "namespace": "inference.put_hugging_face" + "name": "AmazonBedrockServiceSettings", + "namespace": "inference.put_amazonbedrock" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AmazonBedrockTaskSettings", + "namespace": "inference.put_amazonbedrock" } } } ] }, - "description": "Create a Hugging Face inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `hugging_face` service.\n\nYou must first create an inference endpoint on the Hugging Face endpoint page to get an endpoint URL.\nSelect the model you want to use on the new endpoint creation page (for example `intfloat/e5-small-v2`), then select the sentence embeddings task under the advanced configuration section.\nCreate the endpoint and copy the URL after the endpoint initialization has been finished.\n\nThe following models are recommended for the Hugging Face service:\n\n* `all-MiniLM-L6-v2`\n* `all-MiniLM-L12-v2`\n* `all-mpnet-base-v2`\n* `e5-base-v2`\n* `e5-small-v2`\n* `multilingual-e5-base`\n* `multilingual-e5-small`\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "description": "Create an Amazon Bedrock inference endpoint.\n\nCreates 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.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "PutHuggingFaceRequestExample1": { - "description": "Run `PUT _inference/text_embedding/hugging-face-embeddings` to create an inference endpoint that performs a `text_embedding` task type.", + "PutAmazonBedrockRequestExample1": { + "description": "Run `PUT _inference/text_embedding/amazon_bedrock_embeddings` to create an inference endpoint that performs a text embedding task.", "summary": "A text embedding task", - "value": "{\n \"service\": \"hugging_face\",\n \"service_settings\": {\n \"api_key\": \"hugging-face-access-token\", \n \"url\": \"url-endpoint\" \n }\n}" + "value": "{\n \"service\": \"amazonbedrock\",\n \"service_settings\": {\n \"access_key\": \"AWS-access-key\",\n \"secret_key\": \"AWS-secret-key\",\n \"region\": \"us-east-1\",\n \"provider\": \"amazontitan\",\n \"model\": \"amazon.titan-embed-text-v2:0\"\n }\n}" + }, + "PutAmazonBedrockRequestExample2": { + "description": "Run `PUT _inference/completion/openai-completion` to create an inference endpoint to perform a completion task type.", + "summary": "A completion task", + "value": "{\n \"service\": \"openai\",\n \"service_settings\": {\n \"api_key\": \"OpenAI-API-Key\",\n \"model_id\": \"gpt-3.5-turbo\"\n }\n}" } }, "inherits": { @@ -27736,7 +27848,7 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_hugging_face" + "namespace": "inference.put_amazonbedrock" }, "path": [ { @@ -27746,14 +27858,14 @@ "type": { "kind": "instance_of", "type": { - "name": "HuggingFaceTaskType", - "namespace": "inference.put_hugging_face" + "name": "AmazonBedrockTaskType", + "namespace": "inference.put_amazonbedrock" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "huggingface_inference_id", + "name": "amazonbedrock_inference_id", "required": true, "type": { "kind": "instance_of", @@ -27765,7 +27877,7 @@ } ], "query": [], - "specLocation": "inference/put_hugging_face/PutHuggingFaceRequest.ts#L27-L89" + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockRequest.ts#L28-L84" }, { "body": { @@ -27781,9 +27893,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_hugging_face" + "namespace": "inference.put_amazonbedrock" }, - "specLocation": "inference/put_hugging_face/PutHuggingFaceResponse.ts#L22-L24" + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -27807,26 +27919,26 @@ } }, { - "description": "The type of service supported for the specified task type. In this case, `jinaai`.", + "description": "The type of service supported for the specified task type. In this case, `anthropic`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_jinaai" + "namespace": "inference.put_anthropic" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `jinaai` service.", + "description": "Settings used to install the inference model. These settings are specific to the `watsonxai` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "JinaAIServiceSettings", - "namespace": "inference.put_jinaai" + "name": "AnthropicServiceSettings", + "namespace": "inference.put_anthropic" } } }, @@ -27837,24 +27949,148 @@ "type": { "kind": "instance_of", "type": { - "name": "JinaAITaskSettings", - "namespace": "inference.put_jinaai" + "name": "AnthropicTaskSettings", + "namespace": "inference.put_anthropic" } } } ] }, - "description": "Create an JinaAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `jinaai` service.\n\nTo review the available `rerank` models, refer to .\nTo review the available `text_embedding` models, refer to the .\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "description": "Create an Anthropic inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `anthropic` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "PutJinaAiRequestExample1": { - "description": "Run `PUT _inference/text_embedding/jinaai-embeddings` to create an inference endpoint for text embedding tasks using the JinaAI service.", + "PutAnthropicRequestExample1": { + "description": "Run `PUT _inference/completion/anthropic_completion` to create an inference endpoint that performs a completion task.", + "value": "{\n \"service\": \"anthropic\",\n \"service_settings\": {\n \"api_key\": \"Anthropic-Api-Key\",\n \"model_id\": \"Model-ID\"\n },\n \"task_settings\": {\n \"max_tokens\": 1024\n }\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "inference.put_anthropic" + }, + "path": [ + { + "description": "The task type.\nThe only valid task type for the model to perform is `completion`.", + "name": "task_type", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "AnthropicTaskType", + "namespace": "inference.put_anthropic" + } + } + }, + { + "description": "The unique identifier of the inference endpoint.", + "name": "anthropic_inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [], + "specLocation": "inference/put_anthropic/PutAnthropicRequest.ts#L28-L82" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "InferenceEndpointInfo", + "namespace": "inference._types" + } + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.put_anthropic" + }, + "specLocation": "inference/put_anthropic/PutAnthropicResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + } + } + }, + { + "description": "The type of service supported for the specified task type. In this case, `azureaistudio`.", + "name": "service", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_azureaistudio" + } + } + }, + { + "description": "Settings used to install the inference model. These settings are specific to the `openai` service.", + "name": "service_settings", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "AzureAiStudioServiceSettings", + "namespace": "inference.put_azureaistudio" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AzureAiStudioTaskSettings", + "namespace": "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.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "examples": { + "PutAzureAiStudioRequestExample1": { + "description": "Run `PUT _inference/text_embedding/azure_ai_studio_embeddings` to create an inference endpoint that performs a text_embedding task. Note that you do not specify a model here, as it is defined already in the Azure AI Studio deployment.", "summary": "A text embedding task", - "value": "{\n \"service\": \"jinaai\",\n \"service_settings\": {\n \"model_id\": \"jina-embeddings-v3\",\n \"api_key\": \"JinaAi-Api-key\"\n }\n}" + "value": "{\n \"service\": \"azureaistudio\",\n \"service_settings\": {\n \"api_key\": \"Azure-AI-Studio-API-key\",\n \"target\": \"Target-Uri\",\n \"provider\": \"openai\",\n \"endpoint_type\": \"token\"\n }\n}" }, - "PutJinaAiRequestExample2": { - "description": "Run `PUT _inference/rerank/jinaai-rerank` to create an inference endpoint for rerank tasks using the JinaAI service.", - "summary": "A rerank task", - "value": "{\n \"service\": \"jinaai\",\n \"service_settings\": {\n \"api_key\": \"JinaAI-Api-key\",\n \"model_id\": \"jina-reranker-v2-base-multilingual\"\n },\n \"task_settings\": {\n \"top_n\": 10,\n \"return_documents\": true\n }\n}" + "PutAzureAiStudioRequestExample2": { + "description": "Run `PUT _inference/completion/azure_ai_studio_completion` to create an inference endpoint that performs a completion task.", + "summary": "A completion task", + "value": "{\n \"service\": \"azureaistudio\",\n \"service_settings\": {\n \"api_key\": \"Azure-AI-Studio-API-key\",\n \"target\": \"Target-URI\",\n \"provider\": \"databricks\",\n \"endpoint_type\": \"realtime\"\n }\n}" } }, "inherits": { @@ -27866,7 +28102,7 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_jinaai" + "namespace": "inference.put_azureaistudio" }, "path": [ { @@ -27876,14 +28112,14 @@ "type": { "kind": "instance_of", "type": { - "name": "JinaAITaskType", - "namespace": "inference.put_jinaai" + "name": "AzureAiStudioTaskType", + "namespace": "inference.put_azureaistudio" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "jinaai_inference_id", + "name": "azureaistudio_inference_id", "required": true, "type": { "kind": "instance_of", @@ -27895,7 +28131,7 @@ } ], "query": [], - "specLocation": "inference/put_jinaai/PutJinaAiRequest.ts#L28-L84" + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioRequest.ts#L28-L81" }, { "body": { @@ -27911,9 +28147,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_jinaai" + "namespace": "inference.put_azureaistudio" }, - "specLocation": "inference/put_jinaai/PutJinaAiResponse.ts#L22-L24" + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -27937,26 +28173,26 @@ } }, { - "description": "The type of service supported for the specified task type. In this case, `openai`.", + "description": "The type of service supported for the specified task type. In this case, `azureopenai`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_openai" + "namespace": "inference.put_azureopenai" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `openai` service.", + "description": "Settings used to install the inference model. These settings are specific to the `azureopenai` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "OpenAIServiceSettings", - "namespace": "inference.put_openai" + "name": "AzureOpenAIServiceSettings", + "namespace": "inference.put_azureopenai" } } }, @@ -27967,24 +28203,24 @@ "type": { "kind": "instance_of", "type": { - "name": "OpenAITaskSettings", - "namespace": "inference.put_openai" + "name": "AzureOpenAITaskSettings", + "namespace": "inference.put_azureopenai" } } } ] }, - "description": "Create an OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openai` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "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).\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "PutOpenAiRequestExample1": { - "description": "Run `PUT _inference/text_embedding/openai-embeddings` to create an inference endpoint that performs a `text_embedding` task. The embeddings created by requests to this endpoint will have 128 dimensions.", + "PutAzureOpenAiRequestExample1": { + "description": "Run `PUT _inference/text_embedding/azure_openai_embeddings` to create an inference endpoint that performs a `text_embedding` task. You do not specify a model, as it is defined already in the Azure OpenAI deployment.", "summary": "A text embedding task", - "value": "{\n \"service\": \"openai\",\n \"service_settings\": {\n \"api_key\": \"OpenAI-API-Key\",\n \"model_id\": \"text-embedding-3-small\",\n \"dimensions\": 128\n }\n}" + "value": "{\n \"service\": \"azureopenai\",\n \"service_settings\": {\n \"api_key\": \"Api-Key\",\n \"resource_name\": \"Resource-name\",\n \"deployment_id\": \"Deployment-id\",\n \"api_version\": \"2024-02-01\"\n }\n}" }, - "PutOpenAiRequestExample2": { - "description": "Run `PUT _inference/completion/openai-completion` to create an inference endpoint to perform a completion task type.", + "PutAzureOpenAiRequestExample2": { + "description": "Run `PUT _inference/completion/azure_openai_completion` to create an inference endpoint that performs a `completion` task.", "summary": "A completion task", - "value": "{\n \"service\": \"openai\",\n \"service_settings\": {\n \"api_key\": \"OpenAI-API-Key\",\n \"model_id\": \"gpt-3.5-turbo\"\n }\n}" + "value": "{\n \"service\": \"azureopenai\",\n \"service_settings\": {\n \"api_key\": \"Api-Key\",\n \"resource_name\": \"Resource-name\",\n \"deployment_id\": \"Deployment-id\",\n \"api_version\": \"2024-02-01\"\n }\n}" } }, "inherits": { @@ -27996,7 +28232,7 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_openai" + "namespace": "inference.put_azureopenai" }, "path": [ { @@ -28006,14 +28242,14 @@ "type": { "kind": "instance_of", "type": { - "name": "OpenAITaskType", - "namespace": "inference.put_openai" + "name": "AzureOpenAITaskType", + "namespace": "inference.put_azureopenai" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "openai_inference_id", + "name": "azureopenai_inference_id", "required": true, "type": { "kind": "instance_of", @@ -28025,7 +28261,7 @@ } ], "query": [], - "specLocation": "inference/put_openai/PutOpenAiRequest.ts#L28-L82" + "specLocation": "inference/put_azureopenai/PutAzureOpenAiRequest.ts#L27-L88" }, { "body": { @@ -28041,9 +28277,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_openai" + "namespace": "inference.put_azureopenai" }, - "specLocation": "inference/put_openai/PutOpenAiResponse.ts#L22-L24" + "specLocation": "inference/put_azureopenai/PutAzureOpenAiResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -28067,26 +28303,26 @@ } }, { - "description": "The type of service supported for the specified task type. In this case, `voyageai`.", + "description": "The type of service supported for the specified task type. In this case, `cohere`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_voyageai" + "namespace": "inference.put_cohere" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `voyageai` service.", + "description": "Settings used to install the inference model.\nThese settings are specific to the `cohere` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "VoyageAIServiceSettings", - "namespace": "inference.put_voyageai" + "name": "CohereServiceSettings", + "namespace": "inference.put_cohere" } } }, @@ -28097,24 +28333,24 @@ "type": { "kind": "instance_of", "type": { - "name": "VoyageAITaskSettings", - "namespace": "inference.put_voyageai" + "name": "CohereTaskSettings", + "namespace": "inference.put_cohere" } } } ] }, - "description": "Create a VoyageAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `voyageai` service.\n\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.", + "description": "Create a Cohere inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `cohere` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "PutVoyageAIRequestExample1": { - "description": "Run `PUT _inference/text_embedding/voyageai-embeddings` to create an inference endpoint that performs a `text_embedding` task. The embeddings created by requests to this endpoint will have 512 dimensions.", + "PutCohereRequestExample1": { + "description": "Run `PUT _inference/text_embedding/cohere-embeddings` to create an inference endpoint that performs a text embedding task.", "summary": "A text embedding task", - "value": "{\n \"service\": \"voyageai\",\n \"service_settings\": {\n \"model_id\": \"voyage-3-large\",\n \"dimensions\": 512\n }\n}" + "value": "{\n \"service\": \"cohere\",\n \"service_settings\": {\n \"api_key\": \"Cohere-Api-key\",\n \"model_id\": \"embed-english-light-v3.0\",\n \"embedding_type\": \"byte\"\n }\n}" }, - "PutVoyageAIRequestExample2": { - "description": "Run `PUT _inference/rerank/voyageai-rerank` to create an inference endpoint that performs a `rerank` task.", + "PutCohereRequestExample2": { + "description": "Run `PUT _inference/rerank/cohere-rerank` to create an inference endpoint that performs a rerank task.", "summary": "A rerank task", - "value": "{\n \"service\": \"voyageai\",\n \"service_settings\": {\n \"model_id\": \"rerank-2\"\n }\n}" + "value": "{\n \"service\": \"cohere\",\n \"service_settings\": {\n \"api_key\": \"Cohere-API-key\",\n \"model_id\": \"rerank-english-v3.0\"\n },\n \"task_settings\": {\n \"top_n\": 10,\n \"return_documents\": true\n }\n}" } }, "inherits": { @@ -28126,7 +28362,7 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_voyageai" + "namespace": "inference.put_cohere" }, "path": [ { @@ -28136,14 +28372,14 @@ "type": { "kind": "instance_of", "type": { - "name": "VoyageAITaskType", - "namespace": "inference.put_voyageai" + "name": "CohereTaskType", + "namespace": "inference.put_cohere" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "voyageai_inference_id", + "name": "cohere_inference_id", "required": true, "type": { "kind": "instance_of", @@ -28155,7 +28391,7 @@ } ], "query": [], - "specLocation": "inference/put_voyageai/PutVoyageAIRequest.ts#L28-L77" + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L28-L82" }, { "body": { @@ -28171,9 +28407,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_voyageai" + "namespace": "inference.put_cohere" }, - "specLocation": "inference/put_voyageai/PutVoyageAIResponse.ts#L22-L24" + "specLocation": "inference/put_cohere/PutCohereResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -28183,38 +28419,33 @@ "kind": "properties", "properties": [ { - "description": "The type of service supported for the specified task type. In this case, `watsonxai`.", +>>>>>>> ef980f023 (Add Alibaba Cloud inference API (#4021)) + "description": "The type of service supported for the specified task type. In this case, `elastic`.", "name": "service", "required": true, "type": { "kind": "instance_of", "type": { "name": "ServiceType", - "namespace": "inference.put_watsonx" + "namespace": "inference.put_eis" } } }, { - "description": "Settings used to install the inference model. These settings are specific to the `watsonxai` service.", + "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.", "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "WatsonxServiceSettings", - "namespace": "inference.put_watsonx" + "name": "EisServiceSettings", + "namespace": "inference.put_eis" } } } ] }, - "description": "Create a Watsonx inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `watsonxai` service.\nYou need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service.\nYou can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", - "examples": { - "InferenceRequestExample1": { - "description": "Run `PUT _inference/text_embedding/watsonx-embeddings` to create an Watonsx inference endpoint that performs a text embedding task.", - "value": "{\n \"service\": \"watsonxai\",\n \"service_settings\": {\n \"api_key\": \"Watsonx-API-Key\", \n \"url\": \"Wastonx-URL\", \n \"model_id\": \"ibm/slate-30m-english-rtrvr\",\n \"project_id\": \"IBM-Cloud-ID\", \n \"api_version\": \"2024-03-14\"\n }\n}" - } - }, + "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", "inherits": { "type": { "name": "RequestBase", @@ -28224,24 +28455,24 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.put_watsonx" + "namespace": "inference.put_eis" }, "path": [ { - "description": "The task type.\nThe only valid task type for the model to perform is `text_embedding`.", + "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.", "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "WatsonxTaskType", - "namespace": "inference.put_watsonx" + "name": "EisTaskType", + "namespace": "inference.put_eis" } } }, { "description": "The unique identifier of the inference endpoint.", - "name": "watsonx_inference_id", + "name": "eis_inference_id", "required": true, "type": { "kind": "instance_of", @@ -28253,7 +28484,7 @@ } ], "query": [], - "specLocation": "inference/put_watsonx/PutWatsonxRequest.ts#L24-L70" + "specLocation": "inference/put_eis/PutEisRequest.ts#L24-L62" }, { "body": { @@ -28269,9 +28500,9 @@ "kind": "response", "name": { "name": "Response", - "namespace": "inference.put_watsonx" + "namespace": "inference.put_eis" }, - "specLocation": "inference/put_watsonx/PutWatsonxResponse.ts#L22-L24" + "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -28281,64 +28512,51 @@ "kind": "properties", "properties": [ { - "description": "Query input.", - "name": "query", - "required": true, + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "InferenceChunkingSettings", + "namespace": "inference._types" } } }, { - "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.", - "name": "input", + "description": "The type of service supported for the specified task type. In this case, `hugging_face`.", + "name": "service", "required": true, "type": { - "items": [ - { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - }, - { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - } - } - ], - "kind": "union_of" + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_hugging_face" + } } }, { - "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.", - "name": "task_settings", - "required": false, + "description": "Settings used to install the inference model. These settings are specific to the `hugging_face` service.", + "name": "service_settings", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "TaskSettings", - "namespace": "inference._types" + "name": "HuggingFaceServiceSettings", + "namespace": "inference.put_hugging_face" } } } ] }, - "description": "Perform rereanking inference on the service", + "description": "Create a Hugging Face inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `hugging_face` service.\n\nYou must first create an inference endpoint on the Hugging Face endpoint page to get an endpoint URL.\nSelect the model you want to use on the new endpoint creation page (for example `intfloat/e5-small-v2`), then select the sentence embeddings task under the advanced configuration section.\nCreate the endpoint and copy the URL after the endpoint initialization has been finished.\n\nThe following models are recommended for the Hugging Face service:\n\n* `all-MiniLM-L6-v2`\n* `all-MiniLM-L12-v2`\n* `all-mpnet-base-v2`\n* `e5-base-v2`\n* `e5-small-v2`\n* `multilingual-e5-base`\n* `multilingual-e5-small`\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "RerankRequestExample1": { - "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.", - "summary": "Rerank task", - "value": "{\n \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n \"query\": \"star wars main character\"\n}" + "PutHuggingFaceRequestExample1": { + "description": "Run `PUT _inference/text_embedding/hugging-face-embeddings` to create an inference endpoint that performs a `text_embedding` task type.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"hugging_face\",\n \"service_settings\": {\n \"api_key\": \"hugging-face-access-token\", \n \"url\": \"url-endpoint\" \n }\n}" } }, "inherits": { @@ -28350,38 +28568,36 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.rerank" + "namespace": "inference.put_hugging_face" }, "path": [ { - "description": "The unique identifier for the inference endpoint.", - "name": "inference_id", + "description": "The type of the inference task that the model will perform.", + "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Id", - "namespace": "_types" + "name": "HuggingFaceTaskType", + "namespace": "inference.put_hugging_face" } } - } - ], - "query": [ + }, { - "description": "The amount of time to wait for the inference request to complete.", - "name": "timeout", - "required": false, - "serverDefault": "30s", + "description": "The unique identifier of the inference endpoint.", + "name": "huggingface_inference_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Duration", + "name": "Id", "namespace": "_types" } } } ], - "specLocation": "inference/rerank/RerankRequest.ts#L25-L72" + "query": [], + "specLocation": "inference/put_hugging_face/PutHuggingFaceRequest.ts#L27-L89" }, { "body": { @@ -28389,24 +28605,17 @@ "value": { "kind": "instance_of", "type": { - "name": "RerankedInferenceResult", + "name": "InferenceEndpointInfo", "namespace": "inference._types" } } }, - "examples": { - "RerankResponseExample1": { - "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n", - "summary": "Rerank task", - "value": "{\n \"rerank\": [\n {\n \"index\": \"2\",\n \"relevance_score\": \"0.011597361\",\n \"text\": \"leia\"\n },\n {\n \"index\": \"0\",\n \"relevance_score\": \"0.006338922\",\n \"text\": \"luke\"\n },\n {\n \"index\": \"5\",\n \"relevance_score\": \"0.0016166499\",\n \"text\": \"star\"\n },\n {\n \"index\": \"4\",\n \"relevance_score\": \"0.0011695103\",\n \"text\": \"r2d2\"\n },\n {\n \"index\": \"1\",\n \"relevance_score\": \"5.614787E-4\",\n \"text\": \"like\"\n },\n {\n \"index\": \"6\",\n \"relevance_score\": \"3.7850367E-4\",\n \"text\": \"wars\"\n },\n {\n \"index\": \"3\",\n \"relevance_score\": \"1.2508839E-5\",\n \"text\": \"chewy\"\n }\n ]\n}" - } - }, "kind": "response", "name": { "name": "Response", - "namespace": "inference.rerank" + "namespace": "inference.put_hugging_face" }, - "specLocation": "inference/rerank/RerankResponse.ts#L22-L24" + "specLocation": "inference/put_hugging_face/PutHuggingFaceResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -28416,52 +28625,68 @@ "kind": "properties", "properties": [ { - "description": "Inference input.\nEither a string or an array of strings.", - "name": "input", + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + } + } + }, + { + "description": "The type of service supported for the specified task type. In this case, `jinaai`.", + "name": "service", "required": true, "type": { - "items": [ - { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - }, - { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - } - } - ], - "kind": "union_of" + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_jinaai" + } } }, { - "description": "Optional task settings", + "description": "Settings used to install the inference model. These settings are specific to the `jinaai` service.", + "name": "service_settings", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "JinaAIServiceSettings", + "namespace": "inference.put_jinaai" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", "name": "task_settings", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TaskSettings", - "namespace": "inference._types" + "name": "JinaAITaskSettings", + "namespace": "inference.put_jinaai" } } } ] }, - "description": "Perform sparse embedding inference on the service", + "description": "Create an JinaAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `jinaai` service.\n\nTo review the available `rerank` models, refer to .\nTo review the available `text_embedding` models, refer to the .\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "SparseEmbeddingRequestExample1": { - "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.", - "summary": "Sparse embedding task", - "value": "{\n \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}" + "PutJinaAiRequestExample1": { + "description": "Run `PUT _inference/text_embedding/jinaai-embeddings` to create an inference endpoint for text embedding tasks using the JinaAI service.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"jinaai\",\n \"service_settings\": {\n \"model_id\": \"jina-embeddings-v3\",\n \"api_key\": \"JinaAi-Api-key\"\n }\n}" + }, + "PutJinaAiRequestExample2": { + "description": "Run `PUT _inference/rerank/jinaai-rerank` to create an inference endpoint for rerank tasks using the JinaAI service.", + "summary": "A rerank task", + "value": "{\n \"service\": \"jinaai\",\n \"service_settings\": {\n \"api_key\": \"JinaAI-Api-key\",\n \"model_id\": \"jina-reranker-v2-base-multilingual\"\n },\n \"task_settings\": {\n \"top_n\": 10,\n \"return_documents\": true\n }\n}" } }, "inherits": { @@ -28473,38 +28698,36 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.sparse_embedding" + "namespace": "inference.put_jinaai" }, "path": [ { - "description": "The inference Id", - "name": "inference_id", + "description": "The type of the inference task that the model will perform.", + "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Id", - "namespace": "_types" + "name": "JinaAITaskType", + "namespace": "inference.put_jinaai" } } - } - ], - "query": [ + }, { - "description": "Specifies the amount of time to wait for the inference request to complete.", - "name": "timeout", - "required": false, - "serverDefault": "30s", + "description": "The unique identifier of the inference endpoint.", + "name": "jinaai_inference_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Duration", + "name": "Id", "namespace": "_types" } } } ], - "specLocation": "inference/sparse_embedding/SparseEmbeddingRequest.ts#L25-L63" + "query": [], + "specLocation": "inference/put_jinaai/PutJinaAiRequest.ts#L28-L84" }, { "body": { @@ -28512,24 +28735,17 @@ "value": { "kind": "instance_of", "type": { - "name": "SparseEmbeddingInferenceResult", + "name": "InferenceEndpointInfo", "namespace": "inference._types" } } }, - "examples": { - "SparseEmbeddingResponseExample1": { - "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n", - "summary": "Sparse embedding task", - "value": "{\n \"sparse_embedding\": [\n {\n \"port\": 2.1259406,\n \"sky\": 1.7073475,\n \"color\": 1.6922266,\n \"dead\": 1.6247464,\n \"television\": 1.3525393,\n \"above\": 1.2425821,\n \"tuned\": 1.1440028,\n \"colors\": 1.1218185,\n \"tv\": 1.0111054,\n \"ports\": 1.0067928,\n \"poem\": 1.0042328,\n \"channel\": 0.99471164,\n \"tune\": 0.96235967,\n \"scene\": 0.9020516\n }\n ]\n}" - } - }, "kind": "response", "name": { "name": "Response", - "namespace": "inference.sparse_embedding" + "namespace": "inference.put_jinaai" }, - "specLocation": "inference/sparse_embedding/SparseEmbeddingResponse.ts#L22-L24" + "specLocation": "inference/put_jinaai/PutJinaAiResponse.ts#L22-L24" }, { "attachedBehaviors": [ @@ -28539,52 +28755,68 @@ "kind": "properties", "properties": [ { - "description": "Inference input.\nEither a string or an array of strings.", - "name": "input", + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + } + } + }, + { + "description": "The type of service supported for the specified task type. In this case, `openai`.", + "name": "service", "required": true, "type": { - "items": [ - { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - }, - { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - } - } - ], - "kind": "union_of" + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_openai" + } } }, { - "description": "Optional task settings", + "description": "Settings used to install the inference model. These settings are specific to the `openai` service.", + "name": "service_settings", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "OpenAIServiceSettings", + "namespace": "inference.put_openai" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", "name": "task_settings", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TaskSettings", - "namespace": "inference._types" + "name": "OpenAITaskSettings", + "namespace": "inference.put_openai" } } } ] }, - "description": "Perform text embedding inference on the service", + "description": "Create an OpenAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `openai` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", "examples": { - "TextEmbeddingRequestExample1": { - "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,", - "summary": "Text embedding task", - "value": "{\n \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n \"task_settings\": {\n \"input_type\": \"ingest\"\n }\n}" + "PutOpenAiRequestExample1": { + "description": "Run `PUT _inference/text_embedding/openai-embeddings` to create an inference endpoint that performs a `text_embedding` task. The embeddings created by requests to this endpoint will have 128 dimensions.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"openai\",\n \"service_settings\": {\n \"api_key\": \"OpenAI-API-Key\",\n \"model_id\": \"text-embedding-3-small\",\n \"dimensions\": 128\n }\n}" + }, + "PutOpenAiRequestExample2": { + "description": "Run `PUT _inference/completion/openai-completion` to create an inference endpoint to perform a completion task type.", + "summary": "A completion task", + "value": "{\n \"service\": \"openai\",\n \"service_settings\": {\n \"api_key\": \"OpenAI-API-Key\",\n \"model_id\": \"gpt-3.5-turbo\"\n }\n}" } }, "inherits": { @@ -28596,38 +28828,36 @@ "kind": "request", "name": { "name": "Request", - "namespace": "inference.text_embedding" + "namespace": "inference.put_openai" }, "path": [ { - "description": "The inference Id", - "name": "inference_id", + "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.", + "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Id", - "namespace": "_types" + "name": "OpenAITaskType", + "namespace": "inference.put_openai" } } - } - ], - "query": [ + }, { - "description": "Specifies the amount of time to wait for the inference request to complete.", - "name": "timeout", - "required": false, - "serverDefault": "30s", + "description": "The unique identifier of the inference endpoint.", + "name": "openai_inference_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Duration", + "name": "Id", "namespace": "_types" } } } ], - "specLocation": "inference/text_embedding/TextEmbeddingRequest.ts#L25-L63" + "query": [], + "specLocation": "inference/put_openai/PutOpenAiRequest.ts#L28-L82" }, { "body": { @@ -28635,133 +28865,90 @@ "value": { "kind": "instance_of", "type": { - "name": "TextEmbeddingInferenceResult", + "name": "InferenceEndpointInfo", "namespace": "inference._types" } } }, - "examples": { - "TextEmbeddingResponseExample1": { - "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n", - "summary": "Text embedding task", - "value": "{\n \"text_embedding\": [\n {\n \"embedding\": [\n {\n 0.018569946,\n -0.036895752,\n 0.01486969,\n -0.0045204163,\n -0.04385376,\n 0.0075950623,\n 0.04260254,\n -0.004005432,\n 0.007865906,\n 0.030792236,\n -0.050476074,\n 0.011795044,\n -0.011642456,\n -0.010070801\n }\n ]\n }\n ]\n}" - } - }, "kind": "response", "name": { "name": "Response", - "namespace": "inference.text_embedding" + "namespace": "inference.put_openai" }, - "specLocation": "inference/text_embedding/TextEmbeddingResponse.ts#L22-L24" + "specLocation": "inference/put_openai/PutOpenAiResponse.ts#L22-L24" }, { "attachedBehaviors": [ "CommonQueryParameters" ], - "body": { - "kind": "no_body" - }, - "description": "Get cluster info.\nGet basic build, version, and cluster information.", - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, - "kind": "request", - "name": { - "name": "Request", - "namespace": "_global.info" - }, - "path": [], - "query": [], - "specLocation": "_global/info/RootNodeInfoRequest.ts#L22-L39" - }, - { "body": { "kind": "properties", "properties": [ { - "description": "The responding cluster's name.", - "name": "cluster_name", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "Name", - "namespace": "_types" - } - } - }, - { - "name": "cluster_uuid", - "required": true, + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Uuid", - "namespace": "_types" + "name": "InferenceChunkingSettings", + "namespace": "inference._types" } } }, { - "description": "The responding node's name.", - "name": "name", + "description": "The type of service supported for the specified task type. In this case, `voyageai`.", + "name": "service", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Name", - "namespace": "_types" + "name": "ServiceType", + "namespace": "inference.put_voyageai" } } }, { - "name": "tagline", + "description": "Settings used to install the inference model. These settings are specific to the `voyageai` service.", + "name": "service_settings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "VoyageAIServiceSettings", + "namespace": "inference.put_voyageai" } } }, { - "description": "The running version of Elasticsearch.", - "name": "version", - "required": true, + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", + "name": "task_settings", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "ElasticsearchVersionInfo", - "namespace": "_types" + "name": "VoyageAITaskSettings", + "namespace": "inference.put_voyageai" } } } ] }, + "description": "Create a VoyageAI inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `voyageai` service.\n\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.", "examples": { - "RootNodeInfoResponseExample1": { - "description": "A successful response from `GET /`s.", - "value": "{\n \"name\": \"instance-0000000000\",\n \"cluster_name\": \"my_test_cluster\",\n \"cluster_uuid\": \"5QaxoN0pRZuOmWSxstBBwQ\",\n \"version\": {\n \"build_date\": \"2024-02-01T13:07:13.727175297Z\",\n \"minimum_wire_compatibility_version\": \"7.17.0\",\n \"build_hash\": \"6185ba65d27469afabc9bc951cded6c17c21e3f3\",\n \"number\": \"8.12.1\",\n \"lucene_version\": \"9.9.2\",\n \"minimum_index_compatibility_version\": \"7.0.0\",\n \"build_flavor\": \"default\",\n \"build_snapshot\": false,\n \"build_type\": \"docker\"\n },\n \"tagline\": \"You Know, for Search\"\n}" + "PutVoyageAIRequestExample1": { + "description": "Run `PUT _inference/text_embedding/voyageai-embeddings` to create an inference endpoint that performs a `text_embedding` task. The embeddings created by requests to this endpoint will have 512 dimensions.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"voyageai\",\n \"service_settings\": {\n \"model_id\": \"voyage-3-large\",\n \"dimensions\": 512\n }\n}" + }, + "PutVoyageAIRequestExample2": { + "description": "Run `PUT _inference/rerank/voyageai-rerank` to create an inference endpoint that performs a `rerank` task.", + "summary": "A rerank task", + "value": "{\n \"service\": \"voyageai\",\n \"service_settings\": {\n \"model_id\": \"rerank-2\"\n }\n}" } }, - "kind": "response", - "name": { - "name": "Response", - "namespace": "_global.info" - }, - "specLocation": "_global/info/RootNodeInfoResponse.ts#L23-L40" - }, - { - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "body": { - "kind": "no_body" - }, - "description": "Delete pipelines.\nDelete one or more ingest pipelines.", "inherits": { "type": { "name": "RequestBase", @@ -28771,43 +28958,688 @@ "kind": "request", "name": { "name": "Request", - "namespace": "ingest.delete_pipeline" + "namespace": "inference.put_voyageai" }, "path": [ { - "description": "Pipeline ID or wildcard expression of pipeline IDs used to limit the request.\nTo delete all ingest pipelines in a cluster, use a value of `*`.", - "name": "id", + "description": "The type of the inference task that the model will perform.", + "name": "task_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Id", - "namespace": "_types" + "name": "VoyageAITaskType", + "namespace": "inference.put_voyageai" } } - } - ], - "query": [ + }, { - "description": "Period to wait for a connection to the master node.\nIf no response is received before the timeout expires, the request fails and returns an error.", - "name": "master_timeout", - "required": false, - "serverDefault": "30s", + "description": "The unique identifier of the inference endpoint.", + "name": "voyageai_inference_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Duration", + "name": "Id", "namespace": "_types" } } - }, - { - "description": "Period to wait for a response.\nIf no response is received before the timeout expires, the request fails and returns an error.", - "name": "timeout", - "required": false, - "serverDefault": "30s", - "type": { - "kind": "instance_of", + } + ], + "query": [], + "specLocation": "inference/put_voyageai/PutVoyageAIRequest.ts#L28-L77" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "InferenceEndpointInfo", + "namespace": "inference._types" + } + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.put_voyageai" + }, + "specLocation": "inference/put_voyageai/PutVoyageAIResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "The type of service supported for the specified task type. In this case, `watsonxai`.", + "name": "service", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_watsonx" + } + } + }, + { + "description": "Settings used to install the inference model. These settings are specific to the `watsonxai` service.", + "name": "service_settings", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "WatsonxServiceSettings", + "namespace": "inference.put_watsonx" + } + } + } + ] + }, + "description": "Create a Watsonx inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `watsonxai` service.\nYou need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service.\nYou can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "examples": { + "InferenceRequestExample1": { + "description": "Run `PUT _inference/text_embedding/watsonx-embeddings` to create an Watonsx inference endpoint that performs a text embedding task.", + "value": "{\n \"service\": \"watsonxai\",\n \"service_settings\": {\n \"api_key\": \"Watsonx-API-Key\", \n \"url\": \"Wastonx-URL\", \n \"model_id\": \"ibm/slate-30m-english-rtrvr\",\n \"project_id\": \"IBM-Cloud-ID\", \n \"api_version\": \"2024-03-14\"\n }\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "inference.put_watsonx" + }, + "path": [ + { + "description": "The task type.\nThe only valid task type for the model to perform is `text_embedding`.", + "name": "task_type", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "WatsonxTaskType", + "namespace": "inference.put_watsonx" + } + } + }, + { + "description": "The unique identifier of the inference endpoint.", + "name": "watsonx_inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [], + "specLocation": "inference/put_watsonx/PutWatsonxRequest.ts#L24-L70" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "InferenceEndpointInfo", + "namespace": "inference._types" + } + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.put_watsonx" + }, + "specLocation": "inference/put_watsonx/PutWatsonxResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "Query input.", + "name": "query", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "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.", + "name": "input", + "required": true, + "type": { + "items": [ + { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + }, + { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "kind": "union_of" + } + }, + { + "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.", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "TaskSettings", + "namespace": "inference._types" + } + } + } + ] + }, + "description": "Perform rereanking inference on the service", + "examples": { + "RerankRequestExample1": { + "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.", + "summary": "Rerank task", + "value": "{\n \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n \"query\": \"star wars main character\"\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "inference.rerank" + }, + "path": [ + { + "description": "The unique identifier for the inference endpoint.", + "name": "inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [ + { + "description": "The amount of time to wait for the inference request to complete.", + "name": "timeout", + "required": false, + "serverDefault": "30s", + "type": { + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" + } + } + } + ], + "specLocation": "inference/rerank/RerankRequest.ts#L25-L72" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "RerankedInferenceResult", + "namespace": "inference._types" + } + } + }, + "examples": { + "RerankResponseExample1": { + "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n", + "summary": "Rerank task", + "value": "{\n \"rerank\": [\n {\n \"index\": \"2\",\n \"relevance_score\": \"0.011597361\",\n \"text\": \"leia\"\n },\n {\n \"index\": \"0\",\n \"relevance_score\": \"0.006338922\",\n \"text\": \"luke\"\n },\n {\n \"index\": \"5\",\n \"relevance_score\": \"0.0016166499\",\n \"text\": \"star\"\n },\n {\n \"index\": \"4\",\n \"relevance_score\": \"0.0011695103\",\n \"text\": \"r2d2\"\n },\n {\n \"index\": \"1\",\n \"relevance_score\": \"5.614787E-4\",\n \"text\": \"like\"\n },\n {\n \"index\": \"6\",\n \"relevance_score\": \"3.7850367E-4\",\n \"text\": \"wars\"\n },\n {\n \"index\": \"3\",\n \"relevance_score\": \"1.2508839E-5\",\n \"text\": \"chewy\"\n }\n ]\n}" + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.rerank" + }, + "specLocation": "inference/rerank/RerankResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "Inference input.\nEither a string or an array of strings.", + "name": "input", + "required": true, + "type": { + "items": [ + { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + }, + { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "kind": "union_of" + } + }, + { + "description": "Optional task settings", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "TaskSettings", + "namespace": "inference._types" + } + } + } + ] + }, + "description": "Perform sparse embedding inference on the service", + "examples": { + "SparseEmbeddingRequestExample1": { + "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.", + "summary": "Sparse embedding task", + "value": "{\n \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "inference.sparse_embedding" + }, + "path": [ + { + "description": "The inference Id", + "name": "inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [ + { + "description": "Specifies the amount of time to wait for the inference request to complete.", + "name": "timeout", + "required": false, + "serverDefault": "30s", + "type": { + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" + } + } + } + ], + "specLocation": "inference/sparse_embedding/SparseEmbeddingRequest.ts#L25-L63" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "SparseEmbeddingInferenceResult", + "namespace": "inference._types" + } + } + }, + "examples": { + "SparseEmbeddingResponseExample1": { + "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n", + "summary": "Sparse embedding task", + "value": "{\n \"sparse_embedding\": [\n {\n \"port\": 2.1259406,\n \"sky\": 1.7073475,\n \"color\": 1.6922266,\n \"dead\": 1.6247464,\n \"television\": 1.3525393,\n \"above\": 1.2425821,\n \"tuned\": 1.1440028,\n \"colors\": 1.1218185,\n \"tv\": 1.0111054,\n \"ports\": 1.0067928,\n \"poem\": 1.0042328,\n \"channel\": 0.99471164,\n \"tune\": 0.96235967,\n \"scene\": 0.9020516\n }\n ]\n}" + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.sparse_embedding" + }, + "specLocation": "inference/sparse_embedding/SparseEmbeddingResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "Inference input.\nEither a string or an array of strings.", + "name": "input", + "required": true, + "type": { + "items": [ + { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + }, + { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "kind": "union_of" + } + }, + { + "description": "Optional task settings", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "TaskSettings", + "namespace": "inference._types" + } + } + } + ] + }, + "description": "Perform text embedding inference on the service", + "examples": { + "TextEmbeddingRequestExample1": { + "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,", + "summary": "Text embedding task", + "value": "{\n \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n \"task_settings\": {\n \"input_type\": \"ingest\"\n }\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "inference.text_embedding" + }, + "path": [ + { + "description": "The inference Id", + "name": "inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [ + { + "description": "Specifies the amount of time to wait for the inference request to complete.", + "name": "timeout", + "required": false, + "serverDefault": "30s", + "type": { + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" + } + } + } + ], + "specLocation": "inference/text_embedding/TextEmbeddingRequest.ts#L25-L63" + }, + { + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "TextEmbeddingInferenceResult", + "namespace": "inference._types" + } + } + }, + "examples": { + "TextEmbeddingResponseExample1": { + "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n", + "summary": "Text embedding task", + "value": "{\n \"text_embedding\": [\n {\n \"embedding\": [\n {\n 0.018569946,\n -0.036895752,\n 0.01486969,\n -0.0045204163,\n -0.04385376,\n 0.0075950623,\n 0.04260254,\n -0.004005432,\n 0.007865906,\n 0.030792236,\n -0.050476074,\n 0.011795044,\n -0.011642456,\n -0.010070801\n }\n ]\n }\n ]\n}" + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "inference.text_embedding" + }, + "specLocation": "inference/text_embedding/TextEmbeddingResponse.ts#L22-L24" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "no_body" + }, + "description": "Get cluster info.\nGet basic build, version, and cluster information.", + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "_global.info" + }, + "path": [], + "query": [], + "specLocation": "_global/info/RootNodeInfoRequest.ts#L22-L39" + }, + { + "body": { + "kind": "properties", + "properties": [ + { + "description": "The responding cluster's name.", + "name": "cluster_name", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Name", + "namespace": "_types" + } + } + }, + { + "name": "cluster_uuid", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Uuid", + "namespace": "_types" + } + } + }, + { + "description": "The responding node's name.", + "name": "name", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Name", + "namespace": "_types" + } + } + }, + { + "name": "tagline", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "The running version of Elasticsearch.", + "name": "version", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "ElasticsearchVersionInfo", + "namespace": "_types" + } + } + } + ] + }, + "examples": { + "RootNodeInfoResponseExample1": { + "description": "A successful response from `GET /`s.", + "value": "{\n \"name\": \"instance-0000000000\",\n \"cluster_name\": \"my_test_cluster\",\n \"cluster_uuid\": \"5QaxoN0pRZuOmWSxstBBwQ\",\n \"version\": {\n \"build_date\": \"2024-02-01T13:07:13.727175297Z\",\n \"minimum_wire_compatibility_version\": \"7.17.0\",\n \"build_hash\": \"6185ba65d27469afabc9bc951cded6c17c21e3f3\",\n \"number\": \"8.12.1\",\n \"lucene_version\": \"9.9.2\",\n \"minimum_index_compatibility_version\": \"7.0.0\",\n \"build_flavor\": \"default\",\n \"build_snapshot\": false,\n \"build_type\": \"docker\"\n },\n \"tagline\": \"You Know, for Search\"\n}" + } + }, + "kind": "response", + "name": { + "name": "Response", + "namespace": "_global.info" + }, + "specLocation": "_global/info/RootNodeInfoResponse.ts#L23-L40" + }, + { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "no_body" + }, + "description": "Delete pipelines.\nDelete one or more ingest pipelines.", + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "kind": "request", + "name": { + "name": "Request", + "namespace": "ingest.delete_pipeline" + }, + "path": [ + { + "description": "Pipeline ID or wildcard expression of pipeline IDs used to limit the request.\nTo delete all ingest pipelines in a cluster, use a value of `*`.", + "name": "id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [ + { + "description": "Period to wait for a connection to the master node.\nIf no response is received before the timeout expires, the request fails and returns an error.", + "name": "master_timeout", + "required": false, + "serverDefault": "30s", + "type": { + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" + } + } + }, + { + "description": "Period to wait for a response.\nIf no response is received before the timeout expires, the request fails and returns an error.", + "name": "timeout", + "required": false, + "serverDefault": "30s", + "type": { + "kind": "instance_of", "type": { "name": "Duration", "namespace": "_types" @@ -100738,6 +101570,268 @@ "kind": "enum", "members": [ { +<<<<<<< HEAD +======= + "name": "completion" + }, + { + "name": "rerank" + }, + { + "name": "space_embedding" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "AlibabaCloudTaskType", + "namespace": "inference.put_alibabacloud" + }, + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L82-L87" + }, + { + "kind": "enum", + "members": [ + { + "name": "alibabacloud-ai-search" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_alibabacloud" + }, + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L89-L91" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "AmazonBedrockTaskType", + "namespace": "inference.put_amazonbedrock" + }, + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockRequest.ts#L86-L89" + }, + { + "kind": "enum", + "members": [ + { + "name": "amazonbedrock" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_amazonbedrock" + }, + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockRequest.ts#L91-L93" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + } + ], + "name": { + "name": "AnthropicTaskType", + "namespace": "inference.put_anthropic" + }, + "specLocation": "inference/put_anthropic/PutAnthropicRequest.ts#L84-L86" + }, + { + "kind": "enum", + "members": [ + { + "name": "anthropic" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_anthropic" + }, + "specLocation": "inference/put_anthropic/PutAnthropicRequest.ts#L88-L90" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "AzureAiStudioTaskType", + "namespace": "inference.put_azureaistudio" + }, + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioRequest.ts#L83-L86" + }, + { + "kind": "enum", + "members": [ + { + "name": "azureaistudio" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_azureaistudio" + }, + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioRequest.ts#L88-L90" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "AzureOpenAITaskType", + "namespace": "inference.put_azureopenai" + }, + "specLocation": "inference/put_azureopenai/PutAzureOpenAiRequest.ts#L90-L93" + }, + { + "kind": "enum", + "members": [ + { + "name": "azureopenai" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_azureopenai" + }, + "specLocation": "inference/put_azureopenai/PutAzureOpenAiRequest.ts#L95-L97" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + }, + { + "name": "rerank" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "CohereTaskType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L84-L88" + }, + { + "kind": "enum", + "members": [ + { + "name": "byte" + }, + { + "name": "float" + }, + { + "name": "int8" + } + ], + "name": { + "name": "EmbeddingType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L94-L98" + }, + { + "kind": "enum", + "members": [ + { + "name": "classification" + }, + { + "name": "clustering" + }, + { + "name": "ingest" + }, + { + "name": "search" + } + ], + "name": { + "name": "InputType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L100-L105" + }, + { + "kind": "enum", + "members": [ + { + "name": "cohere" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L90-L92" + }, + { + "kind": "enum", + "members": [ + { + "name": "cosine" + }, + { + "name": "dot_product" + }, + { + "name": "l2_norm" + } + ], + "name": { + "name": "SimilarityType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L107-L111" + }, + { + "kind": "enum", + "members": [ + { + "name": "END" + }, + { + "name": "NONE" + }, + { + "name": "START" + } + ], + "name": { + "name": "TruncateType", + "namespace": "inference.put_cohere" + }, + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L113-L117" + }, + { + "kind": "enum", + "members": [ + { +>>>>>>> ef980f023 (Add Alibaba Cloud inference API (#4021)) "name": "chat_completion" } ], @@ -117935,157 +119029,635 @@ }, "properties": [ { - "description": "The language the script is written in.\nFor serach templates, use `mustache`.", - "name": "lang", + "description": "The language the script is written in.\nFor serach templates, use `mustache`.", + "name": "lang", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "ScriptLanguage", + "namespace": "_types" + } + } + }, + { + "name": "options", + "required": false, + "type": { + "key": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + }, + "kind": "dictionary_of", + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + }, + { + "description": "The script source.\nFor search templates, an object containing the search template.", + "name": "source", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "_types/Scripting.ts#L47-L59" + }, + { + "kind": "interface", + "name": { + "name": "Hop", + "namespace": "graph._types" + }, + "properties": [ + { + "description": "Specifies one or more fields from which you want to extract terms that are associated with the specified vertices.", + "name": "connections", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "Hop", + "namespace": "graph._types" + } + } + }, + { + "description": "An optional guiding query that constrains the Graph API as it explores connected terms.", + "name": "query", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "QueryContainer", + "namespace": "_types.query_dsl" + } + } + }, + { + "description": "Contains the fields you are interested in.", + "name": "vertices", + "required": true, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "VertexDefinition", + "namespace": "graph._types" + } + } + } + } + ], + "specLocation": "graph/_types/Hop.ts#L23-L36" + }, + { + "kind": "interface", + "name": { + "name": "VertexDefinition", + "namespace": "graph._types" + }, + "properties": [ + { + "description": "Prevents the specified terms from being included in the results.", + "name": "exclude", + "required": false, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + }, + { + "description": "Identifies a field in the documents of interest.", + "name": "field", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Field", + "namespace": "_types" + } + } + }, + { + "description": "Identifies the terms of interest that form the starting points from which you want to spider out.", + "name": "include", + "required": false, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "VertexInclude", + "namespace": "graph._types" + } + } + } + }, + { + "description": "Specifies how many documents must contain a pair of terms before it is considered to be a useful connection.\nThis setting acts as a certainty threshold.", + "name": "min_doc_count", + "required": false, + "serverDefault": 3, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "description": "Controls how many documents on a particular shard have to contain a pair of terms before the connection is returned for global consideration.", + "name": "shard_min_doc_count", + "required": false, + "serverDefault": 2, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "description": "Specifies the maximum number of vertex terms returned for each field.", + "name": "size", + "required": false, + "serverDefault": 5, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + } + ], + "specLocation": "graph/_types/Vertex.ts#L30-L59" + }, + { + "kind": "interface", + "name": { + "name": "VertexInclude", + "namespace": "graph._types" + }, + "properties": [ + { + "name": "boost", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "double", + "namespace": "_types" + } + } + }, + { + "name": "term", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "graph/_types/Vertex.ts#L61-L64" + }, + { + "kind": "interface", + "name": { + "name": "ExploreControls", + "namespace": "graph._types" + }, + "properties": [ + { + "description": "To avoid the top-matching documents sample being dominated by a single source of results, it is sometimes necessary to request diversity in the sample.\nYou can do this by selecting a single-value field and setting a maximum number of documents per value for that field.", + "name": "sample_diversity", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "SampleDiversity", + "namespace": "graph._types" + } + } + }, + { + "description": "Each hop considers a sample of the best-matching documents on each shard.\nUsing samples improves the speed of execution and keeps exploration focused on meaningfully-connected terms.\nVery small values (less than 50) might not provide sufficient weight-of-evidence to identify significant connections between terms.\nVery large sample sizes can dilute the quality of the results and increase execution times.", + "name": "sample_size", + "required": false, + "serverDefault": 100, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + }, + { + "description": "The length of time in milliseconds after which exploration will be halted and the results gathered so far are returned.\nThis timeout is honored on a best-effort basis.\nExecution might overrun this timeout if, for example, a long pause is encountered while FieldData is loaded for a field.", + "name": "timeout", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" + } + } + }, + { + "description": "Filters associated terms so only those that are significantly associated with your query are included.", + "docId": "search-aggregations-bucket-significantterms-aggregation", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/search-aggregations-bucket-significantterms-aggregation.html", + "name": "use_significance", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "graph/_types/ExploreControls.ts#L24-L49" + }, + { + "kind": "interface", + "name": { + "name": "SampleDiversity", + "namespace": "graph._types" + }, + "properties": [ + { + "name": "field", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Field", + "namespace": "_types" + } + } + }, + { + "name": "max_docs_per_value", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + } + ], + "specLocation": "graph/_types/ExploreControls.ts#L51-L54" + }, + { + "kind": "interface", + "name": { + "name": "Connection", + "namespace": "graph._types" + }, + "properties": [ + { + "name": "doc_count", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "source", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "target", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "weight", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "double", + "namespace": "_types" + } + } + } + ], + "specLocation": "graph/_types/Connection.ts#L22-L27" + }, + { + "kind": "interface", + "name": { + "name": "Vertex", + "namespace": "graph._types" + }, + "properties": [ + { + "name": "depth", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "field", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Field", + "namespace": "_types" + } + } + }, + { + "name": "term", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "name": "weight", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "double", + "namespace": "_types" + } + } + } + ], + "specLocation": "graph/_types/Vertex.ts#L23-L28" + }, + { + "kind": "interface", + "name": { + "name": "IndicesBlockStatus", + "namespace": "indices.add_block" + }, + "properties": [ + { + "name": "name", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "IndexName", + "namespace": "_types" + } + } + }, + { + "name": "blocked", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "indices/add_block/IndicesAddBlockResponse.ts#L30-L33" + }, + { + "kind": "interface", + "name": { + "name": "AnalyzeDetail", + "namespace": "indices.analyze" + }, + "properties": [ + { + "name": "analyzer", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AnalyzerDetail", + "namespace": "indices.analyze" + } + } + }, + { + "name": "charfilters", + "required": false, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "CharFilterDetail", + "namespace": "indices.analyze" + } + } + } + }, + { + "name": "custom_analyzer", "required": true, "type": { "kind": "instance_of", "type": { - "name": "ScriptLanguage", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "options", + "name": "tokenfilters", "required": false, "type": { - "key": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - }, - "kind": "dictionary_of", - "singleKey": false, + "kind": "array_of", "value": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "TokenDetail", + "namespace": "indices.analyze" } } } }, { - "description": "The script source.\nFor search templates, an object containing the search template.", - "name": "source", - "required": true, + "name": "tokenizer", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "TokenDetail", + "namespace": "indices.analyze" } } } ], - "specLocation": "_types/Scripting.ts#L47-L59" + "specLocation": "indices/analyze/types.ts#L24-L30" }, { "kind": "interface", "name": { - "name": "Hop", - "namespace": "graph._types" + "name": "AnalyzerDetail", + "namespace": "indices.analyze" }, "properties": [ { - "description": "Specifies one or more fields from which you want to extract terms that are associated with the specified vertices.", - "name": "connections", - "required": false, - "type": { - "kind": "instance_of", - "type": { - "name": "Hop", - "namespace": "graph._types" - } - } - }, - { - "description": "An optional guiding query that constrains the Graph API as it explores connected terms.", - "name": "query", + "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "QueryContainer", - "namespace": "_types.query_dsl" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Contains the fields you are interested in.", - "name": "vertices", + "name": "tokens", "required": true, "type": { "kind": "array_of", "value": { "kind": "instance_of", "type": { - "name": "VertexDefinition", - "namespace": "graph._types" + "name": "ExplainAnalyzeToken", + "namespace": "indices.analyze" } } } } ], - "specLocation": "graph/_types/Hop.ts#L23-L36" + "specLocation": "indices/analyze/types.ts#L32-L35" }, { - "kind": "interface", - "name": { - "name": "VertexDefinition", - "namespace": "graph._types" - }, - "properties": [ + "attachedBehaviors": [ + "AdditionalProperties" + ], + "behaviors": [ { - "description": "Prevents the specified terms from being included in the results.", - "name": "exclude", - "required": false, - "type": { - "kind": "array_of", - "value": { + "generics": [ + { "kind": "instance_of", "type": { "name": "string", "namespace": "_builtins" } + }, + { + "kind": "user_defined_value" + } + ], + "meta": { + "description": "Additional tokenizer-specific attributes", + "fieldname": "attributes" + }, + "type": { + "name": "AdditionalProperties", + "namespace": "_spec_utils" + } + } + ], + "kind": "interface", + "name": { + "name": "ExplainAnalyzeToken", + "namespace": "indices.analyze" + }, + "properties": [ + { + "name": "bytes", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Identifies a field in the documents of interest.", - "name": "field", + "name": "end_offset", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Field", + "name": "long", "namespace": "_types" } } }, { - "description": "Identifies the terms of interest that form the starting points from which you want to spider out.", - "name": "include", + "name": "keyword", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "VertexInclude", - "namespace": "graph._types" - } + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" } } }, { - "description": "Specifies how many documents must contain a pair of terms before it is considered to be a useful connection.\nThis setting acts as a certainty threshold.", - "name": "min_doc_count", - "required": false, - "serverDefault": 3, + "name": "position", + "required": true, "type": { "kind": "instance_of", "type": { @@ -118095,10 +119667,8 @@ } }, { - "description": "Controls how many documents on a particular shard have to contain a pair of terms before the connection is returned for global consideration.", - "name": "shard_min_doc_count", - "required": false, - "serverDefault": 2, + "name": "positionLength", + "required": true, "type": { "kind": "instance_of", "type": { @@ -118108,41 +119678,40 @@ } }, { - "description": "Specifies the maximum number of vertex terms returned for each field.", - "name": "size", - "required": false, - "serverDefault": 5, + "name": "start_offset", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "integer", + "name": "long", "namespace": "_types" } } - } - ], - "specLocation": "graph/_types/Vertex.ts#L30-L59" - }, - { - "kind": "interface", - "name": { - "name": "VertexInclude", - "namespace": "graph._types" - }, - "properties": [ + }, { - "name": "boost", + "name": "termFrequency", "required": true, "type": { "kind": "instance_of", "type": { - "name": "double", + "name": "long", "namespace": "_types" } } }, { - "name": "term", + "name": "token", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "name": "type", "required": true, "type": { "kind": "instance_of", @@ -118153,111 +119722,110 @@ } } ], - "specLocation": "graph/_types/Vertex.ts#L61-L64" + "specLocation": "indices/analyze/types.ts#L52-L67" }, { "kind": "interface", "name": { - "name": "ExploreControls", - "namespace": "graph._types" + "name": "CharFilterDetail", + "namespace": "indices.analyze" }, "properties": [ { - "description": "To avoid the top-matching documents sample being dominated by a single source of results, it is sometimes necessary to request diversity in the sample.\nYou can do this by selecting a single-value field and setting a maximum number of documents per value for that field.", - "name": "sample_diversity", - "required": false, + "name": "filtered_text", + "required": true, "type": { - "kind": "instance_of", - "type": { - "name": "SampleDiversity", - "namespace": "graph._types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } } }, { - "description": "Each hop considers a sample of the best-matching documents on each shard.\nUsing samples improves the speed of execution and keeps exploration focused on meaningfully-connected terms.\nVery small values (less than 50) might not provide sufficient weight-of-evidence to identify significant connections between terms.\nVery large sample sizes can dilute the quality of the results and increase execution times.", - "name": "sample_size", - "required": false, - "serverDefault": 100, + "name": "name", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "integer", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } - }, + } + ], + "specLocation": "indices/analyze/types.ts#L46-L49" + }, + { + "kind": "interface", + "name": { + "name": "TokenDetail", + "namespace": "indices.analyze" + }, + "properties": [ { - "description": "The length of time in milliseconds after which exploration will be halted and the results gathered so far are returned.\nThis timeout is honored on a best-effort basis.\nExecution might overrun this timeout if, for example, a long pause is encountered while FieldData is loaded for a field.", - "name": "timeout", - "required": false, + "name": "name", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Duration", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Filters associated terms so only those that are significantly associated with your query are included.", - "docId": "search-aggregations-bucket-significantterms-aggregation", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/search-aggregations-bucket-significantterms-aggregation.html", - "name": "use_significance", + "name": "tokens", "required": true, "type": { - "kind": "instance_of", - "type": { - "name": "boolean", - "namespace": "_builtins" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "ExplainAnalyzeToken", + "namespace": "indices.analyze" + } } } } ], - "specLocation": "graph/_types/ExploreControls.ts#L24-L49" + "specLocation": "indices/analyze/types.ts#L71-L74" }, { "kind": "interface", "name": { - "name": "SampleDiversity", - "namespace": "graph._types" + "name": "AnalyzeToken", + "namespace": "indices.analyze" }, "properties": [ { - "name": "field", + "name": "end_offset", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Field", + "name": "long", "namespace": "_types" } } }, { - "name": "max_docs_per_value", + "name": "position", "required": true, "type": { "kind": "instance_of", "type": { - "name": "integer", + "name": "long", "namespace": "_types" } } - } - ], - "specLocation": "graph/_types/ExploreControls.ts#L51-L54" - }, - { - "kind": "interface", - "name": { - "name": "Connection", - "namespace": "graph._types" - }, - "properties": [ + }, { - "name": "doc_count", - "required": true, + "name": "positionLength", + "required": false, "type": { "kind": "instance_of", "type": { @@ -118267,7 +119835,7 @@ } }, { - "name": "source", + "name": "start_offset", "required": true, "type": { "kind": "instance_of", @@ -118278,93 +119846,145 @@ } }, { - "name": "target", + "name": "token", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "weight", + "name": "type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "double", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "graph/_types/Connection.ts#L22-L27" + "specLocation": "indices/analyze/types.ts#L37-L44" }, { "kind": "interface", "name": { - "name": "Vertex", - "namespace": "graph._types" + "name": "DataStreamsStatsItem", + "namespace": "indices.data_streams_stats" }, "properties": [ { - "name": "depth", + "description": "Current number of backing indices for the data stream.", + "name": "backing_indices", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "integer", "namespace": "_types" } } }, { - "name": "field", + "description": "Name of the data stream.", + "name": "data_stream", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Field", + "name": "Name", "namespace": "_types" } } }, { - "name": "term", + "description": "The data stream’s highest `@timestamp` value, converted to milliseconds since the Unix epoch.\nNOTE: This timestamp is provided as a best effort.\nThe data stream may contain `@timestamp` values higher than this if one or more of the following conditions are met:\nThe stream contains closed backing indices;\nBacking indices with a lower generation contain higher `@timestamp` values.", + "name": "maximum_timestamp", "required": true, + "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitMillis", + "namespace": "_types" + } + } + ], + "kind": "instance_of", + "type": { + "name": "EpochTime", + "namespace": "_types" + } + } + }, + { + "description": "Total size of all shards for the data stream’s backing indices.\nThis parameter is only returned if the `human` query parameter is `true`.", + "name": "store_size", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "ByteSize", + "namespace": "_types" } } }, { - "name": "weight", + "description": "Total size, in bytes, of all shards for the data stream’s backing indices.", + "name": "store_size_bytes", "required": true, "type": { "kind": "instance_of", "type": { - "name": "double", + "name": "long", "namespace": "_types" } } } ], - "specLocation": "graph/_types/Vertex.ts#L23-L28" + "specLocation": "indices/data_streams_stats/IndicesDataStreamsStatsResponse.ts#L45-L65" + }, + { + "inherits": { + "type": { + "name": "AcknowledgedResponseBase", + "namespace": "_types" + } + }, + "kind": "interface", + "name": { + "name": "IndicesResponseBase", + "namespace": "_types" + }, + "properties": [ + { + "name": "_shards", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "ShardStatistics", + "namespace": "_types" + } + } + } + ], + "specLocation": "_types/Base.ts#L138-L140" }, { "kind": "interface", "name": { - "name": "IndicesBlockStatus", - "namespace": "indices.add_block" + "name": "DataStreamLifecycleExplain", + "namespace": "indices.explain_data_lifecycle" }, "properties": [ { - "name": "name", + "name": "index", "required": true, "type": { "kind": "instance_of", @@ -118375,7 +119995,7 @@ } }, { - "name": "blocked", + "name": "managed_by_lifecycle", "required": true, "type": { "kind": "instance_of", @@ -118384,174 +120004,193 @@ "namespace": "_builtins" } } - } - ], - "specLocation": "indices/add_block/IndicesAddBlockResponse.ts#L30-L33" - }, - { - "kind": "interface", - "name": { - "name": "AnalyzeDetail", - "namespace": "indices.analyze" - }, - "properties": [ + }, { - "name": "analyzer", + "name": "index_creation_date_millis", "required": false, "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitMillis", + "namespace": "_types" + } + } + ], "kind": "instance_of", "type": { - "name": "AnalyzerDetail", - "namespace": "indices.analyze" + "name": "EpochTime", + "namespace": "_types" } } }, { - "name": "charfilters", + "name": "time_since_index_creation", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "CharFilterDetail", - "namespace": "indices.analyze" - } + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" } } }, { - "name": "custom_analyzer", - "required": true, + "name": "rollover_date_millis", + "required": false, "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitMillis", + "namespace": "_types" + } + } + ], "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "EpochTime", + "namespace": "_types" } } }, { - "name": "tokenfilters", + "name": "time_since_rollover", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "TokenDetail", - "namespace": "indices.analyze" - } + "kind": "instance_of", + "type": { + "name": "Duration", + "namespace": "_types" } } }, { - "name": "tokenizer", + "name": "lifecycle", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TokenDetail", - "namespace": "indices.analyze" + "name": "DataStreamLifecycleWithRollover", + "namespace": "indices._types" } } - } - ], - "specLocation": "indices/analyze/types.ts#L24-L30" - }, - { - "kind": "interface", - "name": { - "name": "AnalyzerDetail", - "namespace": "indices.analyze" - }, - "properties": [ + }, { - "name": "name", - "required": true, + "name": "generation_time", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "Duration", + "namespace": "_types" } } }, { - "name": "tokens", - "required": true, + "name": "error", + "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "ExplainAnalyzeToken", - "namespace": "indices.analyze" - } + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "indices/analyze/types.ts#L32-L35" + "specLocation": "indices/explain_data_lifecycle/IndicesExplainDataLifecycleResponse.ts#L31-L41" }, { - "attachedBehaviors": [ - "AdditionalProperties" - ], - "behaviors": [ - { - "generics": [ - { + "kind": "interface", + "name": { + "name": "IndexAliases", + "namespace": "indices.get_alias" + }, + "properties": [ + { + "name": "aliases", + "required": true, + "type": { + "key": { "kind": "instance_of", "type": { "name": "string", "namespace": "_builtins" } }, - { - "kind": "user_defined_value" + "kind": "dictionary_of", + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "AliasDefinition", + "namespace": "indices._types" + } } - ], - "meta": { - "description": "Additional tokenizer-specific attributes", - "fieldname": "attributes" - }, - "type": { - "name": "AdditionalProperties", - "namespace": "_spec_utils" } } ], + "specLocation": "indices/get_alias/IndicesGetAliasResponse.ts#L37-L39" + }, + { "kind": "interface", "name": { - "name": "ExplainAnalyzeToken", - "namespace": "indices.analyze" + "name": "DataStreamWithLifecycle", + "namespace": "indices.get_data_lifecycle" }, "properties": [ { - "name": "bytes", + "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "DataStreamName", + "namespace": "_types" } } }, { - "name": "end_offset", - "required": true, + "name": "lifecycle", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "DataStreamLifecycleWithRollover", + "namespace": "indices._types" + } + } + } + ], + "specLocation": "indices/get_data_lifecycle/IndicesGetDataLifecycleResponse.ts#L27-L30" + }, + { + "kind": "interface", + "name": { + "name": "DataStream", + "namespace": "indices._types" + }, + "properties": [ + { + "description": "Custom metadata for the stream, copied from the `_meta` object of the stream’s matching index template.\nIf empty, the response omits this property.", + "docId": "mapping-meta-field", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/mapping-meta-field.html", + "name": "_meta", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "Metadata", "namespace": "_types" } } }, { - "name": "keyword", + "description": "If `true`, the data stream allows custom routing on write request.", + "name": "allow_custom_routing", "required": false, "type": { "kind": "instance_of", @@ -118562,469 +120201,539 @@ } }, { - "name": "position", - "required": true, + "description": "Information about failure store backing indices", + "name": "failure_store", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "FailureStore", + "namespace": "indices._types" } } }, { - "name": "positionLength", + "description": "Current generation for the data stream. This number acts as a cumulative count of the stream’s rollovers, starting at 1.", + "name": "generation", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "integer", "namespace": "_types" } } }, { - "name": "start_offset", + "description": "If `true`, the data stream is hidden.", + "name": "hidden", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "termFrequency", - "required": true, + "description": "Name of the current ILM lifecycle policy in the stream’s matching index template.\nThis lifecycle policy is set in the `index.lifecycle.name` setting.\nIf the template does not include a lifecycle policy, this property is not included in the response.\nNOTE: A data stream’s backing indices may be assigned different lifecycle policies. To retrieve the lifecycle policy for individual backing indices, use the get index settings API.", + "name": "ilm_policy", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "Name", "namespace": "_types" } } }, { - "name": "token", + "description": "Name of the lifecycle system that'll manage the next generation of the data stream.", + "name": "next_generation_managed_by", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "ManagedBy", + "namespace": "indices._types" } } }, { - "name": "type", + "description": "Indicates if ILM should take precedence over DSL in case both are configured to managed this data stream.", + "name": "prefer_ilm", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", + "name": "boolean", "namespace": "_builtins" } } - } - ], - "specLocation": "indices/analyze/types.ts#L52-L67" - }, - { - "kind": "interface", - "name": { - "name": "CharFilterDetail", - "namespace": "indices.analyze" - }, - "properties": [ + }, { - "name": "filtered_text", + "description": "Array of objects containing information about the data stream’s backing indices.\nThe last item in this array contains information about the stream’s current write index.", + "name": "indices", "required": true, "type": { "kind": "array_of", "value": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "DataStreamIndex", + "namespace": "indices._types" } } } }, { - "name": "name", - "required": true, + "availability": { + "serverless": { + "stability": "stable" + }, + "stack": { + "since": "8.11.0", + "stability": "stable" + } + }, + "description": "Contains the configuration for the data stream lifecycle of this data stream.", + "name": "lifecycle", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "DataStreamLifecycleWithRollover", + "namespace": "indices._types" } } - } - ], - "specLocation": "indices/analyze/types.ts#L46-L49" - }, - { - "kind": "interface", - "name": { - "name": "TokenDetail", - "namespace": "indices.analyze" - }, - "properties": [ + }, { + "description": "Name of the data stream.", "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "DataStreamName", + "namespace": "_types" } } }, { - "name": "tokens", - "required": true, + "description": "If `true`, the data stream is created and managed by cross-cluster replication and the local cluster can not write into this data stream or change its mappings.", + "name": "replicated", + "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "ExplainAnalyzeToken", - "namespace": "indices.analyze" - } + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" } } - } - ], - "specLocation": "indices/analyze/types.ts#L71-L74" - }, - { - "kind": "interface", - "name": { - "name": "AnalyzeToken", - "namespace": "indices.analyze" - }, - "properties": [ + }, { - "name": "end_offset", + "description": "If `true`, the next write to this data stream will trigger a rollover first and the document will be indexed in the new backing index. If the rollover fails the indexing request will fail too.", + "name": "rollover_on_write", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "position", + "description": "Health status of the data stream.\nThis health status is based on the state of the primary and replica shards of the stream’s backing indices.", + "name": "status", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "HealthStatus", "namespace": "_types" } } }, { - "name": "positionLength", + "availability": { + "serverless": {}, + "stack": { + "since": "7.10.0" + } + }, + "description": "If `true`, the data stream is created and managed by an Elastic stack component and cannot be modified through normal user interaction.", + "name": "system", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "start_offset", + "description": "Name of the index template used to create the data stream’s backing indices.\nThe template’s index pattern must match the name of this data stream.", + "name": "template", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "Name", "namespace": "_types" } } }, { - "name": "token", + "description": "Information about the `@timestamp` field in the data stream.", + "name": "timestamp_field", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", + "name": "DataStreamTimestampField", + "namespace": "indices._types" + } + } + } + ], + "specLocation": "indices/_types/DataStream.ts#L45-L127" + }, + { + "kind": "interface", + "name": { + "name": "FailureStore", + "namespace": "indices._types" + }, + "properties": [ + { + "name": "enabled", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", "namespace": "_builtins" } } }, { - "name": "type", + "name": "indices", + "required": true, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "DataStreamIndex", + "namespace": "indices._types" + } + } + } + }, + { + "name": "rollover_on_write", "required": true, "type": { "kind": "instance_of", "type": { - "name": "string", + "name": "boolean", "namespace": "_builtins" } } } ], - "specLocation": "indices/analyze/types.ts#L37-L44" + "specLocation": "indices/_types/DataStream.ts#L39-L43" }, { "kind": "interface", "name": { - "name": "DataStreamsStatsItem", - "namespace": "indices.data_streams_stats" + "name": "DataStreamIndex", + "namespace": "indices._types" }, "properties": [ { - "description": "Current number of backing indices for the data stream.", - "name": "backing_indices", + "description": "Name of the backing index.", + "name": "index_name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "integer", + "name": "IndexName", "namespace": "_types" } } }, { - "description": "Name of the data stream.", - "name": "data_stream", + "description": "Universally unique identifier (UUID) for the index.", + "name": "index_uuid", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Name", + "name": "Uuid", "namespace": "_types" } } }, { - "description": "The data stream’s highest `@timestamp` value, converted to milliseconds since the Unix epoch.\nNOTE: This timestamp is provided as a best effort.\nThe data stream may contain `@timestamp` values higher than this if one or more of the following conditions are met:\nThe stream contains closed backing indices;\nBacking indices with a lower generation contain higher `@timestamp` values.", - "name": "maximum_timestamp", - "required": true, + "description": "Name of the current ILM lifecycle policy configured for this backing index.", + "name": "ilm_policy", + "required": false, "type": { - "generics": [ - { - "kind": "instance_of", - "type": { - "name": "UnitMillis", - "namespace": "_types" - } - } - ], "kind": "instance_of", "type": { - "name": "EpochTime", + "name": "Name", "namespace": "_types" } } }, { - "description": "Total size of all shards for the data stream’s backing indices.\nThis parameter is only returned if the `human` query parameter is `true`.", - "name": "store_size", + "description": "Name of the lifecycle system that's currently managing this backing index.", + "name": "managed_by", "required": false, "type": { "kind": "instance_of", "type": { - "name": "ByteSize", - "namespace": "_types" + "name": "ManagedBy", + "namespace": "indices._types" } } }, { - "description": "Total size, in bytes, of all shards for the data stream’s backing indices.", - "name": "store_size_bytes", + "description": "Indicates if ILM should take precedence over DSL in case both are configured to manage this index.", + "name": "prefer_ilm", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "indices/_types/DataStream.ts#L136-L157" + }, + { + "kind": "interface", + "name": { + "name": "DataStreamTimestampField", + "namespace": "indices._types" + }, + "properties": [ + { + "description": "Name of the timestamp field for the data stream, which must be `@timestamp`. The `@timestamp` field must be included in every document indexed to the data stream.", + "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "Field", "namespace": "_types" } } } ], - "specLocation": "indices/data_streams_stats/IndicesDataStreamsStatsResponse.ts#L45-L65" + "specLocation": "indices/_types/DataStream.ts#L129-L134" }, { - "inherits": { - "type": { - "name": "AcknowledgedResponseBase", - "namespace": "_types" - } - }, "kind": "interface", "name": { - "name": "IndicesResponseBase", - "namespace": "_types" + "name": "IndexTemplateItem", + "namespace": "indices.get_index_template" }, "properties": [ { - "name": "_shards", - "required": false, + "name": "name", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "ShardStatistics", + "name": "Name", "namespace": "_types" } } + }, + { + "name": "index_template", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "IndexTemplate", + "namespace": "indices._types" + } + } } ], - "specLocation": "_types/Base.ts#L138-L140" + "specLocation": "indices/get_index_template/IndicesGetIndexTemplateResponse.ts#L29-L32" }, { "kind": "interface", "name": { - "name": "DataStreamLifecycleExplain", - "namespace": "indices.explain_data_lifecycle" + "name": "IndexTemplate", + "namespace": "indices._types" }, "properties": [ { - "name": "index", + "description": "Name of the index template.", + "name": "index_patterns", "required": true, "type": { "kind": "instance_of", "type": { - "name": "IndexName", + "name": "Names", "namespace": "_types" } } }, { - "name": "managed_by_lifecycle", + "description": "An ordered list of component template names.\nComponent templates are merged in the order specified, meaning that the last component template specified has the highest precedence.", + "name": "composed_of", "required": true, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "Name", + "namespace": "_types" + } + } + } + }, + { + "description": "Template to be applied.\nIt may optionally include an `aliases`, `mappings`, or `settings` configuration.", + "name": "template", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "IndexTemplateSummary", + "namespace": "indices._types" } } }, { - "name": "index_creation_date_millis", + "description": "Version number used to manage index templates externally.\nThis number is not automatically generated by Elasticsearch.", + "name": "version", "required": false, "type": { - "generics": [ - { - "kind": "instance_of", - "type": { - "name": "UnitMillis", - "namespace": "_types" - } - } - ], "kind": "instance_of", "type": { - "name": "EpochTime", + "name": "VersionNumber", "namespace": "_types" } } }, { - "name": "time_since_index_creation", + "description": "Priority to determine index template precedence when a new data stream or index is created.\nThe index template with the highest priority is chosen.\nIf no priority is specified the template is treated as though it is of priority 0 (lowest priority).\nThis number is not automatically generated by Elasticsearch.", + "name": "priority", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Duration", + "name": "long", "namespace": "_types" } } }, { - "name": "rollover_date_millis", + "description": "Optional user metadata about the index template. May have any contents.\nThis map is not automatically generated by Elasticsearch.", + "docId": "mapping-meta-field", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/mapping-meta-field.html", + "name": "_meta", "required": false, "type": { - "generics": [ - { - "kind": "instance_of", - "type": { - "name": "UnitMillis", - "namespace": "_types" - } - } - ], "kind": "instance_of", "type": { - "name": "EpochTime", + "name": "Metadata", "namespace": "_types" } } }, { - "name": "time_since_rollover", + "name": "allow_auto_create", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Duration", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "lifecycle", + "description": "If this object is included, the template is used to create data streams and their backing indices.\nSupports an empty object.\nData streams require a matching index template with a `data_stream` object.", + "name": "data_stream", "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamLifecycleWithRollover", + "name": "IndexTemplateDataStreamConfiguration", "namespace": "indices._types" } } }, { - "name": "generation_time", + "availability": { + "serverless": {}, + "stack": { + "since": "8.12.0" + } + }, + "description": "Marks this index template as deprecated.\nWhen creating or updating a non-deprecated index template that uses deprecated components,\nElasticsearch will emit a deprecation warning.", + "name": "deprecated", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Duration", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "name": "error", + "availability": { + "serverless": {}, + "stack": { + "since": "8.7.0" + } + }, + "description": "A list of component template names that are allowed to be absent.", + "name": "ignore_missing_component_templates", "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "Names", + "namespace": "_types" } } } ], - "specLocation": "indices/explain_data_lifecycle/IndicesExplainDataLifecycleResponse.ts#L31-L41" + "specLocation": "indices/_types/IndexTemplate.ts#L28-L81" }, { "kind": "interface", "name": { - "name": "IndexAliases", - "namespace": "indices.get_alias" + "name": "IndexTemplateSummary", + "namespace": "indices._types" }, "properties": [ { + "description": "Aliases to add.\nIf the index template includes a `data_stream` object, these are data stream aliases.\nOtherwise, these are index aliases.\nData stream aliases ignore the `index_routing`, `routing`, and `search_routing` options.", "name": "aliases", - "required": true, + "required": false, "type": { "key": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "IndexName", + "namespace": "_types" } }, "kind": "dictionary_of", @@ -119032,34 +120741,46 @@ "value": { "kind": "instance_of", "type": { - "name": "AliasDefinition", + "name": "Alias", "namespace": "indices._types" } } } - } - ], - "specLocation": "indices/get_alias/IndicesGetAliasResponse.ts#L37-L39" - }, - { - "kind": "interface", - "name": { - "name": "DataStreamWithLifecycle", - "namespace": "indices.get_data_lifecycle" - }, - "properties": [ + }, { - "name": "name", - "required": true, + "description": "Mapping for fields in the index.\nIf specified, this mapping can include field names, field data types, and mapping parameters.", + "name": "mappings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "TypeMapping", + "namespace": "_types.mapping" + } + } + }, + { + "description": "Configuration options for the index.", + "name": "settings", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamName", - "namespace": "_types" + "name": "IndexSettings", + "namespace": "indices._types" } } }, { + "availability": { + "serverless": { + "stability": "stable" + }, + "stack": { + "since": "8.11.0", + "stability": "stable" + } + }, "name": "lifecycle", "required": false, "type": { @@ -119071,33 +120792,33 @@ } } ], - "specLocation": "indices/get_data_lifecycle/IndicesGetDataLifecycleResponse.ts#L27-L30" + "specLocation": "indices/_types/IndexTemplate.ts#L96-L118" }, { "kind": "interface", "name": { - "name": "DataStream", + "name": "IndexTemplateDataStreamConfiguration", "namespace": "indices._types" }, "properties": [ { - "description": "Custom metadata for the stream, copied from the `_meta` object of the stream’s matching index template.\nIf empty, the response omits this property.", - "docId": "mapping-meta-field", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/mapping-meta-field.html", - "name": "_meta", + "description": "If true, the data stream is hidden.", + "name": "hidden", "required": false, + "serverDefault": false, "type": { "kind": "instance_of", "type": { - "name": "Metadata", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "description": "If `true`, the data stream allows custom routing on write request.", + "description": "If true, the data stream supports custom routing.", "name": "allow_custom_routing", "required": false, + "serverDefault": false, "type": { "kind": "instance_of", "type": { @@ -119105,94 +120826,167 @@ "namespace": "_builtins" } } - }, + } + ], + "specLocation": "indices/_types/IndexTemplate.ts#L83-L94" + }, + { + "kind": "interface", + "name": { + "name": "IndexMappingRecord", + "namespace": "indices.get_mapping" + }, + "properties": [ { - "description": "Information about failure store backing indices", - "name": "failure_store", + "name": "item", "required": false, "type": { "kind": "instance_of", "type": { - "name": "FailureStore", - "namespace": "indices._types" + "name": "TypeMapping", + "namespace": "_types.mapping" } } }, { - "description": "Current generation for the data stream. This number acts as a cumulative count of the stream’s rollovers, starting at 1.", - "name": "generation", + "name": "mappings", "required": true, "type": { "kind": "instance_of", "type": { - "name": "integer", - "namespace": "_types" + "name": "TypeMapping", + "namespace": "_types.mapping" } } - }, + } + ], + "specLocation": "indices/get_mapping/IndicesGetMappingResponse.ts#L29-L32" + }, + { + "kind": "interface", + "name": { + "name": "Action", + "namespace": "indices.modify_data_stream" + }, + "properties": [ { - "description": "If `true`, the data stream is hidden.", - "name": "hidden", - "required": true, + "description": "Adds an existing index as a backing index for a data stream.\nThe index is hidden as part of this operation.\nWARNING: Adding indices with the `add_backing_index` action can potentially result in improper data stream behavior.\nThis should be considered an expert level API.", + "name": "add_backing_index", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "IndexAndDataStreamAction", + "namespace": "indices.modify_data_stream" } } }, { - "description": "Name of the current ILM lifecycle policy in the stream’s matching index template.\nThis lifecycle policy is set in the `index.lifecycle.name` setting.\nIf the template does not include a lifecycle policy, this property is not included in the response.\nNOTE: A data stream’s backing indices may be assigned different lifecycle policies. To retrieve the lifecycle policy for individual backing indices, use the get index settings API.", - "name": "ilm_policy", + "description": "Removes a backing index from a data stream.\nThe index is unhidden as part of this operation.\nA data stream’s write index cannot be removed.", + "name": "remove_backing_index", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Name", - "namespace": "_types" + "name": "IndexAndDataStreamAction", + "namespace": "indices.modify_data_stream" } } - }, + } + ], + "specLocation": "indices/modify_data_stream/types.ts#L22-L37", + "variants": { + "kind": "container" + } + }, + { + "kind": "interface", + "name": { + "name": "IndexAndDataStreamAction", + "namespace": "indices.modify_data_stream" + }, + "properties": [ { - "description": "Name of the lifecycle system that'll manage the next generation of the data stream.", - "name": "next_generation_managed_by", + "description": "Data stream targeted by the action.", + "name": "data_stream", "required": true, "type": { "kind": "instance_of", "type": { - "name": "ManagedBy", - "namespace": "indices._types" + "name": "DataStreamName", + "namespace": "_types" } } }, { - "description": "Indicates if ILM should take precedence over DSL in case both are configured to managed this data stream.", - "name": "prefer_ilm", + "description": "Index for the action.", + "name": "index", "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "IndexName", + "namespace": "_types" } } - }, + } + ], + "specLocation": "indices/modify_data_stream/types.ts#L39-L44" + }, + { + "kind": "interface", + "name": { + "name": "IndexTemplateMapping", + "namespace": "indices.put_index_template" + }, + "properties": [ { - "description": "Array of objects containing information about the data stream’s backing indices.\nThe last item in this array contains information about the stream’s current write index.", - "name": "indices", - "required": true, + "description": "Aliases to add.\nIf the index template includes a `data_stream` object, these are data stream aliases.\nOtherwise, these are index aliases.\nData stream aliases ignore the `index_routing`, `routing`, and `search_routing` options.", + "name": "aliases", + "required": false, "type": { - "kind": "array_of", + "key": { + "kind": "instance_of", + "type": { + "name": "IndexName", + "namespace": "_types" + } + }, + "kind": "dictionary_of", + "singleKey": false, "value": { "kind": "instance_of", "type": { - "name": "DataStreamIndex", + "name": "Alias", "namespace": "indices._types" } } } }, + { + "description": "Mapping for fields in the index.\nIf specified, this mapping can include field names, field data types, and mapping parameters.", + "name": "mappings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "TypeMapping", + "namespace": "_types.mapping" + } + } + }, + { + "description": "Configuration options for the index.", + "name": "settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "IndexSettings", + "namespace": "indices._types" + } + } + }, { "availability": { "serverless": { @@ -119203,32 +120997,39 @@ "stability": "stable" } }, - "description": "Contains the configuration for the data stream lifecycle of this data stream.", "name": "lifecycle", "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamLifecycleWithRollover", + "name": "DataStreamLifecycle", "namespace": "indices._types" } } - }, + } + ], + "specLocation": "indices/put_index_template/IndicesPutIndexTemplateRequest.ts#L159-L181" + }, + { + "kind": "interface", + "name": { + "name": "DataStreamVisibility", + "namespace": "indices._types" + }, + "properties": [ { - "description": "Name of the data stream.", - "name": "name", - "required": true, + "name": "hidden", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamName", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "description": "If `true`, the data stream is created and managed by cross-cluster replication and the local cluster can not write into this data stream or change its mappings.", - "name": "replicated", + "name": "allow_custom_routing", "required": false, "type": { "kind": "instance_of", @@ -119237,52 +121038,100 @@ "namespace": "_builtins" } } - }, + } + ], + "specLocation": "indices/_types/DataStream.ts#L159-L162" + }, + { + "kind": "interface", + "name": { + "name": "ShardsOperationResponseBase", + "namespace": "_types" + }, + "properties": [ { - "description": "If `true`, the next write to this data stream will trigger a rollover first and the document will be indexed in the new backing index. If the rollover fails the indexing request will fail too.", - "name": "rollover_on_write", - "required": true, + "name": "_shards", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "ShardStatistics", + "namespace": "_types" } } - }, + } + ], + "specLocation": "_types/Base.ts#L142-L145" + }, + { + "kind": "interface", + "name": { + "name": "ResolveIndexItem", + "namespace": "indices.resolve_index" + }, + "properties": [ { - "description": "Health status of the data stream.\nThis health status is based on the state of the primary and replica shards of the stream’s backing indices.", - "name": "status", + "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "HealthStatus", + "name": "Name", "namespace": "_types" } } }, { - "availability": { - "serverless": {}, - "stack": { - "since": "7.10.0" + "name": "aliases", + "required": false, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } - }, - "description": "If `true`, the data stream is created and managed by an Elastic stack component and cannot be modified through normal user interaction.", - "name": "system", + } + }, + { + "name": "attributes", + "required": true, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + }, + { + "name": "data_stream", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "DataStreamName", + "namespace": "_types" } } - }, + } + ], + "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L30-L35" + }, + { + "kind": "interface", + "name": { + "name": "ResolveIndexAliasItem", + "namespace": "indices.resolve_index" + }, + "properties": [ { - "description": "Name of the index template used to create the data stream’s backing indices.\nThe template’s index pattern must match the name of this data stream.", - "name": "template", + "name": "name", "required": true, "type": { "kind": "instance_of", @@ -119293,347 +121142,291 @@ } }, { - "description": "Information about the `@timestamp` field in the data stream.", - "name": "timestamp_field", + "name": "indices", "required": true, "type": { "kind": "instance_of", "type": { - "name": "DataStreamTimestampField", - "namespace": "indices._types" + "name": "Indices", + "namespace": "_types" } } } ], - "specLocation": "indices/_types/DataStream.ts#L45-L127" + "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L37-L40" }, { "kind": "interface", "name": { - "name": "FailureStore", - "namespace": "indices._types" + "name": "ResolveIndexDataStreamsItem", + "namespace": "indices.resolve_index" }, "properties": [ { - "name": "enabled", + "name": "name", "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "DataStreamName", + "namespace": "_types" } } }, { - "name": "indices", + "name": "timestamp_field", "required": true, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "DataStreamIndex", - "namespace": "indices._types" - } + "kind": "instance_of", + "type": { + "name": "Field", + "namespace": "_types" } } }, { - "name": "rollover_on_write", + "name": "backing_indices", "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "Indices", + "namespace": "_types" } } } ], - "specLocation": "indices/_types/DataStream.ts#L39-L43" + "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L42-L46" }, { "kind": "interface", "name": { - "name": "DataStreamIndex", - "namespace": "indices._types" + "name": "RolloverConditions", + "namespace": "indices.rollover" }, "properties": [ { - "description": "Name of the backing index.", - "name": "index_name", - "required": true, + "name": "min_age", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexName", + "name": "Duration", "namespace": "_types" } } }, { - "description": "Universally unique identifier (UUID) for the index.", - "name": "index_uuid", - "required": true, + "name": "max_age", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Uuid", + "name": "Duration", "namespace": "_types" } } }, { - "description": "Name of the current ILM lifecycle policy configured for this backing index.", - "name": "ilm_policy", + "name": "max_age_millis", "required": false, "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitMillis", + "namespace": "_types" + } + } + ], "kind": "instance_of", "type": { - "name": "Name", + "name": "DurationValue", "namespace": "_types" } } }, { - "description": "Name of the lifecycle system that's currently managing this backing index.", - "name": "managed_by", + "name": "min_docs", "required": false, "type": { "kind": "instance_of", "type": { - "name": "ManagedBy", - "namespace": "indices._types" + "name": "long", + "namespace": "_types" } } }, { - "description": "Indicates if ILM should take precedence over DSL in case both are configured to manage this index.", - "name": "prefer_ilm", + "name": "max_docs", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "long", + "namespace": "_types" } } - } - ], - "specLocation": "indices/_types/DataStream.ts#L136-L157" - }, - { - "kind": "interface", - "name": { - "name": "DataStreamTimestampField", - "namespace": "indices._types" - }, - "properties": [ + }, { - "description": "Name of the timestamp field for the data stream, which must be `@timestamp`. The `@timestamp` field must be included in every document indexed to the data stream.", - "name": "name", - "required": true, + "name": "max_size", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Field", + "name": "ByteSize", "namespace": "_types" } } - } - ], - "specLocation": "indices/_types/DataStream.ts#L129-L134" - }, - { - "kind": "interface", - "name": { - "name": "IndexTemplateItem", - "namespace": "indices.get_index_template" - }, - "properties": [ + }, { - "name": "name", - "required": true, + "name": "max_size_bytes", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Name", + "name": "long", "namespace": "_types" } } }, { - "name": "index_template", - "required": true, + "name": "min_size", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexTemplate", - "namespace": "indices._types" + "name": "ByteSize", + "namespace": "_types" } } - } - ], - "specLocation": "indices/get_index_template/IndicesGetIndexTemplateResponse.ts#L29-L32" - }, - { - "kind": "interface", - "name": { - "name": "IndexTemplate", - "namespace": "indices._types" - }, - "properties": [ + }, { - "description": "Name of the index template.", - "name": "index_patterns", - "required": true, + "name": "min_size_bytes", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Names", + "name": "long", "namespace": "_types" } } }, { - "description": "An ordered list of component template names.\nComponent templates are merged in the order specified, meaning that the last component template specified has the highest precedence.", - "name": "composed_of", - "required": true, - "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "Name", - "namespace": "_types" - } - } - } - }, - { - "description": "Template to be applied.\nIt may optionally include an `aliases`, `mappings`, or `settings` configuration.", - "name": "template", + "name": "max_primary_shard_size", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexTemplateSummary", - "namespace": "indices._types" + "name": "ByteSize", + "namespace": "_types" } } }, { - "description": "Version number used to manage index templates externally.\nThis number is not automatically generated by Elasticsearch.", - "name": "version", + "name": "max_primary_shard_size_bytes", "required": false, "type": { "kind": "instance_of", "type": { - "name": "VersionNumber", + "name": "long", "namespace": "_types" } } }, { - "description": "Priority to determine index template precedence when a new data stream or index is created.\nThe index template with the highest priority is chosen.\nIf no priority is specified the template is treated as though it is of priority 0 (lowest priority).\nThis number is not automatically generated by Elasticsearch.", - "name": "priority", + "name": "min_primary_shard_size", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "ByteSize", "namespace": "_types" } } }, { - "description": "Optional user metadata about the index template. May have any contents.\nThis map is not automatically generated by Elasticsearch.", - "docId": "mapping-meta-field", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/mapping-meta-field.html", - "name": "_meta", + "name": "min_primary_shard_size_bytes", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Metadata", + "name": "long", "namespace": "_types" } } }, { - "name": "allow_auto_create", + "name": "max_primary_shard_docs", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "long", + "namespace": "_types" } } }, { - "description": "If this object is included, the template is used to create data streams and their backing indices.\nSupports an empty object.\nData streams require a matching index template with a `data_stream` object.", - "name": "data_stream", + "name": "min_primary_shard_docs", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexTemplateDataStreamConfiguration", - "namespace": "indices._types" + "name": "long", + "namespace": "_types" } } - }, - { - "availability": { - "serverless": {}, - "stack": { - "since": "8.12.0" - } - }, - "description": "Marks this index template as deprecated.\nWhen creating or updating a non-deprecated index template that uses deprecated components,\nElasticsearch will emit a deprecation warning.", - "name": "deprecated", - "required": false, + } + ], + "specLocation": "indices/rollover/types.ts#L24-L40" + }, + { + "kind": "interface", + "name": { + "name": "Overlapping", + "namespace": "indices.simulate_template" + }, + "properties": [ + { + "name": "name", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "Name", + "namespace": "_types" } } }, { - "availability": { - "serverless": {}, - "stack": { - "since": "8.7.0" - } - }, - "description": "A list of component template names that are allowed to be absent.", - "name": "ignore_missing_component_templates", - "required": false, + "name": "index_patterns", + "required": true, "type": { - "kind": "instance_of", - "type": { - "name": "Names", - "namespace": "_types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } } } ], - "specLocation": "indices/_types/IndexTemplate.ts#L28-L81" + "specLocation": "indices/simulate_template/IndicesSimulateTemplateResponse.ts#L39-L42" }, { "kind": "interface", "name": { - "name": "IndexTemplateSummary", - "namespace": "indices._types" + "name": "Template", + "namespace": "indices.simulate_template" }, "properties": [ { - "description": "Aliases to add.\nIf the index template includes a `data_stream` object, these are data stream aliases.\nOtherwise, these are index aliases.\nData stream aliases ignore the `index_routing`, `routing`, and `search_routing` options.", "name": "aliases", - "required": false, + "required": true, "type": { "key": { "kind": "instance_of", @@ -119654,9 +121447,8 @@ } }, { - "description": "Mapping for fields in the index.\nIf specified, this mapping can include field names, field data types, and mapping parameters.", "name": "mappings", - "required": false, + "required": true, "type": { "kind": "instance_of", "type": { @@ -119666,9 +121458,8 @@ } }, { - "description": "Configuration options for the index.", "name": "settings", - "required": false, + "required": true, "type": { "kind": "instance_of", "type": { @@ -119676,158 +121467,121 @@ "namespace": "indices._types" } } - }, - { - "availability": { - "serverless": { - "stability": "stable" - }, - "stack": { - "since": "8.11.0", - "stability": "stable" - } - }, - "name": "lifecycle", - "required": false, - "type": { - "kind": "instance_of", - "type": { - "name": "DataStreamLifecycleWithRollover", - "namespace": "indices._types" - } - } } ], - "specLocation": "indices/_types/IndexTemplate.ts#L96-L118" + "specLocation": "indices/simulate_template/IndicesSimulateTemplateResponse.ts#L33-L37" }, { "kind": "interface", "name": { - "name": "IndexTemplateDataStreamConfiguration", - "namespace": "indices._types" + "name": "Action", + "namespace": "indices.update_aliases" }, "properties": [ { - "description": "If true, the data stream is hidden.", - "name": "hidden", + "description": "Adds a data stream or index to an alias.\nIf the alias doesn’t exist, the `add` action creates it.", + "name": "add", "required": false, - "serverDefault": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "AddAction", + "namespace": "indices.update_aliases" } } }, { - "description": "If true, the data stream supports custom routing.", - "name": "allow_custom_routing", - "required": false, - "serverDefault": false, - "type": { - "kind": "instance_of", - "type": { - "name": "boolean", - "namespace": "_builtins" - } - } - } - ], - "specLocation": "indices/_types/IndexTemplate.ts#L83-L94" - }, - { - "kind": "interface", - "name": { - "name": "IndexMappingRecord", - "namespace": "indices.get_mapping" - }, - "properties": [ - { - "name": "item", + "description": "Removes a data stream or index from an alias.", + "name": "remove", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TypeMapping", - "namespace": "_types.mapping" + "name": "RemoveAction", + "namespace": "indices.update_aliases" } } }, { - "name": "mappings", - "required": true, + "description": "Deletes an index.\nYou cannot use this action on aliases or data streams.", + "name": "remove_index", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "TypeMapping", - "namespace": "_types.mapping" + "name": "RemoveIndexAction", + "namespace": "indices.update_aliases" } } } ], - "specLocation": "indices/get_mapping/IndicesGetMappingResponse.ts#L29-L32" + "specLocation": "indices/update_aliases/types.ts#L23-L39", + "variants": { + "kind": "container" + } }, { "kind": "interface", "name": { - "name": "Action", - "namespace": "indices.modify_data_stream" + "name": "AddAction", + "namespace": "indices.update_aliases" }, "properties": [ { - "description": "Adds an existing index as a backing index for a data stream.\nThe index is hidden as part of this operation.\nWARNING: Adding indices with the `add_backing_index` action can potentially result in improper data stream behavior.\nThis should be considered an expert level API.", - "name": "add_backing_index", + "description": "Alias for the action.\nIndex alias names support date math.", + "name": "alias", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexAndDataStreamAction", - "namespace": "indices.modify_data_stream" + "name": "IndexAlias", + "namespace": "_types" } } }, { - "description": "Removes a backing index from a data stream.\nThe index is unhidden as part of this operation.\nA data stream’s write index cannot be removed.", - "name": "remove_backing_index", + "description": "Aliases for the action.\nIndex alias names support date math.", + "name": "aliases", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "IndexAndDataStreamAction", - "namespace": "indices.modify_data_stream" - } + "items": [ + { + "kind": "instance_of", + "type": { + "name": "IndexAlias", + "namespace": "_types" + } + }, + { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "IndexAlias", + "namespace": "_types" + } + } + } + ], + "kind": "union_of" } - } - ], - "specLocation": "indices/modify_data_stream/types.ts#L22-L37", - "variants": { - "kind": "container" - } - }, - { - "kind": "interface", - "name": { - "name": "IndexAndDataStreamAction", - "namespace": "indices.modify_data_stream" - }, - "properties": [ + }, { - "description": "Data stream targeted by the action.", - "name": "data_stream", - "required": true, + "description": "Query used to limit documents the alias can access.", + "name": "filter", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamName", - "namespace": "_types" + "name": "QueryContainer", + "namespace": "_types.query_dsl" } } }, { - "description": "Index for the action.", + "description": "Data stream or index for the action.\nSupports wildcards (`*`).", "name": "index", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -119835,221 +121589,205 @@ "namespace": "_types" } } - } - ], - "specLocation": "indices/modify_data_stream/types.ts#L39-L44" - }, - { - "kind": "interface", - "name": { - "name": "IndexTemplateMapping", - "namespace": "indices.put_index_template" - }, - "properties": [ + }, { - "description": "Aliases to add.\nIf the index template includes a `data_stream` object, these are data stream aliases.\nOtherwise, these are index aliases.\nData stream aliases ignore the `index_routing`, `routing`, and `search_routing` options.", - "name": "aliases", + "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", + "name": "indices", "required": false, "type": { - "key": { - "kind": "instance_of", - "type": { - "name": "IndexName", - "namespace": "_types" - } - }, - "kind": "dictionary_of", - "singleKey": false, - "value": { - "kind": "instance_of", - "type": { - "name": "Alias", - "namespace": "indices._types" - } + "kind": "instance_of", + "type": { + "name": "Indices", + "namespace": "_types" } } }, { - "description": "Mapping for fields in the index.\nIf specified, this mapping can include field names, field data types, and mapping parameters.", - "name": "mappings", + "description": "Value used to route indexing operations to a specific shard.\nIf specified, this overwrites the `routing` value for indexing operations.\nData stream aliases don’t support this parameter.", + "name": "index_routing", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TypeMapping", - "namespace": "_types.mapping" + "name": "Routing", + "namespace": "_types" } } }, { - "description": "Configuration options for the index.", - "name": "settings", + "description": "If `true`, the alias is hidden.", + "name": "is_hidden", "required": false, + "serverDefault": false, "type": { "kind": "instance_of", "type": { - "name": "IndexSettings", - "namespace": "indices._types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "availability": { - "serverless": { - "stability": "stable" - }, - "stack": { - "since": "8.11.0", - "stability": "stable" - } - }, - "name": "lifecycle", + "description": "If `true`, sets the write index or data stream for the alias.", + "name": "is_write_index", "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamLifecycle", - "namespace": "indices._types" + "name": "boolean", + "namespace": "_builtins" } } - } - ], - "specLocation": "indices/put_index_template/IndicesPutIndexTemplateRequest.ts#L159-L181" - }, - { - "kind": "interface", - "name": { - "name": "DataStreamVisibility", - "namespace": "indices._types" - }, - "properties": [ + }, { - "name": "hidden", + "description": "Value used to route indexing and search operations to a specific shard.\nData stream aliases don’t support this parameter.", + "name": "routing", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "Routing", + "namespace": "_types" } } }, { - "name": "allow_custom_routing", + "description": "Value used to route search operations to a specific shard.\nIf specified, this overwrites the `routing` value for search operations.\nData stream aliases don’t support this parameter.", + "name": "search_routing", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "Routing", + "namespace": "_types" } } - } - ], - "specLocation": "indices/_types/DataStream.ts#L159-L162" - }, - { - "kind": "interface", - "name": { - "name": "ShardsOperationResponseBase", - "namespace": "_types" - }, - "properties": [ + }, { - "name": "_shards", + "description": "If `true`, the alias must exist to perform the action.", + "name": "must_exist", "required": false, + "serverDefault": false, "type": { "kind": "instance_of", "type": { - "name": "ShardStatistics", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } } ], - "specLocation": "_types/Base.ts#L142-L145" + "specLocation": "indices/update_aliases/types.ts#L41-L95" }, { "kind": "interface", "name": { - "name": "ResolveIndexItem", - "namespace": "indices.resolve_index" + "name": "RemoveAction", + "namespace": "indices.update_aliases" }, "properties": [ { - "name": "name", - "required": true, + "description": "Alias for the action.\nIndex alias names support date math.", + "name": "alias", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Name", + "name": "IndexAlias", "namespace": "_types" } } }, { + "description": "Aliases for the action.\nIndex alias names support date math.", "name": "aliases", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" + "items": [ + { + "kind": "instance_of", + "type": { + "name": "IndexAlias", + "namespace": "_types" + } + }, + { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "IndexAlias", + "namespace": "_types" + } + } } - } + ], + "kind": "union_of" } }, { - "name": "attributes", - "required": true, + "description": "Data stream or index for the action.\nSupports wildcards (`*`).", + "name": "index", + "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } + "kind": "instance_of", + "type": { + "name": "IndexName", + "namespace": "_types" } } }, { - "name": "data_stream", + "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", + "name": "indices", "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamName", + "name": "Indices", "namespace": "_types" } } + }, + { + "description": "If `true`, the alias must exist to perform the action.", + "name": "must_exist", + "required": false, + "serverDefault": false, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } } ], - "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L30-L35" + "specLocation": "indices/update_aliases/types.ts#L97-L122" }, { "kind": "interface", "name": { - "name": "ResolveIndexAliasItem", - "namespace": "indices.resolve_index" + "name": "RemoveIndexAction", + "namespace": "indices.update_aliases" }, "properties": [ { - "name": "name", - "required": true, + "description": "Data stream or index for the action.\nSupports wildcards (`*`).", + "name": "index", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "Name", + "name": "IndexName", "namespace": "_types" } } }, { + "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", "name": "indices", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -120057,656 +121795,801 @@ "namespace": "_types" } } + }, + { + "description": "If `true`, the alias must exist to perform the action.", + "name": "must_exist", + "required": false, + "serverDefault": false, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } } ], - "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L37-L40" + "specLocation": "indices/update_aliases/types.ts#L124-L139" }, { "kind": "interface", "name": { - "name": "ResolveIndexDataStreamsItem", - "namespace": "indices.resolve_index" + "name": "IndicesValidationExplanation", + "namespace": "indices.validate_query" }, "properties": [ { - "name": "name", - "required": true, + "name": "error", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "DataStreamName", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "timestamp_field", + "name": "explanation", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "name": "index", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Field", + "name": "IndexName", "namespace": "_types" } } }, { - "name": "backing_indices", + "name": "valid", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Indices", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } } ], - "specLocation": "indices/resolve_index/ResolveIndexResponse.ts#L42-L46" + "specLocation": "indices/validate_query/IndicesValidateQueryResponse.ts#L32-L37" }, { + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, "kind": "interface", "name": { - "name": "RolloverConditions", - "namespace": "indices.rollover" + "name": "RequestChatCompletionBase", + "namespace": "inference._types" }, "properties": [ { - "name": "min_age", - "required": false, + "description": "A list of objects representing the conversation.", + "name": "messages", + "required": true, "type": { - "kind": "instance_of", - "type": { - "name": "Duration", - "namespace": "_types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "Message", + "namespace": "inference.chat_completion_unified" + } } } }, { - "name": "max_age", + "description": "The ID of the model to use.", + "name": "model", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Duration", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "max_age_millis", + "description": "The upper bound limit for the number of tokens that can be generated for a completion request.", + "name": "max_completion_tokens", "required": false, "type": { - "generics": [ - { - "kind": "instance_of", - "type": { - "name": "UnitMillis", - "namespace": "_types" - } - } - ], "kind": "instance_of", "type": { - "name": "DurationValue", + "name": "long", "namespace": "_types" } } }, { - "name": "min_docs", + "description": "A sequence of strings to control when the model should stop generating additional tokens.", + "name": "stop", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "long", - "namespace": "_types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } } }, { - "name": "max_docs", + "description": "The sampling temperature to use.", + "name": "temperature", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "float", "namespace": "_types" } } }, { - "name": "max_size", + "description": "Controls which tool is called by the model.", + "name": "tool_choice", "required": false, "type": { "kind": "instance_of", "type": { - "name": "ByteSize", - "namespace": "_types" + "name": "CompletionToolType", + "namespace": "inference.chat_completion_unified" } } }, { - "name": "max_size_bytes", + "description": "A list of tools that the model can call.", + "name": "tools", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "long", - "namespace": "_types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "CompletionTool", + "namespace": "inference.chat_completion_unified" + } } } }, { - "name": "min_size", + "description": "Nucleus sampling, an alternative to sampling with temperature.", + "name": "top_p", "required": false, "type": { "kind": "instance_of", "type": { - "name": "ByteSize", + "name": "float", "namespace": "_types" } } - }, + } + ], + "specLocation": "inference/_types/CommonTypes.ts#L28-L61" + }, + { + "description": "An object representing part of the conversation.", + "kind": "interface", + "name": { + "name": "Message", + "namespace": "inference.chat_completion_unified" + }, + "properties": [ { - "name": "min_size_bytes", + "description": "The content of the message.", + "name": "content", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "MessageContent", + "namespace": "inference.chat_completion_unified" } } }, { - "name": "max_primary_shard_size", - "required": false, + "description": "The role of the message author.", + "name": "role", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "ByteSize", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "max_primary_shard_size_bytes", + "description": "The tool call that this message is responding to.", + "name": "tool_call_id", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "Id", "namespace": "_types" } } }, { - "name": "min_primary_shard_size", + "description": "The tool calls generated by the model.", + "name": "tool_calls", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "ByteSize", - "namespace": "_types" + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "ToolCall", + "namespace": "inference.chat_completion_unified" + } } } - }, + } + ], + "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L110-L130" + }, + { + "description": "A tool call generated by the model.", + "kind": "interface", + "name": { + "name": "ToolCall", + "namespace": "inference.chat_completion_unified" + }, + "properties": [ { - "name": "min_primary_shard_size_bytes", - "required": false, + "description": "The identifier of the tool call.", + "name": "id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "Id", "namespace": "_types" } } }, { - "name": "max_primary_shard_docs", - "required": false, + "description": "The function that the model called.", + "name": "function", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "ToolCallFunction", + "namespace": "inference.chat_completion_unified" } } }, { - "name": "min_primary_shard_docs", - "required": false, + "description": "The type of the tool call.", + "name": "type", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "long", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "indices/rollover/types.ts#L24-L40" + "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L87-L103" }, { + "description": "The function that the model called.", "kind": "interface", "name": { - "name": "Overlapping", - "namespace": "indices.simulate_template" + "name": "ToolCallFunction", + "namespace": "inference.chat_completion_unified" }, "properties": [ { - "name": "name", + "description": "The arguments to call the function with in JSON format.", + "name": "arguments", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Name", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "index_patterns", + "description": "The name of the function to call.", + "name": "name", "required": true, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "indices/simulate_template/IndicesSimulateTemplateResponse.ts#L39-L42" + "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L73-L85" }, { + "description": "A list of tools that the model can call.", "kind": "interface", "name": { - "name": "Template", - "namespace": "indices.simulate_template" + "name": "CompletionTool", + "namespace": "inference.chat_completion_unified" }, "properties": [ { - "name": "aliases", - "required": true, - "type": { - "key": { - "kind": "instance_of", - "type": { - "name": "IndexName", - "namespace": "_types" - } - }, - "kind": "dictionary_of", - "singleKey": false, - "value": { - "kind": "instance_of", - "type": { - "name": "Alias", - "namespace": "indices._types" - } - } - } - }, - { - "name": "mappings", + "description": "The type of tool.", + "name": "type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "TypeMapping", - "namespace": "_types.mapping" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "settings", + "description": "The function definition.", + "name": "function", "required": true, "type": { "kind": "instance_of", "type": { - "name": "IndexSettings", - "namespace": "indices._types" + "name": "CompletionToolFunction", + "namespace": "inference.chat_completion_unified" } } } ], - "specLocation": "indices/simulate_template/IndicesSimulateTemplateResponse.ts#L33-L37" + "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L180-L192" }, { + "description": "The completion tool function definition.", "kind": "interface", "name": { - "name": "Action", - "namespace": "indices.update_aliases" + "name": "CompletionToolFunction", + "namespace": "inference.chat_completion_unified" }, "properties": [ { - "description": "Adds a data stream or index to an alias.\nIf the alias doesn’t exist, the `add` action creates it.", - "name": "add", + "description": "A description of what the function does.\nThis is used by the model to choose when and how to call the function.", + "name": "description", "required": false, "type": { "kind": "instance_of", "type": { - "name": "AddAction", - "namespace": "indices.update_aliases" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Removes a data stream or index from an alias.", - "name": "remove", - "required": false, + "description": "The name of the function.", + "name": "name", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "RemoveAction", - "namespace": "indices.update_aliases" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Deletes an index.\nYou cannot use this action on aliases or data streams.", - "name": "remove_index", + "description": "The parameters the functional accepts. This should be formatted as a JSON object.", + "name": "parameters", + "required": false, + "type": { + "kind": "user_defined_value" + } + }, + { + "description": "Whether to enable schema adherence when generating the function call.", + "name": "strict", "required": false, "type": { "kind": "instance_of", "type": { - "name": "RemoveIndexAction", - "namespace": "indices.update_aliases" + "name": "boolean", + "namespace": "_builtins" } } } ], - "specLocation": "indices/update_aliases/types.ts#L23-L39", - "variants": { - "kind": "container" - } + "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L157-L178" }, { + "description": "Defines the completion result.", "kind": "interface", "name": { - "name": "AddAction", - "namespace": "indices.update_aliases" + "name": "CompletionInferenceResult", + "namespace": "inference._types" }, "properties": [ { - "description": "Alias for the action.\nIndex alias names support date math.", - "name": "alias", - "required": false, + "name": "completion", + "required": true, + "type": { + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "CompletionResult", + "namespace": "inference._types" + } + } + } + } + ], + "specLocation": "inference/_types/Results.ts#L83-L88" + }, + { + "description": "The completion result object", + "kind": "interface", + "name": { + "name": "CompletionResult", + "namespace": "inference._types" + }, + "properties": [ + { + "name": "result", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "IndexAlias", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } - }, + } + ], + "specLocation": "inference/_types/Results.ts#L76-L81" + }, + { + "description": "Acknowledged response. For dry_run, contains the list of pipelines which reference the inference endpoint", + "inherits": { + "type": { + "name": "AcknowledgedResponseBase", + "namespace": "_types" + } + }, + "kind": "interface", + "name": { + "name": "DeleteInferenceEndpointResult", + "namespace": "inference._types" + }, + "properties": [ { - "description": "Aliases for the action.\nIndex alias names support date math.", - "name": "aliases", - "required": false, + "name": "pipelines", + "required": true, "type": { - "items": [ - { - "kind": "instance_of", - "type": { - "name": "IndexAlias", - "namespace": "_types" - } - }, - { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "IndexAlias", - "namespace": "_types" - } - } + "kind": "array_of", + "value": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } - ], - "kind": "union_of" + } } - }, + } + ], + "specLocation": "inference/_types/Results.ts#L109-L114" + }, + { + "description": "Represents an inference endpoint as returned by the GET API", + "inherits": { + "type": { + "name": "InferenceEndpoint", + "namespace": "inference._types" + } + }, + "kind": "interface", + "name": { + "name": "InferenceEndpointInfo", + "namespace": "inference._types" + }, + "properties": [ { - "description": "Query used to limit documents the alias can access.", - "name": "filter", - "required": false, + "description": "The inference Id", + "name": "inference_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "QueryContainer", - "namespace": "_types.query_dsl" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Data stream or index for the action.\nSupports wildcards (`*`).", - "name": "index", + "description": "The task type", + "name": "task_type", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "TaskType", + "namespace": "inference._types" + } + } + } + ], + "specLocation": "inference/_types/Services.ts#L46-L58" + }, + { + "description": "Configuration options when storing the inference endpoint", + "kind": "interface", + "name": { + "name": "InferenceEndpoint", + "namespace": "inference._types" + }, + "properties": [ + { + "description": "Chunking configuration object", + "name": "chunking_settings", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexName", - "namespace": "_types" + "name": "InferenceChunkingSettings", + "namespace": "inference._types" } } }, { - "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", - "name": "indices", - "required": false, + "description": "The service type", + "name": "service", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Indices", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Value used to route indexing operations to a specific shard.\nIf specified, this overwrites the `routing` value for indexing operations.\nData stream aliases don’t support this parameter.", - "name": "index_routing", - "required": false, + "description": "Settings specific to the service", + "name": "service_settings", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Routing", - "namespace": "_types" + "name": "ServiceSettings", + "namespace": "inference._types" } } }, { - "description": "If `true`, the alias is hidden.", - "name": "is_hidden", + "description": "Task settings specific to the service and task type", + "name": "task_settings", "required": false, - "serverDefault": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "TaskSettings", + "namespace": "inference._types" } } - }, + } + ], + "specLocation": "inference/_types/Services.ts#L24-L44" + }, + { + "description": "Chunking configuration object", + "inherits": { + "type": { + "name": "InferenceEndpoint", + "namespace": "inference._types" + } + }, + "kind": "interface", + "name": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + }, + "properties": [ { - "description": "If `true`, sets the write index or data stream for the alias.", - "name": "is_write_index", + "description": "The maximum size of a chunk in words.\nThis value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).", + "name": "max_chunk_size", "required": false, + "serverDefault": 250, "type": { "kind": "instance_of", "type": { - "name": "boolean", - "namespace": "_builtins" + "name": "integer", + "namespace": "_types" } } }, { - "description": "Value used to route indexing and search operations to a specific shard.\nData stream aliases don’t support this parameter.", - "name": "routing", + "description": "The number of overlapping words for chunks.\nIt is applicable only to a `word` chunking strategy.\nThis value cannot be higher than half the `max_chunk_size` value.", + "name": "overlap", "required": false, + "serverDefault": 100, "type": { "kind": "instance_of", "type": { - "name": "Routing", + "name": "integer", "namespace": "_types" } } }, { - "description": "Value used to route search operations to a specific shard.\nIf specified, this overwrites the `routing` value for search operations.\nData stream aliases don’t support this parameter.", - "name": "search_routing", + "description": "The number of overlapping sentences for chunks.\nIt is applicable only for a `sentence` chunking strategy.\nIt can be either `1` or `0`.", + "name": "sentence_overlap", "required": false, + "serverDefault": 1, "type": { "kind": "instance_of", "type": { - "name": "Routing", + "name": "integer", "namespace": "_types" } } }, { - "description": "If `true`, the alias must exist to perform the action.", - "name": "must_exist", + "description": "The chunking strategy: `sentence` or `word`.", + "name": "strategy", "required": false, - "serverDefault": false, + "serverDefault": "sentence", "type": { "kind": "instance_of", "type": { - "name": "boolean", + "name": "string", "namespace": "_builtins" } } } ], - "specLocation": "indices/update_aliases/types.ts#L41-L95" + "specLocation": "inference/_types/Services.ts#L60-L89" }, { "kind": "interface", "name": { - "name": "RemoveAction", - "namespace": "indices.update_aliases" +<<<<<<< HEAD +======= + "name": "AlibabaCloudServiceSettings", + "namespace": "inference.put_alibabacloud" }, "properties": [ { - "description": "Alias for the action.\nIndex alias names support date math.", - "name": "alias", - "required": false, + "description": "A valid API key for the AlibabaCloud AI Search API.", + "name": "api_key", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "IndexAlias", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Aliases for the action.\nIndex alias names support date math.", - "name": "aliases", - "required": false, + "description": "The name of the host address used for the inference task.\nYou can find the host address in the API keys section of the documentation.", + "extDocId": "alibabacloud-api-keys", + "extDocUrl": "https://opensearch.console.aliyun.com/cn-shanghai/rag/api-key", + "name": "host", + "required": true, "type": { - "items": [ - { - "kind": "instance_of", - "type": { - "name": "IndexAlias", - "namespace": "_types" - } - }, - { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "IndexAlias", - "namespace": "_types" - } - } - } - ], - "kind": "union_of" + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } }, - { - "description": "Data stream or index for the action.\nSupports wildcards (`*`).", - "name": "index", + { + "description": "This setting helps to minimize the number of rate limit errors returned from AlibabaCloud AI Search.\nBy default, the `alibabacloud-ai-search` service sets the number of requests allowed per minute to `1000`.", + "name": "rate_limit", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexName", - "namespace": "_types" + "name": "RateLimitSetting", + "namespace": "inference._types" } } }, { - "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", - "name": "indices", - "required": false, + "description": "The name of the model service to use for the inference task.\nThe following service IDs are available for the `completion` task:\n\n* `ops-qwen-turbo`\n* `qwen-turbo`\n* `qwen-plus`\n* `qwen-max ÷ qwen-max-longcontext`\n\nThe following service ID is available for the `rerank` task:\n\n* `ops-bge-reranker-larger`\n\nThe following service ID is available for the `sparse_embedding` task:\n\n* `ops-text-sparse-embedding-001`\n\nThe following service IDs are available for the `text_embedding` task:\n\n`ops-text-embedding-001`\n`ops-text-embedding-zh-001`\n`ops-text-embedding-en-001`\n`ops-text-embedding-002`", + "name": "service_id", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "Indices", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "If `true`, the alias must exist to perform the action.", - "name": "must_exist", - "required": false, - "serverDefault": false, + "description": "The name of the workspace used for the inference task.", + "name": "workspace", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", + "name": "string", "namespace": "_builtins" } } } ], - "specLocation": "indices/update_aliases/types.ts#L97-L122" + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L93-L138" }, { "kind": "interface", "name": { - "name": "RemoveIndexAction", - "namespace": "indices.update_aliases" + "name": "RateLimitSetting", + "namespace": "inference._types" }, "properties": [ { - "description": "Data stream or index for the action.\nSupports wildcards (`*`).", - "name": "index", + "description": "The number of requests allowed per minute.", + "name": "requests_per_minute", "required": false, "type": { "kind": "instance_of", "type": { - "name": "IndexName", + "name": "integer", "namespace": "_types" } } - }, + } + ], + "specLocation": "inference/_types/Services.ts#L95-L100" + }, + { + "kind": "interface", + "name": { + "name": "AlibabaCloudTaskSettings", + "namespace": "inference.put_alibabacloud" + }, + "properties": [ { - "description": "Data streams or indices for the action.\nSupports wildcards (`*`).", - "name": "indices", + "description": "For a `sparse_embedding` or `text_embedding` task, specify the type of input passed to the model.\nValid values are:\n\n* `ingest` for storing document embeddings in a vector database.\n* `search` for storing embeddings of search queries run against a vector database to find relevant documents.", + "name": "input_type", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Indices", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "If `true`, the alias must exist to perform the action.", - "name": "must_exist", + "description": "For a `sparse_embedding` task, it affects whether the token name will be returned in the response.\nIt defaults to `false`, which means only the token ID will be returned in the response.", + "name": "return_token", "required": false, - "serverDefault": false, "type": { "kind": "instance_of", "type": { @@ -120716,18 +122599,19 @@ } } ], - "specLocation": "indices/update_aliases/types.ts#L124-L139" + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L140-L154" }, { "kind": "interface", "name": { - "name": "IndicesValidationExplanation", - "namespace": "indices.validate_query" + "name": "AmazonBedrockServiceSettings", + "namespace": "inference.put_amazonbedrock" }, "properties": [ { - "name": "error", - "required": false, + "description": "A valid AWS access key that has permissions to use Amazon Bedrock and access to models for inference requests.", + "name": "access_key", + "required": true, "type": { "kind": "instance_of", "type": { @@ -120737,7 +122621,22 @@ } }, { - "name": "explanation", + "description": "The base model ID or an ARN to a custom model based on a foundational model.\nThe base model IDs can be found in the Amazon Bedrock documentation.\nNote that the model ID must be available for the provider chosen and your IAM user must have access to the model.", + "extDocId": "amazonbedrock-models", + "extDocUrl": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", + "name": "model", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "The model provider for your deployment.\nNote that some providers may support only certain task types.\nSupported providers include:\n\n* `amazontitan` - available for `text_embedding` and `completion` task types\n* `anthropic` - available for `completion` task type only\n* `ai21labs` - available for `completion` task type only\n* `cohere` - available for `text_embedding` and `completion` task types\n* `meta` - available for `completion` task type only\n* `mistral` - available for `completion` task type only", + "name": "provider", "required": false, "type": { "kind": "instance_of", @@ -120748,103 +122647,95 @@ } }, { - "name": "index", + "description": "The region that your model or ARN is deployed in.\nThe list of available regions per model can be found in the Amazon Bedrock documentation.", + "extDocId": "amazonbedrock-models", + "extDocUrl": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", + "name": "region", "required": true, "type": { "kind": "instance_of", "type": { - "name": "IndexName", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "name": "valid", + "description": "This setting helps to minimize the number of rate limit errors returned from Watsonx.\nBy default, the `watsonxai` service sets the number of requests allowed per minute to 120.", + "name": "rate_limit", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "RateLimitSetting", + "namespace": "inference._types" + } + } + }, + { + "description": "A valid AWS secret key that is paired with the `access_key`.\nFor informationg about creating and managing access and secret keys, refer to the AWS documentation.", + "extDocId": "amazonbedrock-secret-keys", + "extDocUrl": "https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_access-keys.html", + "name": "secret_key", "required": true, "type": { "kind": "instance_of", "type": { - "name": "boolean", + "name": "string", "namespace": "_builtins" } } } ], - "specLocation": "indices/validate_query/IndicesValidateQueryResponse.ts#L32-L37" + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockRequest.ts#L95-L137" }, { - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, "kind": "interface", "name": { - "name": "RequestChatCompletionBase", - "namespace": "inference._types" + "name": "AmazonBedrockTaskSettings", + "namespace": "inference.put_amazonbedrock" }, "properties": [ { - "description": "A list of objects representing the conversation.", - "name": "messages", - "required": true, - "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "Message", - "namespace": "inference.chat_completion_unified" - } - } - } - }, - { - "description": "The ID of the model to use.", - "name": "model", + "description": "For a `completion` task, it sets the maximum number for the output tokens to be generated.", + "name": "max_new_tokens", "required": false, + "serverDefault": 64, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "integer", + "namespace": "_types" } } }, { - "description": "The upper bound limit for the number of tokens that can be generated for a completion request.", - "name": "max_completion_tokens", + "description": "For a `completion` task, it is a number between 0.0 and 1.0 that controls the apparent creativity of the results.\nAt temperature 0.0 the model is most deterministic, at temperature 1.0 most random.\nIt should not be used if `top_p` or `top_k` is specified.", + "name": "temperature", "required": false, "type": { "kind": "instance_of", "type": { - "name": "long", + "name": "float", "namespace": "_types" } } }, { - "description": "A sequence of strings to control when the model should stop generating additional tokens.", - "name": "stop", + "description": "For a `completion` task, it limits samples to the top-K most likely words, balancing coherence and variability.\nIt is only available for anthropic, cohere, and mistral providers.\nIt is an alternative to `temperature`; it should not be used if `temperature` is specified.", + "name": "top_k", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } + "kind": "instance_of", + "type": { + "name": "float", + "namespace": "_types" } } }, { - "description": "The sampling temperature to use.", - "name": "temperature", + "description": "For a `completion` task, it is a number in the range of 0.0 to 1.0, to eliminate low-probability tokens.\nTop-p uses nucleus sampling to select top tokens whose sum of likelihoods does not exceed a certain value, ensuring both variety and coherence.\nIt is an alternative to `temperature`; it should not be used if `temperature` is specified.", + "name": "top_p", "required": false, "type": { "kind": "instance_of", @@ -120853,146 +122744,155 @@ "namespace": "_types" } } - }, + } + ], + "specLocation": "inference/put_amazonbedrock/PutAmazonBedrockRequest.ts#L139-L163" + }, + { + "kind": "interface", + "name": { + "name": "AnthropicServiceSettings", + "namespace": "inference.put_anthropic" + }, + "properties": [ { - "description": "Controls which tool is called by the model.", - "name": "tool_choice", - "required": false, + "description": "A valid API key for the Anthropic API.", + "name": "api_key", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "CompletionToolType", - "namespace": "inference.chat_completion_unified" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "A list of tools that the model can call.", - "name": "tools", - "required": false, + "description": "The name of the model to use for the inference task.\nRefer to the Anthropic documentation for the list of supported models.", + "extDocId": "anothropic-models", + "name": "model_id", + "required": true, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "CompletionTool", - "namespace": "inference.chat_completion_unified" - } + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } }, { - "description": "Nucleus sampling, an alternative to sampling with temperature.", - "name": "top_p", + "description": "This setting helps to minimize the number of rate limit errors returned from Anthropic.\nBy default, the `anthropic` service sets the number of requests allowed per minute to 50.", + "name": "rate_limit", "required": false, "type": { "kind": "instance_of", "type": { - "name": "float", - "namespace": "_types" + "name": "RateLimitSetting", + "namespace": "inference._types" } } } ], - "specLocation": "inference/_types/CommonTypes.ts#L28-L61" + "specLocation": "inference/put_anthropic/PutAnthropicRequest.ts#L92-L108" }, { - "description": "An object representing part of the conversation.", "kind": "interface", "name": { - "name": "Message", - "namespace": "inference.chat_completion_unified" + "name": "AnthropicTaskSettings", + "namespace": "inference.put_anthropic" }, "properties": [ { - "description": "The content of the message.", - "name": "content", - "required": false, + "description": "For a `completion` task, it is the maximum number of tokens to generate before stopping.", + "name": "max_tokens", + "required": true, "type": { "kind": "instance_of", "type": { - "name": "MessageContent", - "namespace": "inference.chat_completion_unified" + "name": "integer", + "namespace": "_types" } } }, { - "description": "The role of the message author.", - "name": "role", - "required": true, + "description": "For a `completion` task, it is the amount of randomness injected into the response.\nFor more details about the supported range, refer to Anthropic documentation.", + "extDocId": "anthropic-messages", + "extDocUrl": "https://docs.anthropic.com/en/api/messages", + "name": "temperature", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "float", + "namespace": "_types" } } }, { - "description": "The tool call that this message is responding to.", - "name": "tool_call_id", + "description": "For a `completion` task, it specifies to only sample from the top K options for each subsequent token.\nIt is recommended for advanced use cases only.\nYou usually only need to use `temperature`.", + "name": "top_k", "required": false, "type": { "kind": "instance_of", "type": { - "name": "Id", + "name": "integer", "namespace": "_types" } } }, { - "description": "The tool calls generated by the model.", - "name": "tool_calls", + "description": "For a `completion` task, it specifies to use Anthropic's nucleus sampling.\nIn nucleus sampling, Anthropic computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches the specified probability.\nYou should either alter `temperature` or `top_p`, but not both.\nIt is recommended for advanced use cases only.\nYou usually only need to use `temperature`.", + "name": "top_p", "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "ToolCall", - "namespace": "inference.chat_completion_unified" - } + "kind": "instance_of", + "type": { + "name": "float", + "namespace": "_types" } } } ], - "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L110-L130" + "specLocation": "inference/put_anthropic/PutAnthropicRequest.ts#L110-L135" }, { - "description": "A tool call generated by the model.", "kind": "interface", "name": { - "name": "ToolCall", - "namespace": "inference.chat_completion_unified" + "name": "AzureAiStudioServiceSettings", + "namespace": "inference.put_azureaistudio" }, "properties": [ { - "description": "The identifier of the tool call.", - "name": "id", + "description": "A valid API key of your Azure AI Studio model deployment.\nThis key can be found on the overview page for your deployment in the management section of your Azure AI Studio account.\n\nIMPORTANT: You need to provide the API key only once, during the inference model creation.\nThe get inference endpoint API does not retrieve your API key.\nAfter creating the inference model, you cannot change the associated API key.\nIf you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.", + "extDocId": "azureaistudio-api-keys", + "extDocUrl": "https://ai.azure.com/", + "name": "api_key", "required": true, "type": { "kind": "instance_of", "type": { - "name": "Id", - "namespace": "_types" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "The function that the model called.", - "name": "function", + "description": "The type of endpoint that is available for deployment through Azure AI Studio: `token` or `realtime`.\nThe `token` endpoint type is for \"pay as you go\" endpoints that are billed per token.\nThe `realtime` endpoint type is for \"real-time\" endpoints that are billed per hour of usage.", + "extDocId": "azureaistudio-endpoint-types", + "extDocUrl": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/deployments-overview#billing-for-deploying-and-inferencing-llms-in-azure-ai-studio", + "name": "endpoint_type", "required": true, "type": { "kind": "instance_of", "type": { - "name": "ToolCallFunction", - "namespace": "inference.chat_completion_unified" + "name": "string", + "namespace": "_builtins" } } }, { - "description": "The type of the tool call.", - "name": "type", + "description": "The target URL of your Azure AI Studio model deployment.\nThis can be found on the overview page for your deployment in the management section of your Azure AI Studio account.", + "name": "target", "required": true, "type": { "kind": "instance_of", @@ -121001,21 +122901,10 @@ "namespace": "_builtins" } } - } - ], - "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L87-L103" - }, - { - "description": "The function that the model called.", - "kind": "interface", - "name": { - "name": "ToolCallFunction", - "namespace": "inference.chat_completion_unified" - }, - "properties": [ + }, { - "description": "The arguments to call the function with in JSON format.", - "name": "arguments", + "description": "The model provider for your deployment.\nNote that some providers may support only certain task types.\nSupported providers include:\n\n* `cohere` - available for `text_embedding` and `completion` task types\n* `databricks` - available for `completion` task type only\n* `meta` - available for `completion` task type only\n* `microsoft_phi` - available for `completion` task type only\n* `mistral` - available for `completion` task type only\n* `openai` - available for `text_embedding` and `completion` task types", + "name": "provider", "required": true, "type": { "kind": "instance_of", @@ -121026,66 +122915,103 @@ } }, { - "description": "The name of the function to call.", - "name": "name", - "required": true, + "description": "This setting helps to minimize the number of rate limit errors returned from Azure AI Studio.\nBy default, the `azureaistudio` service sets the number of requests allowed per minute to 240.", + "name": "rate_limit", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "RateLimitSetting", + "namespace": "inference._types" } } } ], - "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L73-L85" + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioRequest.ts#L92-L134" }, { - "description": "A list of tools that the model can call.", "kind": "interface", "name": { - "name": "CompletionTool", - "namespace": "inference.chat_completion_unified" + "name": "AzureAiStudioTaskSettings", + "namespace": "inference.put_azureaistudio" }, "properties": [ { - "description": "The type of tool.", - "name": "type", - "required": true, + "description": "For a `completion` task, instruct the inference process to perform sampling.\nIt has no effect unless `temperature` or `top_p` is specified.", + "name": "do_sample", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "float", + "namespace": "_types" } } }, { - "description": "The function definition.", - "name": "function", - "required": true, + "description": "For a `completion` task, provide a hint for the maximum number of output tokens to be generated.", + "name": "max_new_tokens", + "required": false, + "serverDefault": 64, "type": { "kind": "instance_of", "type": { - "name": "CompletionToolFunction", - "namespace": "inference.chat_completion_unified" + "name": "integer", + "namespace": "_types" + } + } + }, + { + "description": "For a `completion` task, control the apparent creativity of generated completions with a sampling temperature.\nIt must be a number in the range of 0.0 to 2.0.\nIt should not be used if `top_p` is specified.", + "name": "temperature", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "float", + "namespace": "_types" + } + } + }, + { + "description": "For a `completion` task, make the model consider the results of the tokens with nucleus sampling probability.\nIt is an alternative value to `temperature` and must be a number in the range of 0.0 to 2.0.\nIt should not be used if `temperature` is specified.", + "name": "top_p", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "float", + "namespace": "_types" + } + } + }, + { + "description": "For a `text_embedding` task, specify the user issuing the request.\nThis information can be used for abuse detection.", + "name": "user", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L180-L192" + "specLocation": "inference/put_azureaistudio/PutAzureAiStudioRequest.ts#L136-L164" }, { - "description": "The completion tool function definition.", "kind": "interface", "name": { - "name": "CompletionToolFunction", - "namespace": "inference.chat_completion_unified" + "name": "AzureOpenAIServiceSettings", + "namespace": "inference.put_azureopenai" }, "properties": [ { - "description": "A description of what the function does.\nThis is used by the model to choose when and how to call the function.", - "name": "description", + "description": "A valid API key for your Azure OpenAI account.\nYou must specify either `api_key` or `entra_id`.\nIf you do not provide either or you provide both, you will receive an error when you try to create your model.\n\nIMPORTANT: You need to provide the API key only once, during the inference model creation.\nThe get inference endpoint API does not retrieve your API key.\nAfter creating the inference model, you cannot change the associated API key.\nIf you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.", + "extDocId": "azureopenai-auth", + "extDocUrl": "https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#authentication", + "name": "api_key", "required": false, "type": { "kind": "instance_of", @@ -121096,8 +123022,8 @@ } }, { - "description": "The name of the function.", - "name": "name", + "description": "The Azure API version ID to use.\nIt is recommended to use the latest supported non-preview version.", + "name": "api_version", "required": true, "type": { "kind": "instance_of", @@ -121108,63 +123034,52 @@ } }, { - "description": "The parameters the functional accepts. This should be formatted as a JSON object.", - "name": "parameters", - "required": false, + "description": "The deployment name of your deployed models.\nYour Azure OpenAI deployments can be found though the Azure OpenAI Studio portal that is linked to your subscription.", + "extDocId": "azureopenai", + "extDocUrl": "https://oai.azure.com/", + "name": "deployment_id", + "required": true, "type": { - "kind": "user_defined_value" + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } } }, { - "description": "Whether to enable schema adherence when generating the function call.", - "name": "strict", + "description": "A valid Microsoft Entra token.\nYou must specify either `api_key` or `entra_id`.\nIf you do not provide either or you provide both, you will receive an error when you try to create your model.", + "extDocId": "azureopenai-auth", + "extDocUrl": "https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#authentication", + "name": "entra_id", "required": false, "type": { "kind": "instance_of", "type": { - "name": "boolean", + "name": "string", "namespace": "_builtins" } } - } - ], - "specLocation": "inference/chat_completion_unified/UnifiedRequest.ts#L157-L178" - }, - { - "description": "Defines the completion result.", - "kind": "interface", - "name": { - "name": "CompletionInferenceResult", - "namespace": "inference._types" - }, - "properties": [ + }, { - "name": "completion", - "required": true, + "description": "This setting helps to minimize the number of rate limit errors returned from Azure.\nThe `azureopenai` service sets a default number of requests allowed per minute depending on the task type.\nFor `text_embedding`, it is set to `1440`.\nFor `completion`, it is set to `120`.", + "extDocId": "azureopenai-quota-limits", + "extDocUrl": "https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits", + "name": "rate_limit", + "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "CompletionResult", - "namespace": "inference._types" - } + "kind": "instance_of", + "type": { + "name": "RateLimitSetting", + "namespace": "inference._types" } } - } - ], - "specLocation": "inference/_types/Results.ts#L83-L88" - }, - { - "description": "The completion result object", - "kind": "interface", - "name": { - "name": "CompletionResult", - "namespace": "inference._types" - }, - "properties": [ + }, { - "name": "result", + "description": "The name of your Azure OpenAI resource.\nYou can find this from the list of resources in the Azure Portal for your subscription.", + "extDocId": "azureopenai-portal", + "extDocUrl": "https://portal.azure.com/#view/HubsExtension/BrowseAll", + "name": "resource_name", "required": true, "type": { "kind": "instance_of", @@ -121175,56 +123090,42 @@ } } ], - "specLocation": "inference/_types/Results.ts#L76-L81" + "specLocation": "inference/put_azureopenai/PutAzureOpenAiRequest.ts#L99-L144" }, { - "description": "Acknowledged response. For dry_run, contains the list of pipelines which reference the inference endpoint", - "inherits": { - "type": { - "name": "AcknowledgedResponseBase", - "namespace": "_types" - } - }, "kind": "interface", "name": { - "name": "DeleteInferenceEndpointResult", - "namespace": "inference._types" + "name": "AzureOpenAITaskSettings", + "namespace": "inference.put_azureopenai" }, "properties": [ { - "name": "pipelines", - "required": true, + "description": "For a `completion` or `text_embedding` task, specify the user issuing the request.\nThis information can be used for abuse detection.", + "name": "user", + "required": false, "type": { - "kind": "array_of", - "value": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" } } } ], - "specLocation": "inference/_types/Results.ts#L109-L114" + "specLocation": "inference/put_azureopenai/PutAzureOpenAiRequest.ts#L146-L152" }, { - "description": "Represents an inference endpoint as returned by the GET API", - "inherits": { - "type": { - "name": "InferenceEndpoint", - "namespace": "inference._types" - } - }, "kind": "interface", "name": { - "name": "InferenceEndpointInfo", - "namespace": "inference._types" + "name": "CohereServiceSettings", + "namespace": "inference.put_cohere" }, "properties": [ { - "description": "The inference Id", - "name": "inference_id", + "description": "A valid API key for your Cohere account.\nYou can find or create your Cohere API keys on the Cohere API key settings page.\n\nIMPORTANT: You need to provide the API key only once, during the inference model creation.\nThe get inference endpoint API does not retrieve your API key.\nAfter creating the inference model, you cannot change the associated API key.\nIf you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.", + "extDocId": "cohere-api-keys", + "extDocUrl": "https://dashboard.cohere.com/api-keys", + "name": "api_key", "required": true, "type": { "kind": "instance_of", @@ -121235,44 +123136,22 @@ } }, { - "description": "The task type", - "name": "task_type", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "TaskType", - "namespace": "inference._types" - } - } - } - ], - "specLocation": "inference/_types/Services.ts#L46-L58" - }, - { - "description": "Configuration options when storing the inference endpoint", - "kind": "interface", - "name": { - "name": "InferenceEndpoint", - "namespace": "inference._types" - }, - "properties": [ - { - "description": "Chunking configuration object", - "name": "chunking_settings", + "description": "For a `text_embedding` task, the types of embeddings you want to get back.\nUse `byte` for signed int8 embeddings (this is a synonym of `int8`).\nUse `float` for the default float embeddings.\nUse `int8` for signed int8 embeddings.", + "name": "embedding_type", "required": false, + "serverDefault": "float", "type": { "kind": "instance_of", "type": { - "name": "InferenceChunkingSettings", - "namespace": "inference._types" + "name": "EmbeddingType", + "namespace": "inference.put_cohere" } } }, { - "description": "The service type", - "name": "service", - "required": true, + "description": "For a `completion`, `rerank`, or `text_embedding` task, the name of the model to use for the inference task.\n\n* For the available `completion` models, refer to the [Cohere command docs](https://docs.cohere.com/docs/models#command).\n* For the available `rerank` models, refer to the [Cohere rerank docs](https://docs.cohere.com/reference/rerank-1).\n* For the available `text_embedding` models, refer to [Cohere embed docs](https://docs.cohere.com/reference/embed).\n\nThe default value for a text embedding task is `embed-english-v2.0`.", + "name": "model_id", + "required": false, "type": { "kind": "instance_of", "type": { @@ -121282,77 +123161,67 @@ } }, { - "description": "Settings specific to the service", - "name": "service_settings", - "required": true, + "description": "This setting helps to minimize the number of rate limit errors returned from Cohere.\nBy default, the `cohere` service sets the number of requests allowed per minute to 10000.", + "name": "rate_limit", + "required": false, "type": { "kind": "instance_of", "type": { - "name": "ServiceSettings", + "name": "RateLimitSetting", "namespace": "inference._types" } } }, { - "description": "Task settings specific to the service and task type", - "name": "task_settings", + "description": "The similarity measure.\nIf the `embedding_type` is `float`, the default value is `dot_product`.\nIf the `embedding_type` is `int8` or `byte`, the default value is `cosine`.", + "name": "similarity", "required": false, "type": { "kind": "instance_of", "type": { - "name": "TaskSettings", - "namespace": "inference._types" + "name": "SimilarityType", + "namespace": "inference.put_cohere" } } } ], - "specLocation": "inference/_types/Services.ts#L24-L44" + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L119-L160" }, { - "description": "Chunking configuration object", - "inherits": { - "type": { - "name": "InferenceEndpoint", - "namespace": "inference._types" - } - }, "kind": "interface", "name": { - "name": "InferenceChunkingSettings", - "namespace": "inference._types" + "name": "CohereTaskSettings", + "namespace": "inference.put_cohere" }, "properties": [ { - "description": "The maximum size of a chunk in words.\nThis value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).", - "name": "max_chunk_size", + "description": "For a `text_embedding` task, the type of input passed to the model.\nValid values are:\n\n* `classification`: Use it for embeddings passed through a text classifier.\n* `clustering`: Use it for the embeddings run through a clustering algorithm.\n* `ingest`: Use it for storing document embeddings in a vector database.\n* `search`: Use it for storing embeddings of search queries run against a vector database to find relevant documents.\n\nIMPORTANT: The `input_type` field is required when using embedding models `v3` and higher.", + "name": "input_type", "required": false, - "serverDefault": 250, "type": { "kind": "instance_of", "type": { - "name": "integer", - "namespace": "_types" + "name": "InputType", + "namespace": "inference.put_cohere" } } }, { - "description": "The number of overlapping words for chunks.\nIt is applicable only to a `word` chunking strategy.\nThis value cannot be higher than half the `max_chunk_size` value.", - "name": "overlap", + "description": "For a `rerank` task, return doc text within the results.", + "name": "return_documents", "required": false, - "serverDefault": 100, "type": { "kind": "instance_of", "type": { - "name": "integer", - "namespace": "_types" + "name": "boolean", + "namespace": "_builtins" } } }, { - "description": "The number of overlapping sentences for chunks.\nIt is applicable only for a `sentence` chunking strategy.\nIt can be either `1` or `0`.", - "name": "sentence_overlap", + "description": "For a `rerank` task, the number of most relevant documents to return.\nIt defaults to the number of the documents.\nIf this inference endpoint is used in a `text_similarity_reranker` retriever query and `top_n` is set, it must be greater than or equal to `rank_window_size` in the query.", + "name": "top_n", "required": false, - "serverDefault": 1, "type": { "kind": "instance_of", "type": { @@ -121362,24 +123231,24 @@ } }, { - "description": "The chunking strategy: `sentence` or `word`.", - "name": "strategy", + "description": "For a `text_embedding` task, the method to handle inputs longer than the maximum token length.\nValid values are:\n\n* `END`: When the input exceeds the maximum input token length, the end of the input is discarded.\n* `NONE`: When the input exceeds the maximum input token length, an error is returned.\n* `START`: When the input exceeds the maximum input token length, the start of the input is discarded.", + "name": "truncate", "required": false, - "serverDefault": "sentence", "type": { "kind": "instance_of", "type": { - "name": "string", - "namespace": "_builtins" + "name": "TruncateType", + "namespace": "inference.put_cohere" } } } ], - "specLocation": "inference/_types/Services.ts#L60-L89" + "specLocation": "inference/put_cohere/PutCohereRequest.ts#L162-L194" }, { "kind": "interface", "name": { +>>>>>>> ef980f023 (Add Alibaba Cloud inference API (#4021)) "name": "EisServiceSettings", "namespace": "inference.put_eis" }, diff --git a/output/schema/schema.json b/output/schema/schema.json index c75cfa6206..d4248f6b5c 100644 --- a/output/schema/schema.json +++ b/output/schema/schema.json @@ -9351,6 +9351,51 @@ } ] }, + { + "availability": { + "serverless": { + "stability": "stable", + "visibility": "public" + }, + "stack": { + "since": "8.16.0", + "stability": "stable", + "visibility": "public" + } + }, + "description": "Create an AlibabaCloud AI Search inference endpoint.\n\nCreate an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "docId": "inference-api-put-alibabacloud", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-alibabacloud-ai-search.html", + "name": "inference.put_alibabacloud", + "privileges": { + "cluster": [ + "manage_inference" + ] + }, + "request": { + "name": "Request", + "namespace": "inference.put_alibabacloud" + }, + "requestBodyRequired": false, + "requestMediaType": [ + "application/json" + ], + "response": { + "name": "Response", + "namespace": "inference.put_alibabacloud" + }, + "responseMediaType": [ + "application/json" + ], + "urls": [ + { + "methods": [ + "PUT" + ], + "path": "/_inference/{task_type}/{alibabacloud_inference_id}" + } + ] + }, { "availability": { "serverless": { @@ -150528,6 +150573,287 @@ }, "specLocation": "inference/put/PutResponse.ts#L22-L24" }, + { + "kind": "interface", + "name": { + "name": "AlibabaCloudServiceSettings", + "namespace": "inference.put_alibabacloud" + }, + "properties": [ + { + "description": "A valid API key for the AlibabaCloud AI Search API.", + "name": "api_key", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "The name of the host address used for the inference task.\nYou can find the host address in the API keys section of the documentation.", + "extDocId": "alibabacloud-api-keys", + "extDocUrl": "https://opensearch.console.aliyun.com/cn-shanghai/rag/api-key", + "name": "host", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "This setting helps to minimize the number of rate limit errors returned from AlibabaCloud AI Search.\nBy default, the `alibabacloud-ai-search` service sets the number of requests allowed per minute to `1000`.", + "name": "rate_limit", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "RateLimitSetting", + "namespace": "inference._types" + } + } + }, + { + "description": "The name of the model service to use for the inference task.\nThe following service IDs are available for the `completion` task:\n\n* `ops-qwen-turbo`\n* `qwen-turbo`\n* `qwen-plus`\n* `qwen-max ÷ qwen-max-longcontext`\n\nThe following service ID is available for the `rerank` task:\n\n* `ops-bge-reranker-larger`\n\nThe following service ID is available for the `sparse_embedding` task:\n\n* `ops-text-sparse-embedding-001`\n\nThe following service IDs are available for the `text_embedding` task:\n\n`ops-text-embedding-001`\n`ops-text-embedding-zh-001`\n`ops-text-embedding-en-001`\n`ops-text-embedding-002`", + "name": "service_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "The name of the workspace used for the inference task.", + "name": "workspace", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L93-L138" + }, + { + "kind": "interface", + "name": { + "name": "AlibabaCloudTaskSettings", + "namespace": "inference.put_alibabacloud" + }, + "properties": [ + { + "description": "For a `sparse_embedding` or `text_embedding` task, specify the type of input passed to the model.\nValid values are:\n\n* `ingest` for storing document embeddings in a vector database.\n* `search` for storing embeddings of search queries run against a vector database to find relevant documents.", + "name": "input_type", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "string", + "namespace": "_builtins" + } + } + }, + { + "description": "For a `sparse_embedding` task, it affects whether the token name will be returned in the response.\nIt defaults to `false`, which means only the token ID will be returned in the response.", + "name": "return_token", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + } + ], + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L140-L154" + }, + { + "kind": "enum", + "members": [ + { + "name": "completion" + }, + { + "name": "rerank" + }, + { + "name": "space_embedding" + }, + { + "name": "text_embedding" + } + ], + "name": { + "name": "AlibabaCloudTaskType", + "namespace": "inference.put_alibabacloud" + }, + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L82-L87" + }, + { + "kind": "request", + "attachedBehaviors": [ + "CommonQueryParameters" + ], + "body": { + "kind": "properties", + "properties": [ + { + "description": "The chunking configuration object.", + "extDocId": "inference-chunking", + "extDocUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config", + "name": "chunking_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "InferenceChunkingSettings", + "namespace": "inference._types" + } + } + }, + { + "description": "The type of service supported for the specified task type. In this case, `alibabacloud-ai-search`.", + "name": "service", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "ServiceType", + "namespace": "inference.put_alibabacloud" + } + } + }, + { + "description": "Settings used to install the inference model. These settings are specific to the `alibabacloud-ai-search` service.", + "name": "service_settings", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "AlibabaCloudServiceSettings", + "namespace": "inference.put_alibabacloud" + } + } + }, + { + "description": "Settings to configure the inference task.\nThese settings are specific to the task type you specified.", + "name": "task_settings", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AlibabaCloudTaskSettings", + "namespace": "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.\n\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\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.", + "examples": { + "PutAlibabaCloudRequestExample1": { + "description": "Run `PUT _inference/completion/alibabacloud_ai_search_completion` to create an inference endpoint that performs a completion task.", + "summary": "A completion task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"host\" : \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-qwen-turbo\",\n \"workspace\" : \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample2": { + "description": "Run `PUT _inference/rerank/alibabacloud_ai_search_rerank` to create an inference endpoint that performs a rerank task.", + "summary": "A rerank task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-bge-reranker-larger\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample3": { + "description": "Run `PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse` to create an inference endpoint that performs perform a sparse embedding task.", + "summary": "A sparse embedding task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-sparse-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + }, + "PutAlibabaCloudRequestExample4": { + "description": "Run `PUT _inference/text_embedding/alibabacloud_ai_search_embeddings` to create an inference endpoint that performs a text embedding task.", + "summary": "A text embedding task", + "value": "{\n \"service\": \"alibabacloud-ai-search\",\n \"service_settings\": {\n \"api_key\": \"AlibabaCloud-API-Key\",\n \"service_id\": \"ops-text-embedding-001\",\n \"host\": \"default-j01.platform-cn-shanghai.opensearch.aliyuncs.com\",\n \"workspace\": \"default\"\n }\n}" + } + }, + "inherits": { + "type": { + "name": "RequestBase", + "namespace": "_types" + } + }, + "name": { + "name": "Request", + "namespace": "inference.put_alibabacloud" + }, + "path": [ + { + "description": "The type of the inference task that the model will perform.", + "name": "task_type", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "AlibabaCloudTaskType", + "namespace": "inference.put_alibabacloud" + } + } + }, + { + "description": "The unique identifier of the inference endpoint.", + "name": "alibabacloud_inference_id", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + } + } + ], + "query": [], + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L27-L80" + }, + { + "kind": "response", + "body": { + "kind": "value", + "value": { + "kind": "instance_of", + "type": { + "name": "InferenceEndpointInfo", + "namespace": "inference._types" + } + } + }, + "name": { + "name": "Response", + "namespace": "inference.put_alibabacloud" + }, + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudResponse.ts#L22-L24" + }, + { + "kind": "enum", + "members": [ + { + "name": "alibabacloud-ai-search" + } + ], + "name": { + "name": "ServiceType", + "namespace": "inference.put_alibabacloud" + }, + "specLocation": "inference/put_alibabacloud/PutAlibabaCloudRequest.ts#L89-L91" + }, { "kind": "interface", "name": { diff --git a/output/typescript/types.ts b/output/typescript/types.ts index d9734eadbd..71be3658a6 100644 --- a/output/typescript/types.ts +++ b/output/typescript/types.ts @@ -13249,6 +13249,36 @@ export interface InferencePutRequest extends RequestBase { export type InferencePutResponse = InferenceInferenceEndpointInfo +export interface InferencePutAlibabacloudAlibabaCloudServiceSettings { + api_key: string + host: string + rate_limit?: InferenceRateLimitSetting + service_id: string + workspace: string +} + +export interface InferencePutAlibabacloudAlibabaCloudTaskSettings { + input_type?: string + return_token?: boolean +} + +export type InferencePutAlibabacloudAlibabaCloudTaskType = 'completion' | 'rerank' | 'space_embedding' | 'text_embedding' + +export interface InferencePutAlibabacloudRequest extends RequestBase { + task_type: InferencePutAlibabacloudAlibabaCloudTaskType + alibabacloud_inference_id: Id + body?: { + chunking_settings?: InferenceInferenceChunkingSettings + service: InferencePutAlibabacloudServiceType + service_settings: InferencePutAlibabacloudAlibabaCloudServiceSettings + task_settings?: InferencePutAlibabacloudAlibabaCloudTaskSettings + } +} + +export type InferencePutAlibabacloudResponse = InferenceInferenceEndpointInfo + +export type InferencePutAlibabacloudServiceType = 'alibabacloud-ai-search' + export interface InferencePutEisEisServiceSettings { model_id: string rate_limit?: InferenceRateLimitSetting diff --git a/specification/_doc_ids/table.csv b/specification/_doc_ids/table.csv index 04818b0fd8..bb6575b41a 100644 --- a/specification/_doc_ids/table.csv +++ b/specification/_doc_ids/table.csv @@ -2,6 +2,7 @@ apis,https://www.elastic.co/docs/api/doc/elasticsearch/v8 add-nodes,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/add-elasticsearch-nodes.html alias-update,https://www.elastic.co/docs/api/doc/elasticsearch/v8/operation/operation-indices-put-alias aliases-update,https://www.elastic.co/docs/api/doc/elasticsearch/v8/operation/operation-indices-update-aliases +alibabacloud-api-keys,https://opensearch.console.aliyun.com/cn-shanghai/rag/api-key analysis-analyzers,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/analysis-analyzers.html analysis-charfilters,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/analysis-charfilters.html analysis-normalizers,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/analysis-normalizers.html @@ -320,6 +321,7 @@ inference-api-get,https://www.elastic.co/guide/en/elasticsearch/reference/{branc inference-api-post,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html inference-api-post-eis-chat-completion,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html inference-api-put,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/put-inference-api.html +inference-api-put-alibabacloud,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-alibabacloud-ai-search.html inference-api-put-eis,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-elastic.html inference-api-put-huggingface,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-hugging-face.html inference-api-put-jinaai,https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-jinaai.html diff --git a/specification/_json_spec/inference.put_alibabacloud.json b/specification/_json_spec/inference.put_alibabacloud.json new file mode 100644 index 0000000000..b39d5abe97 --- /dev/null +++ b/specification/_json_spec/inference.put_alibabacloud.json @@ -0,0 +1,35 @@ +{ + "inference.put_alibabacloud": { + "documentation": { + "url": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-alibabacloud-ai-search.html", + "description": "Configure an AlibabaCloud AI Search inference endpoint" + }, + "stability": "stable", + "visibility": "public", + "headers": { + "accept": ["application/json"], + "content_type": ["application/json"] + }, + "url": { + "paths": [ + { + "path": "/_inference/{task_type}/{alibabacloud_inference_id}", + "methods": ["PUT"], + "parts": { + "task_type": { + "type": "string", + "description": "The task type" + }, + "alibabacloud_inference_id": { + "type": "string", + "description": "The inference Id" + } + } + } + ] + }, + "body": { + "description": "The inference endpoint's task and service settings" + } + } +} diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts new file mode 100644 index 0000000000..11770daa84 --- /dev/null +++ b/specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts @@ -0,0 +1,154 @@ +/* + * Licensed to Elasticsearch B.V. under one or more contributor + * license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright + * ownership. Elasticsearch B.V. licenses this file to you under + * the Apache License, Version 2.0 (the "License"); you may + * not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +import { + InferenceChunkingSettings, + RateLimitSetting +} from '@inference/_types/Services' +import { RequestBase } from '@_types/Base' +import { Id } from '@_types/common' + +/** + * Create an AlibabaCloud AI Search inference endpoint. + * + * Create an inference endpoint to perform an inference task with the `alibabacloud-ai-search` service. + * + * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. + * After creating the endpoint, wait for the model deployment to complete before using it. + * To verify the deployment status, use the get trained model statistics API. + * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. + * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. + * @rest_spec_name inference.put_alibabacloud + * @availability stack since=8.16.0 stability=stable visibility=public + * @availability serverless stability=stable visibility=public + * @cluster_privileges manage_inference + * @doc_id inference-api-put-alibabacloud + */ +export interface Request extends RequestBase { + urls: [ + { + path: '/_inference/{task_type}/{alibabacloud_inference_id}' + methods: ['PUT'] + } + ] + path_parts: { + /** + * The type of the inference task that the model will perform. + */ + task_type: AlibabaCloudTaskType + /** + * The unique identifier of the inference endpoint. + */ + alibabacloud_inference_id: Id + } + body: { + /** + * The chunking configuration object. + * @ext_doc_id inference-chunking + */ + chunking_settings?: InferenceChunkingSettings + /** + * The type of service supported for the specified task type. In this case, `alibabacloud-ai-search`. + */ + service: ServiceType + /** + * Settings used to install the inference model. These settings are specific to the `alibabacloud-ai-search` service. + */ + service_settings: AlibabaCloudServiceSettings + /** + * Settings to configure the inference task. + * These settings are specific to the task type you specified. + */ + task_settings?: AlibabaCloudTaskSettings + } +} + +export enum AlibabaCloudTaskType { + completion, + rerank, + space_embedding, + text_embedding +} + +export enum ServiceType { + 'alibabacloud-ai-search' +} + +export class AlibabaCloudServiceSettings { + /** + * A valid API key for the AlibabaCloud AI Search API. + */ + api_key: string + /** + * The name of the host address used for the inference task. + * You can find the host address in the API keys section of the documentation. + * @ext_doc_id alibabacloud-api-keys + */ + host: string + /** + * This setting helps to minimize the number of rate limit errors returned from AlibabaCloud AI Search. + * By default, the `alibabacloud-ai-search` service sets the number of requests allowed per minute to `1000`. + */ + rate_limit?: RateLimitSetting + /** + * The name of the model service to use for the inference task. + * The following service IDs are available for the `completion` task: + * + * * `ops-qwen-turbo` + * * `qwen-turbo` + * * `qwen-plus` + * * `qwen-max ÷ qwen-max-longcontext` + * + * The following service ID is available for the `rerank` task: + * + * * `ops-bge-reranker-larger` + * + * The following service ID is available for the `sparse_embedding` task: + * + * * `ops-text-sparse-embedding-001` + * + * The following service IDs are available for the `text_embedding` task: + * + * `ops-text-embedding-001` + * `ops-text-embedding-zh-001` + * `ops-text-embedding-en-001` + * `ops-text-embedding-002` + */ + service_id: string + /** + * The name of the workspace used for the inference task. + */ + workspace: string +} + +export class AlibabaCloudTaskSettings { + /** + * For a `sparse_embedding` or `text_embedding` task, specify the type of input passed to the model. + * Valid values are: + * + * * `ingest` for storing document embeddings in a vector database. + * * `search` for storing embeddings of search queries run against a vector database to find relevant documents. + */ + input_type?: string + /** + * For a `sparse_embedding` task, it affects whether the token name will be returned in the response. + * It defaults to `false`, which means only the token ID will be returned in the response. + */ + return_token?: boolean +} diff --git a/specification/inference/put_alibabacloud/PutAlibabaCloudResponse.ts b/specification/inference/put_alibabacloud/PutAlibabaCloudResponse.ts new file mode 100644 index 0000000000..d40639b031 --- /dev/null +++ b/specification/inference/put_alibabacloud/PutAlibabaCloudResponse.ts @@ -0,0 +1,24 @@ +/* + * Licensed to Elasticsearch B.V. under one or more contributor + * license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright + * ownership. Elasticsearch B.V. licenses this file to you under + * the Apache License, Version 2.0 (the "License"); you may + * not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +import { InferenceEndpointInfo } from '@inference/_types/Services' + +export class Response { + body: InferenceEndpointInfo +} diff --git a/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample1.yaml b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample1.yaml new file mode 100644 index 0000000000..4a939a2ee2 --- /dev/null +++ b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample1.yaml @@ -0,0 +1,14 @@ +summary: A completion task +description: Run `PUT _inference/completion/alibabacloud_ai_search_completion` to create an inference endpoint that performs a completion task. +# method_request: "PUT _inference/completion/alibabacloud_ai_search_completion" +# type: "request" +value: |- + { + "service": "alibabacloud-ai-search", + "service_settings": { + "host" : "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com", + "api_key": "AlibabaCloud-API-Key", + "service_id": "ops-qwen-turbo", + "workspace" : "default" + } + } diff --git a/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample2.yaml b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample2.yaml new file mode 100644 index 0000000000..1a4f9a832d --- /dev/null +++ b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample2.yaml @@ -0,0 +1,14 @@ +summary: A rerank task +description: Run `PUT _inference/rerank/alibabacloud_ai_search_rerank` to create an inference endpoint that performs a rerank task. +# method_request: "PUT _inference/rerank/alibabacloud_ai_search_rerank" +# type: "request" +value: |- + { + "service": "alibabacloud-ai-search", + "service_settings": { + "api_key": "AlibabaCloud-API-Key", + "service_id": "ops-bge-reranker-larger", + "host": "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com", + "workspace": "default" + } + } diff --git a/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample3.yaml b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample3.yaml new file mode 100644 index 0000000000..c43ee4b6bf --- /dev/null +++ b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample3.yaml @@ -0,0 +1,14 @@ +summary: A sparse embedding task +description: Run `PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse` to create an inference endpoint that performs perform a sparse embedding task. +# method_request: "PUT _inference/sparse_embedding/alibabacloud_ai_search_sparse" +# type: "request" +value: |- + { + "service": "alibabacloud-ai-search", + "service_settings": { + "api_key": "AlibabaCloud-API-Key", + "service_id": "ops-text-sparse-embedding-001", + "host": "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com", + "workspace": "default" + } + } diff --git a/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample4.yaml b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample4.yaml new file mode 100644 index 0000000000..17a76344fb --- /dev/null +++ b/specification/inference/put_alibabacloud/examples/request/PutAlibabaCloudRequestExample4.yaml @@ -0,0 +1,14 @@ +summary: A text embedding task +description: Run `PUT _inference/text_embedding/alibabacloud_ai_search_embeddings` to create an inference endpoint that performs a text embedding task. +# method_request: "PUT _inference/text_embedding/alibabacloud_ai_search_embeddings" +# type: "request" +value: |- + { + "service": "alibabacloud-ai-search", + "service_settings": { + "api_key": "AlibabaCloud-API-Key", + "service_id": "ops-text-embedding-001", + "host": "default-j01.platform-cn-shanghai.opensearch.aliyuncs.com", + "workspace": "default" + } + }