elasticsearch-api 9.0.3 → 9.1.0

data/lib/elasticsearch/api/actions/inference/put_azureopenai.rb

@@ -23,24 +23,31 @@ module Elasticsearch
     module Inference
       module Actions
         # Create an Azure OpenAI inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +azureopenai+ service.
+        # Create an inference endpoint to perform an inference task with the `azureopenai` service.
         # The list of chat completion models that you can choose from in your Azure OpenAI deployment include:
         # * {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 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-35 GPT-3.5}
         # The list of embeddings models that you can choose from in your deployment can be found in the {https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#embeddings Azure models documentation}.
-        # 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.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform.
-        #  NOTE: The +chat_completion+ task type only supports streaming and only through the _stream API. (*Required*)
+        #  NOTE: The `chat_completion` task type only supports streaming and only through the _stream API. (*Required*)
         # @option arguments [String] :azureopenai_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-azureopenai
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-azureopenai
         #
         def put_azureopenai(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_azureopenai' }
@@ -68,7 +75,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_azureopenai_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_cohere.rb

@@ -23,19 +23,26 @@ module Elasticsearch
     module Inference
       module Actions
         # Create a Cohere inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +cohere+ service.
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `cohere` service.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :cohere_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-cohere
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-cohere
         #
         def put_cohere(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_cohere' }
@@ -63,7 +70,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_cohere_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_custom.rb

@@ -0,0 +1,112 @@
+# 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.
+#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
+module Elasticsearch
+  module API
+    module Inference
+      module Actions
+        # Create a custom inference endpoint.
+        # The custom service gives more control over how to interact with external inference services that aren't explicitly supported through dedicated integrations.
+        # The custom service gives you the ability to define the headers, url, query parameters, request body, and secrets.
+        # The custom service supports the template replacement functionality, which enables you to define a template that can be replaced with the value associated with that key.
+        # Templates are portions of a string that start with `${` and end with `}`.
+        # The parameters `secret_parameters` and `task_settings` are checked for keys for template replacement. Template replacement is supported in the `request`, `headers`, `url`, and `query_parameters`.
+        # If the definition (key) is not found for a template, an error message is returned.
+        # In case of an endpoint definition like the following:
+        #
+        # ```
+        # PUT _inference/text_embedding/test-text-embedding
+        # {
+        #   "service": "custom",
+        #   "service_settings": {
+        #      "secret_parameters": {
+        #           "api_key": "<some api key>"
+        #      },
+        #      "url": "...endpoints.huggingface.cloud/v1/embeddings",
+        #      "headers": {
+        #          "Authorization": "Bearer ${api_key}",
+        #          "Content-Type": "application/json"
+        #      },
+        #      "request": "{\"input\": ${input}}",
+        #      "response": {
+        #          "json_parser": {
+        #              "text_embeddings":"$.data[*].embedding[*]"
+        #          }
+        #      }
+        #   }
+        # }
+        # ```
+        #
+        # To replace `${api_key}` the `secret_parameters` and `task_settings` are checked for a key named `api_key`.
+        #
+        # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
+        # @option arguments [String] :custom_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
+        # @option arguments [Hash] :headers Custom HTTP headers
+        # @option arguments [Hash] :body request body
+        #
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-custom
+        #
+        def put_custom(arguments = {})
+          request_opts = { endpoint: arguments[:endpoint] || 'inference.put_custom' }
+
+          defined_params = [:task_type, :custom_inference_id].each_with_object({}) do |variable, set_variables|
+            set_variables[variable] = arguments[variable] if arguments.key?(variable)
+          end
+          request_opts[:defined_params] = defined_params unless defined_params.empty?
+
+          raise ArgumentError, "Required argument 'task_type' missing" unless arguments[:task_type]
+
+          unless arguments[:custom_inference_id]
+            raise ArgumentError,
+                  "Required argument 'custom_inference_id' missing"
+          end
+
+          arguments = arguments.clone
+          headers = arguments.delete(:headers) || {}
+
+          body = arguments.delete(:body)
+
+          _task_type = arguments.delete(:task_type)
+
+          _custom_inference_id = arguments.delete(:custom_inference_id)
+
+          method = Elasticsearch::API::HTTP_PUT
+          path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_custom_inference_id)}"
+          params = Utils.process_params(arguments)
+
+          Elasticsearch::API::Response.new(
+            perform_request(method, path, params, body, headers, request_opts)
+          )
+        end
+      end
+    end
+  end
+end

data/lib/elasticsearch/api/actions/inference/put_deepseek.rb

@@ -0,0 +1,82 @@
+# 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.
+#
+# This code was automatically generated from the Elasticsearch Specification
+# See https://github.com/elastic/elasticsearch-specification
+# See Elasticsearch::ES_SPECIFICATION_COMMIT for commit hash.
+module Elasticsearch
+  module API
+    module Inference
+      module Actions
+        # Create a DeepSeek inference endpoint.
+        # Create an inference endpoint to perform an inference task with the `deepseek` service.
+        #
+        # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
+        # @option arguments [String] :deepseek_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
+        # @option arguments [Hash] :headers Custom HTTP headers
+        # @option arguments [Hash] :body request body
+        #
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-deepseek
+        #
+        def put_deepseek(arguments = {})
+          request_opts = { endpoint: arguments[:endpoint] || 'inference.put_deepseek' }
+
+          defined_params = [:task_type, :deepseek_inference_id].each_with_object({}) do |variable, set_variables|
+            set_variables[variable] = arguments[variable] if arguments.key?(variable)
+          end
+          request_opts[:defined_params] = defined_params unless defined_params.empty?
+
+          raise ArgumentError, "Required argument 'task_type' missing" unless arguments[:task_type]
+
+          unless arguments[:deepseek_inference_id]
+            raise ArgumentError,
+                  "Required argument 'deepseek_inference_id' missing"
+          end
+
+          arguments = arguments.clone
+          headers = arguments.delete(:headers) || {}
+
+          body = arguments.delete(:body)
+
+          _task_type = arguments.delete(:task_type)
+
+          _deepseek_inference_id = arguments.delete(:deepseek_inference_id)
+
+          method = Elasticsearch::API::HTTP_PUT
+          path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_deepseek_inference_id)}"
+          params = Utils.process_params(arguments)
+
+          Elasticsearch::API::Response.new(
+            perform_request(method, path, params, body, headers, request_opts)
+          )
+        end
+      end
+    end
+  end
+end

data/lib/elasticsearch/api/actions/inference/put_elasticsearch.rb

@@ -23,15 +23,27 @@ module Elasticsearch
     module Inference
       module Actions
         # Create an Elasticsearch inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +elasticsearch+ service.
+        # Create an inference endpoint to perform an inference task with the `elasticsearch` service.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :elasticsearch_inference_id The unique identifier of the inference endpoint.
-        #  The must not match the +model_id+. (*Required*)
+        #  The must not match the `model_id`. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-elasticsearch
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-elasticsearch
         #
         def put_elasticsearch(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_elasticsearch' }
@@ -59,7 +71,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_elasticsearch_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_elser.rb

@@ -23,15 +23,27 @@ module Elasticsearch
     module Inference
       module Actions
         # Create an ELSER inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +elser+ service.
+        # Create an inference endpoint to perform an inference task with the `elser` service.
         # You can also deploy ELSER by using the Elasticsearch inference integration.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :elser_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-elser
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-elser
         #
         def put_elser(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_elser' }
@@ -55,7 +67,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_elser_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_googleaistudio.rb

@@ -23,19 +23,26 @@ module Elasticsearch
     module Inference
       module Actions
         # Create an Google AI Studio inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +googleaistudio+ service.
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `googleaistudio` service.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :googleaistudio_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-googleaistudio
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-googleaistudio
         #
         def put_googleaistudio(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_googleaistudio' }
@@ -63,7 +70,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_googleaistudio_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_googlevertexai.rb

@@ -23,19 +23,26 @@ module Elasticsearch
     module Inference
       module Actions
         # Create a Google Vertex AI inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +googlevertexai+ service.
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `googlevertexai` service.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :googlevertexai_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-googlevertexai
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-googlevertexai
         #
         def put_googlevertexai(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_googlevertexai' }
@@ -63,7 +70,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_googlevertexai_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_hugging_face.rb

@@ -23,30 +23,54 @@ module Elasticsearch
     module Inference
       module Actions
         # Create a Hugging Face inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +hugging_face+ service.
-        # You must first create an inference endpoint on the Hugging Face endpoint page to get an endpoint URL.
-        # Select 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.
-        # Create the endpoint and copy the URL after the endpoint initialization has been finished.
-        # The following models are recommended for the Hugging Face service:
-        # * +all-MiniLM-L6-v2+
-        # * +all-MiniLM-L12-v2+
-        # * +all-mpnet-base-v2+
-        # * +e5-base-v2+
-        # * +e5-small-v2+
-        # * +multilingual-e5-base+
-        # * +multilingual-e5-small+
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `hugging_face` service.
+        # Supported tasks include: `text_embedding`, `completion`, and `chat_completion`.
+        # To configure the endpoint, first visit the Hugging Face Inference Endpoints page and create a new endpoint.
+        # Select a model that supports the task you intend to use.
+        # For Elastic's `text_embedding` task:
+        # The selected model must support the `Sentence Embeddings` task. On the new endpoint creation page, select the `Sentence Embeddings` task under the `Advanced Configuration` section.
+        # After the endpoint has initialized, copy the generated endpoint URL.
+        # Recommended models for `text_embedding` task:
+        # * `all-MiniLM-L6-v2`
+        # * `all-MiniLM-L12-v2`
+        # * `all-mpnet-base-v2`
+        # * `e5-base-v2`
+        # * `e5-small-v2`
+        # * `multilingual-e5-base`
+        # * `multilingual-e5-small`
+        # For Elastic's `chat_completion` and `completion` tasks:
+        # The selected model must support the `Text Generation` task and expose OpenAI API. HuggingFace supports both serverless and dedicated endpoints for `Text Generation`. When creating dedicated endpoint select the `Text Generation` task.
+        # After the endpoint is initialized (for dedicated) or ready (for serverless), ensure it supports the OpenAI API and includes `/v1/chat/completions` part in URL. Then, copy the full endpoint URL for use.
+        # Recommended models for `chat_completion` and `completion` tasks:
+        # * `Mistral-7B-Instruct-v0.2`
+        # * `QwQ-32B`
+        # * `Phi-3-mini-128k-instruct`
+        # For Elastic's `rerank` task:
+        # The selected model must support the `sentence-ranking` task and expose OpenAI API.
+        # HuggingFace supports only dedicated (not serverless) endpoints for `Rerank` so far.
+        # After the endpoint is initialized, copy the full endpoint URL for use.
+        # Tested models for `rerank` task:
+        # * `bge-reranker-base`
+        # * `jina-reranker-v1-turbo-en-GGUF`
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :huggingface_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-hugging-face
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-hugging-face
         #
         def put_hugging_face(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_hugging_face' }
@@ -74,7 +98,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_huggingface_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_jinaai.rb

@@ -23,21 +23,28 @@ module Elasticsearch
     module Inference
       module Actions
         # Create an JinaAI inference endpoint.
-        # Create an inference endpoint to perform an inference task with the +jinaai+ service.
-        # To review the available +rerank+ models, refer to <https://jina.ai/reranker>.
-        # To review the available +text_embedding+ models, refer to the <https://jina.ai/embeddings/>.
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `jinaai` service.
+        # To review the available `rerank` models, refer to <https://jina.ai/reranker>.
+        # To review the available `text_embedding` models, refer to the <https://jina.ai/embeddings/>.
         #
         # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :jinaai_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-jinaai
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-jinaai
         #
         def put_jinaai(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_jinaai' }
@@ -65,7 +72,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_jinaai_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)

data/lib/elasticsearch/api/actions/inference/put_mistral.rb

@@ -23,20 +23,26 @@ module Elasticsearch
     module Inference
       module Actions
         # Create a Mistral inference endpoint.
-        # Creates an inference endpoint to perform an inference task with the +mistral+ service.
-        # When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-        # After creating the endpoint, wait for the model deployment to complete before using it.
-        # To verify the deployment status, use the get trained model statistics API.
-        # Look for +"state": "fully_allocated"+ in the response and ensure that the +"allocation_count"+ matches the +"target_allocation_count"+.
-        # Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
+        # Create an inference endpoint to perform an inference task with the `mistral` service.
         #
-        # @option arguments [String] :task_type The task type.
-        #  The only valid task type for the model to perform is +text_embedding+. (*Required*)
+        # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
         # @option arguments [String] :mistral_inference_id The unique identifier of the inference endpoint. (*Required*)
+        # @option arguments [Time] :timeout Specifies the amount of time to wait for the inference endpoint to be created. Server default: 30s.
+        # @option arguments [Boolean] :error_trace When set to `true` Elasticsearch will include the full stack trace of errors
+        #  when they occur.
+        # @option arguments [String, Array<String>] :filter_path Comma-separated list of filters in dot notation which reduce the response
+        #  returned by Elasticsearch.
+        # @option arguments [Boolean] :human When set to `true` will return statistics in a format suitable for humans.
+        #  For example `"exists_time": "1h"` for humans and
+        #  `"exists_time_in_millis": 3600000` for computers. When disabled the human
+        #  readable values will be omitted. This makes sense for responses being consumed
+        #  only by machines.
+        # @option arguments [Boolean] :pretty If set to `true` the returned JSON will be "pretty-formatted". Only use
+        #  this option for debugging only.
         # @option arguments [Hash] :headers Custom HTTP headers
         # @option arguments [Hash] :body request body
         #
-        # @see https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-mistral
+        # @see https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-mistral
         #
         def put_mistral(arguments = {})
           request_opts = { endpoint: arguments[:endpoint] || 'inference.put_mistral' }
@@ -64,7 +70,7 @@ module Elasticsearch
 
           method = Elasticsearch::API::HTTP_PUT
           path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_mistral_inference_id)}"
-          params = {}
+          params = Utils.process_params(arguments)
 
           Elasticsearch::API::Response.new(
             perform_request(method, path, params, body, headers, request_opts)