[API] Adds inference.put_ai21 and inference.put_llama

picandocodigo · picandocodigo · commit 6bcff71e2204 · 2025-08-11T14:19:10.000+01:00
diff --git a/elasticsearch-api/lib/elasticsearch/api/actions/inference/put.rb b/elasticsearch-api/lib/elasticsearch/api/actions/inference/put.rb
@@ -27,24 +27,26 @@ module Actions
         # For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.
         # However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.
         # The following integrations are available through the inference API. You can find the available task types next to the integration name:
+        # * AI21 (`chat_completion`, `completion`)
         # * AlibabaCloud AI Search (`completion`, `rerank`, `sparse_embedding`, `text_embedding`)
         # * Amazon Bedrock (`completion`, `text_embedding`)
         # * Amazon SageMaker (`chat_completion`, `completion`, `rerank`, `sparse_embedding`, `text_embedding`)
         # * Anthropic (`completion`)
         # * Azure AI Studio (`completion`, 'rerank', `text_embedding`)
         # * Azure OpenAI (`completion`, `text_embedding`)
         # * Cohere (`completion`, `rerank`, `text_embedding`)
-        # * DeepSeek (`completion`, `chat_completion`)
+        # * DeepSeek (`chat_completion`, `completion`)
         # * Elasticsearch (`rerank`, `sparse_embedding`, `text_embedding` - this service is for built-in models and models uploaded through Eland)
         # * ELSER (`sparse_embedding`)
         # * Google AI Studio (`completion`, `text_embedding`)
-        # * Google Vertex AI (`rerank`, `text_embedding`)
+        # * Google Vertex AI (`chat_completion`, `completion`, `rerank`, `text_embedding`)
         # * Hugging Face (`chat_completion`, `completion`, `rerank`, `text_embedding`)
+        # * JinaAI (`rerank`, `text_embedding`)
+        # * Llama (`chat_completion`, `completion`, `text_embedding`)
         # * Mistral (`chat_completion`, `completion`, `text_embedding`)
         # * OpenAI (`chat_completion`, `completion`, `text_embedding`)
-        # * VoyageAI (`text_embedding`, `rerank`)
+        # * VoyageAI (`rerank`, `text_embedding`)
         # * Watsonx inference integration (`text_embedding`)
-        # * JinaAI (`text_embedding`, `rerank`)
         #
         # @option arguments [String] :task_type The task type. Refer to the integration list in the API description for the available task types.
         # @option arguments [String] :inference_id The inference Id (*Required*)
diff --git a/elasticsearch-api/lib/elasticsearch/api/actions/inference/put_ai21.rb b/elasticsearch-api/lib/elasticsearch/api/actions/inference/put_ai21.rb
@@ -0,0 +1,78 @@
+# 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 AI21 inference endpoint.
+        # Create an inference endpoint to perform an inference task with the `ai21` service.
+        #
+        # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
+        # @option arguments [String] :ai21_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-ai21
+        #
+        def put_ai21(arguments = {})
+          request_opts = { endpoint: arguments[:endpoint] || 'inference.put_ai21' }
+
+          defined_params = [:task_type, :ai21_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]
+          raise ArgumentError, "Required argument 'ai21_inference_id' missing" unless arguments[:ai21_inference_id]
+
+          arguments = arguments.clone
+          headers = arguments.delete(:headers) || {}
+
+          body = arguments.delete(:body)
+
+          _task_type = arguments.delete(:task_type)
+
+          _ai21_inference_id = arguments.delete(:ai21_inference_id)
+
+          method = Elasticsearch::API::HTTP_PUT
+          path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_ai21_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
diff --git a/elasticsearch-api/lib/elasticsearch/api/actions/inference/put_llama.rb b/elasticsearch-api/lib/elasticsearch/api/actions/inference/put_llama.rb
@@ -0,0 +1,78 @@
+# 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 Llama inference endpoint.
+        # Create an inference endpoint to perform an inference task with the `llama` service.
+        #
+        # @option arguments [String] :task_type The type of the inference task that the model will perform. (*Required*)
+        # @option arguments [String] :llama_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-llama
+        #
+        def put_llama(arguments = {})
+          request_opts = { endpoint: arguments[:endpoint] || 'inference.put_llama' }
+
+          defined_params = [:task_type, :llama_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]
+          raise ArgumentError, "Required argument 'llama_inference_id' missing" unless arguments[:llama_inference_id]
+
+          arguments = arguments.clone
+          headers = arguments.delete(:headers) || {}
+
+          body = arguments.delete(:body)
+
+          _task_type = arguments.delete(:task_type)
+
+          _llama_inference_id = arguments.delete(:llama_inference_id)
+
+          method = Elasticsearch::API::HTTP_PUT
+          path   = "_inference/#{Utils.listify(_task_type)}/#{Utils.listify(_llama_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
diff --git a/elasticsearch-api/spec/unit/actions/inference/put_ai21_spec.rb b/elasticsearch-api/spec/unit/actions/inference/put_ai21_spec.rb
@@ -0,0 +1,36 @@
+# 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.
+
+require 'spec_helper'
+
+describe 'client#inference.put_ai21' do
+  let(:expected_args) do
+    [
+      'PUT',
+      '_inference/foo/bar',
+      {},
+      nil,
+      {},
+      { defined_params: { ai21_inference_id: 'bar', task_type: 'foo' },
+        endpoint: 'inference.put_ai21' }
+    ]
+  end
+
+  it 'performs the request' do
+    expect(client_double.inference.put_ai21(task_type: 'foo', ai21_inference_id: 'bar')).to be_a Elasticsearch::API::Response
+  end
+end
diff --git a/elasticsearch-api/spec/unit/actions/inference/put_llama_spec.rb b/elasticsearch-api/spec/unit/actions/inference/put_llama_spec.rb
@@ -0,0 +1,36 @@
+# 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.
+
+require 'spec_helper'
+
+describe 'client#inference.put_llama' do
+  let(:expected_args) do
+    [
+      'PUT',
+      '_inference/foo/bar',
+      {},
+      nil,
+      {},
+      { defined_params: { llama_inference_id: 'bar', task_type: 'foo' },
+        endpoint: 'inference.put_llama' }
+    ]
+  end
+
+  it 'performs the request' do
+    expect(client_double.inference.put_llama(task_type: 'foo', llama_inference_id: 'bar')).to be_a Elasticsearch::API::Response
+  end
+end
