vellum_ai 0.3.4

data/lib/vellum_ai/types/workflow_stream_event.rb

@@ -0,0 +1,90 @@
+# frozen_string_literal: true
+
+require "json"
+require_relative "workflow_execution_workflow_result_event"
+require_relative "workflow_execution_node_result_event"
+
+module Vellum
+  class WorkflowStreamEvent
+    attr_reader :member, :discriminant
+
+    private_class_method :new
+    alias kind_of? is_a?
+    # @param member [Object]
+    # @param discriminant [String]
+    # @return [WorkflowStreamEvent]
+    def initialize(member:, discriminant:)
+      # @type [Object]
+      @member = member
+      # @type [String]
+      @discriminant = discriminant
+    end
+
+    # Deserialize a JSON object to an instance of WorkflowStreamEvent
+    #
+    # @param json_object [JSON]
+    # @return [WorkflowStreamEvent]
+    def self.from_json(json_object:)
+      struct = JSON.parse(json_object, object_class: OpenStruct)
+      member = case struct.type
+               when "WORKFLOW"
+                 WorkflowExecutionWorkflowResultEvent.from_json(json_object: json_object)
+               when "NODE"
+                 WorkflowExecutionNodeResultEvent.from_json(json_object: json_object)
+               else
+                 WorkflowExecutionWorkflowResultEvent.from_json(json_object: json_object)
+               end
+      new(member: member, discriminant: struct.type)
+    end
+
+    # For Union Types, to_json functionality is delegated to the wrapped member.
+    #
+    # @return [JSON]
+    def to_json(*_args)
+      case @discriminant
+      when "WORKFLOW"
+        { **@member.to_json, type: @discriminant }.to_json
+      when "NODE"
+        { **@member.to_json, type: @discriminant }.to_json
+      else
+        { "type": @discriminant, value: @member }.to_json
+      end
+      @member.to_json
+    end
+
+    # Leveraged for Union-type generation, validate_raw attempts to parse the given hash and check each fields type against the current object's property definitions.
+    #
+    # @param obj [Object]
+    # @return [Void]
+    def self.validate_raw(obj:)
+      case obj.type
+      when "WORKFLOW"
+        WorkflowExecutionWorkflowResultEvent.validate_raw(obj: obj)
+      when "NODE"
+        WorkflowExecutionNodeResultEvent.validate_raw(obj: obj)
+      else
+        raise("Passed value matched no type within the union, validation failed.")
+      end
+    end
+
+    # For Union Types, is_a? functionality is delegated to the wrapped member.
+    #
+    # @param obj [Object]
+    # @return [Boolean]
+    def is_a?(obj)
+      @member.is_a?(obj)
+    end
+
+    # @param member [WorkflowExecutionWorkflowResultEvent]
+    # @return [WorkflowStreamEvent]
+    def self.workflow(member:)
+      new(member: member, discriminant: "WORKFLOW")
+    end
+
+    # @param member [WorkflowExecutionNodeResultEvent]
+    # @return [WorkflowStreamEvent]
+    def self.node(member:)
+      new(member: member, discriminant: "NODE")
+    end
+  end
+end

data/lib/vellum_ai/workflow_deployments/client.rb

@@ -0,0 +1,82 @@
+# frozen_string_literal: true
+
+require_relative "../../requests"
+require_relative "types/workflow_deployments_list_request_status"
+require_relative "../types/paginated_slim_workflow_deployment_list"
+require "async"
+
+module Vellum
+  class WorkflowDeploymentsClient
+    attr_reader :request_client
+
+    # @param request_client [RequestClient]
+    # @return [WorkflowDeploymentsClient]
+    def initialize(request_client:)
+      # @type [RequestClient]
+      @request_client = request_client
+    end
+
+    # @param limit [Integer] Number of results to return per page.
+    # @param offset [Integer] The initial index from which to return the results.
+    # @param ordering [String] Which field to use when ordering the results.
+    # @param status [WORKFLOW_DEPLOYMENTS_LIST_REQUEST_STATUS] The current status of the workflow deployment
+    #   - `ACTIVE` - Active
+    #   - `ARCHIVED` - Archived
+    # @param request_options [RequestOptions]
+    # @return [PaginatedSlimWorkflowDeploymentList]
+    def list(limit: nil, offset: nil, ordering: nil, status: nil, request_options: nil)
+      response = @request_client.conn.get do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.params = {
+          **(request_options&.additional_query_parameters || {}),
+          "limit": limit,
+          "offset": offset,
+          "ordering": ordering,
+          "status": status
+        }.compact
+        req.url "#{@request_client.default_environment[:Default]}/v1/workflow-deployments"
+      end
+      PaginatedSlimWorkflowDeploymentList.from_json(json_object: response.body)
+    end
+  end
+
+  class AsyncWorkflowDeploymentsClient
+    attr_reader :request_client
+
+    # @param request_client [AsyncRequestClient]
+    # @return [AsyncWorkflowDeploymentsClient]
+    def initialize(request_client:)
+      # @type [AsyncRequestClient]
+      @request_client = request_client
+    end
+
+    # @param limit [Integer] Number of results to return per page.
+    # @param offset [Integer] The initial index from which to return the results.
+    # @param ordering [String] Which field to use when ordering the results.
+    # @param status [WORKFLOW_DEPLOYMENTS_LIST_REQUEST_STATUS] The current status of the workflow deployment
+    #   - `ACTIVE` - Active
+    #   - `ARCHIVED` - Archived
+    # @param request_options [RequestOptions]
+    # @return [PaginatedSlimWorkflowDeploymentList]
+    def list(limit: nil, offset: nil, ordering: nil, status: nil, request_options: nil)
+      Async do
+        response = @request_client.conn.get do |req|
+          req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+          req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+          req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+          req.params = {
+            **(request_options&.additional_query_parameters || {}),
+            "limit": limit,
+            "offset": offset,
+            "ordering": ordering,
+            "status": status
+          }.compact
+          req.url "#{@request_client.default_environment[:Default]}/v1/workflow-deployments"
+        end
+        PaginatedSlimWorkflowDeploymentList.from_json(json_object: response.body)
+      end
+    end
+  end
+end

data/lib/vellum_ai/workflow_deployments/types/workflow_deployments_list_request_status.rb

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+module Vellum
+  module WorkflowDeployments
+    # @type [WORKFLOW_DEPLOYMENTS_LIST_REQUEST_STATUS]
+    WORKFLOW_DEPLOYMENTS_LIST_REQUEST_STATUS = { active: "ACTIVE", archived: "ARCHIVED" }.freeze
+  end
+end

data/lib/vellum_ai.rb

@@ -0,0 +1,476 @@
+# frozen_string_literal: true
+
+require_relative "environment"
+require_relative "types_export"
+require_relative "requests"
+require_relative "vellum_ai/deployments/client"
+require_relative "vellum_ai/document_indexes/client"
+require_relative "vellum_ai/documents/client"
+require_relative "vellum_ai/model_versions/client"
+require_relative "vellum_ai/registered_prompts/client"
+require_relative "vellum_ai/sandboxes/client"
+require_relative "vellum_ai/test_suites/client"
+require_relative "vellum_ai/workflow_deployments/client"
+require_relative "vellum_ai/types/prompt_deployment_input_request"
+require_relative "vellum_ai/types/prompt_deployment_expand_meta_request_request"
+require_relative "vellum_ai/types/raw_prompt_execution_overrides_request"
+require_relative "vellum_ai/types/execute_prompt_response"
+require_relative "vellum_ai/types/workflow_request_input_request"
+require_relative "vellum_ai/types/execute_workflow_response"
+require_relative "vellum_ai/types/generate_request"
+require_relative "vellum_ai/types/generate_options_request"
+require_relative "vellum_ai/types/generate_response"
+require_relative "vellum_ai/types/search_request_options_request"
+require_relative "vellum_ai/types/search_response"
+require_relative "vellum_ai/types/submit_completion_actual_request"
+require_relative "vellum_ai/types/submit_workflow_execution_actual_request"
+
+module Vellum
+  class Client
+    attr_reader :deployments, :document_indexes, :documents, :model_versions, :registered_prompts, :sandboxes,
+                :test_suites, :workflow_deployments
+
+    # @param environment [Environment]
+    # @param max_retries [Long] The number of times to retry a failed request, defaults to 2.
+    # @param timeout_in_seconds [Long]
+    # @param api_key [String]
+    # @return [Client]
+    def initialize(api_key:, environment: Environment::PRODUCTION, max_retries: nil, timeout_in_seconds: nil)
+      @request_client = RequestClient.new(environment: environment, max_retries: max_retries,
+                                          timeout_in_seconds: timeout_in_seconds, api_key: api_key)
+      @deployments = DeploymentsClient.new(request_client: @request_client)
+      @document_indexes = DocumentIndexesClient.new(request_client: @request_client)
+      @documents = DocumentsClient.new(request_client: @request_client)
+      @model_versions = ModelVersionsClient.new(request_client: @request_client)
+      @registered_prompts = RegisteredPromptsClient.new(request_client: @request_client)
+      @sandboxes = SandboxesClient.new(request_client: @request_client)
+      @test_suites = TestSuitesClient.new(request_client: @request_client)
+      @workflow_deployments = WorkflowDeploymentsClient.new(request_client: @request_client)
+    end
+
+    # Executes a deployed Prompt and returns the result.
+    #
+    # Note: This endpoint temporarily does not support prompts with function calling, support is coming soon.
+    # In the meantime, we recommend still using the `/generate` endpoint for prompts with function calling.
+    #
+    # @param inputs [Array<Hash>] The list of inputs defined in the Prompt's deployment with their corresponding values.Request of type Array<PromptDeploymentInputRequest>, as a Hash
+    # @param prompt_deployment_id [String] The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+    # @param prompt_deployment_name [String] The name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+    # @param release_tag [String] Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+    # @param external_id [String]
+    # @param expand_meta [Hash] The name of the Prompt Deployment. Must provide either this or prompt_deployment_id.Request of type PromptDeploymentExpandMetaRequestRequest, as a Hash
+    #   * :model_name (Boolean)
+    #   * :latency (Boolean)
+    #   * :deployment_release_tag (Boolean)
+    #   * :prompt_version_id (Boolean)
+    #   * :finish_reason (Boolean)
+    # @param raw_overrides [Hash] Request of type RawPromptExecutionOverridesRequest, as a Hash
+    #   * :body (Hash{String => String})
+    #   * :headers (Hash{String => String})
+    #   * :url (String)
+    # @param expand_raw [Array<String>] Returns the raw API response data sent from the model host. Combined with `raw_overrides`, it can be used to access new features from models.
+    # @param metadata [Hash{String => String}]
+    # @param request_options [RequestOptions]
+    # @return [ExecutePromptResponse]
+    def execute_prompt(inputs:, prompt_deployment_id: nil, prompt_deployment_name: nil, release_tag: nil,
+                       external_id: nil, expand_meta: nil, raw_overrides: nil, expand_raw: nil, metadata: nil, request_options: nil)
+      response = @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          inputs: inputs,
+          prompt_deployment_id: prompt_deployment_id,
+          prompt_deployment_name: prompt_deployment_name,
+          release_tag: release_tag,
+          external_id: external_id,
+          expand_meta: expand_meta,
+          raw_overrides: raw_overrides,
+          expand_raw: expand_raw,
+          metadata: metadata
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/execute-prompt"
+      end
+      ExecutePromptResponse.from_json(json_object: response.body)
+    end
+
+    # Executes a deployed Workflow and returns its outputs.
+    #
+    # @param workflow_deployment_id [String] The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+    # @param workflow_deployment_name [String] The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+    # @param release_tag [String] Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+    # @param inputs [Array<Hash>] The list of inputs defined in the Workflow's Deployment with their corresponding values.Request of type Array<WorkflowRequestInputRequest>, as a Hash
+    # @param external_id [String] Optionally include a unique identifier for monitoring purposes.
+    # @param request_options [RequestOptions]
+    # @return [ExecuteWorkflowResponse]
+    def execute_workflow(inputs:, workflow_deployment_id: nil, workflow_deployment_name: nil, release_tag: nil,
+                         external_id: nil, request_options: nil)
+      response = @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          workflow_deployment_id: workflow_deployment_id,
+          workflow_deployment_name: workflow_deployment_name,
+          release_tag: release_tag,
+          inputs: inputs,
+          external_id: external_id
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/execute-workflow"
+      end
+      ExecuteWorkflowResponse.from_json(json_object: response.body)
+    end
+
+    # Generate a completion using a previously defined deployment.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param deployment_id [String] The ID of the deployment. Must provide either this or deployment_name.
+    # @param deployment_name [String] The name of the deployment. Must provide either this or deployment_id.
+    # @param requests [Array<Hash>] The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.Request of type Array<GenerateRequest>, as a Hash
+    #   * :input_values (Hash{String => String})
+    #   * :chat_history (Array<ChatMessageRequest>)
+    #   * :external_ids (Array<String>)
+    # @param options [Hash] Additional configuration that can be used to control what's included in the response.Request of type GenerateOptionsRequest, as a Hash
+    #   * :logprobs (LOGPROBS_ENUM)
+    # @param request_options [RequestOptions]
+    # @return [GenerateResponse]
+    def generate(requests:, deployment_id: nil, deployment_name: nil, options: nil, request_options: nil)
+      response = @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          deployment_id: deployment_id,
+          deployment_name: deployment_name,
+          requests: requests,
+          options: options
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/generate"
+      end
+      GenerateResponse.from_json(json_object: response.body)
+    end
+
+    # Perform a search against a document index.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param index_id [String] The ID of the index to search against. Must provide either this or index_name.
+    # @param index_name [String] The name of the index to search against. Must provide either this or index_id.
+    # @param query [String] The query to search for.
+    # @param options [Hash] Configuration options for the search.Request of type SearchRequestOptionsRequest, as a Hash
+    #   * :limit (Integer)
+    #   * :weights (Hash)
+    #     * :semantic_similarity (Float)
+    #     * :keywords (Float)
+    #   * :result_merging (Hash)
+    #     * :enabled (Boolean)
+    #   * :filters (Hash)
+    #     * :external_ids (Array<String>)
+    #     * :metadata (Hash)
+    #       * :combinator (METADATA_FILTER_RULE_COMBINATOR)
+    #       * :negated (Boolean)
+    #       * :rules (Array<MetadataFilterRuleRequest>)
+    #       * :field (String)
+    #       * :operator (LOGICAL_OPERATOR)
+    #       * :value (String)
+    # @param request_options [RequestOptions]
+    # @return [SearchResponse]
+    def search(query:, index_id: nil, index_name: nil, options: nil, request_options: nil)
+      response = @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          index_id: index_id,
+          index_name: index_name,
+          query: query,
+          options: options
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/search"
+      end
+      SearchResponse.from_json(json_object: response.body)
+    end
+
+    # Used to submit feedback regarding the quality of previously generated completions.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param deployment_id [String] The ID of the deployment. Must provide either this or deployment_name.
+    # @param deployment_name [String] The name of the deployment. Must provide either this or deployment_id.
+    # @param actuals [Array<Hash>] Feedback regarding the quality of previously generated completionsRequest of type Array<SubmitCompletionActualRequest>, as a Hash
+    #   * :id (String)
+    #   * :external_id (String)
+    #   * :text (String)
+    #   * :quality (Float)
+    #   * :timestamp (DateTime)
+    # @param request_options [RequestOptions]
+    # @return [Void]
+    def submit_completion_actuals(actuals:, deployment_id: nil, deployment_name: nil, request_options: nil)
+      @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          deployment_id: deployment_id,
+          deployment_name: deployment_name,
+          actuals: actuals
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/submit-completion-actuals"
+      end
+    end
+
+    #     Used to submit feedback regarding the quality of previous workflow execution and its outputs.
+    #
+    #     **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param actuals [Array<Hash>] Feedback regarding the quality of an output on a previously executed workflow.Request of type Array<SubmitWorkflowExecutionActualRequest>, as a Hash
+    # @param execution_id [String] The Vellum-generated ID of a previously executed workflow. Must provide either this or external_id.
+    # @param external_id [String] The external ID that was originally provided by when executing the workflow, if applicable, that you'd now like to submit actuals for. Must provide either this or execution_id.
+    # @param request_options [RequestOptions]
+    # @return [Void]
+    def submit_workflow_execution_actuals(actuals:, execution_id: nil, external_id: nil, request_options: nil)
+      @request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          actuals: actuals,
+          execution_id: execution_id,
+          external_id: external_id
+        }.compact
+        req.url "#{@request_client.default_environment[:Predict]}/v1/submit-workflow-execution-actuals"
+      end
+    end
+  end
+
+  class AsyncClient
+    attr_reader :deployments, :document_indexes, :documents, :model_versions, :registered_prompts, :sandboxes,
+                :test_suites, :workflow_deployments
+
+    # @param environment [Environment]
+    # @param max_retries [Long] The number of times to retry a failed request, defaults to 2.
+    # @param timeout_in_seconds [Long]
+    # @param api_key [String]
+    # @return [AsyncClient]
+    def initialize(api_key:, environment: Environment::PRODUCTION, max_retries: nil, timeout_in_seconds: nil)
+      @async_request_client = AsyncRequestClient.new(environment: environment, max_retries: max_retries,
+                                                     timeout_in_seconds: timeout_in_seconds, api_key: api_key)
+      @deployments = AsyncDeploymentsClient.new(request_client: @async_request_client)
+      @document_indexes = AsyncDocumentIndexesClient.new(request_client: @async_request_client)
+      @documents = AsyncDocumentsClient.new(request_client: @async_request_client)
+      @model_versions = AsyncModelVersionsClient.new(request_client: @async_request_client)
+      @registered_prompts = AsyncRegisteredPromptsClient.new(request_client: @async_request_client)
+      @sandboxes = AsyncSandboxesClient.new(request_client: @async_request_client)
+      @test_suites = AsyncTestSuitesClient.new(request_client: @async_request_client)
+      @workflow_deployments = AsyncWorkflowDeploymentsClient.new(request_client: @async_request_client)
+    end
+
+    # Executes a deployed Prompt and returns the result.
+    #
+    # Note: This endpoint temporarily does not support prompts with function calling, support is coming soon.
+    # In the meantime, we recommend still using the `/generate` endpoint for prompts with function calling.
+    #
+    # @param inputs [Array<Hash>] The list of inputs defined in the Prompt's deployment with their corresponding values.Request of type Array<PromptDeploymentInputRequest>, as a Hash
+    # @param prompt_deployment_id [String] The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+    # @param prompt_deployment_name [String] The name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+    # @param release_tag [String] Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+    # @param external_id [String]
+    # @param expand_meta [Hash] The name of the Prompt Deployment. Must provide either this or prompt_deployment_id.Request of type PromptDeploymentExpandMetaRequestRequest, as a Hash
+    #   * :model_name (Boolean)
+    #   * :latency (Boolean)
+    #   * :deployment_release_tag (Boolean)
+    #   * :prompt_version_id (Boolean)
+    #   * :finish_reason (Boolean)
+    # @param raw_overrides [Hash] Request of type RawPromptExecutionOverridesRequest, as a Hash
+    #   * :body (Hash{String => String})
+    #   * :headers (Hash{String => String})
+    #   * :url (String)
+    # @param expand_raw [Array<String>] Returns the raw API response data sent from the model host. Combined with `raw_overrides`, it can be used to access new features from models.
+    # @param metadata [Hash{String => String}]
+    # @param request_options [RequestOptions]
+    # @return [ExecutePromptResponse]
+    def execute_prompt(inputs:, prompt_deployment_id: nil, prompt_deployment_name: nil, release_tag: nil,
+                       external_id: nil, expand_meta: nil, raw_overrides: nil, expand_raw: nil, metadata: nil, request_options: nil)
+      response = @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          inputs: inputs,
+          prompt_deployment_id: prompt_deployment_id,
+          prompt_deployment_name: prompt_deployment_name,
+          release_tag: release_tag,
+          external_id: external_id,
+          expand_meta: expand_meta,
+          raw_overrides: raw_overrides,
+          expand_raw: expand_raw,
+          metadata: metadata
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/execute-prompt"
+      end
+      ExecutePromptResponse.from_json(json_object: response.body)
+    end
+
+    # Executes a deployed Workflow and returns its outputs.
+    #
+    # @param workflow_deployment_id [String] The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+    # @param workflow_deployment_name [String] The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+    # @param release_tag [String] Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+    # @param inputs [Array<Hash>] The list of inputs defined in the Workflow's Deployment with their corresponding values.Request of type Array<WorkflowRequestInputRequest>, as a Hash
+    # @param external_id [String] Optionally include a unique identifier for monitoring purposes.
+    # @param request_options [RequestOptions]
+    # @return [ExecuteWorkflowResponse]
+    def execute_workflow(inputs:, workflow_deployment_id: nil, workflow_deployment_name: nil, release_tag: nil,
+                         external_id: nil, request_options: nil)
+      response = @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          workflow_deployment_id: workflow_deployment_id,
+          workflow_deployment_name: workflow_deployment_name,
+          release_tag: release_tag,
+          inputs: inputs,
+          external_id: external_id
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/execute-workflow"
+      end
+      ExecuteWorkflowResponse.from_json(json_object: response.body)
+    end
+
+    # Generate a completion using a previously defined deployment.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param deployment_id [String] The ID of the deployment. Must provide either this or deployment_name.
+    # @param deployment_name [String] The name of the deployment. Must provide either this or deployment_id.
+    # @param requests [Array<Hash>] The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.Request of type Array<GenerateRequest>, as a Hash
+    #   * :input_values (Hash{String => String})
+    #   * :chat_history (Array<ChatMessageRequest>)
+    #   * :external_ids (Array<String>)
+    # @param options [Hash] Additional configuration that can be used to control what's included in the response.Request of type GenerateOptionsRequest, as a Hash
+    #   * :logprobs (LOGPROBS_ENUM)
+    # @param request_options [RequestOptions]
+    # @return [GenerateResponse]
+    def generate(requests:, deployment_id: nil, deployment_name: nil, options: nil, request_options: nil)
+      response = @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          deployment_id: deployment_id,
+          deployment_name: deployment_name,
+          requests: requests,
+          options: options
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/generate"
+      end
+      GenerateResponse.from_json(json_object: response.body)
+    end
+
+    # Perform a search against a document index.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param index_id [String] The ID of the index to search against. Must provide either this or index_name.
+    # @param index_name [String] The name of the index to search against. Must provide either this or index_id.
+    # @param query [String] The query to search for.
+    # @param options [Hash] Configuration options for the search.Request of type SearchRequestOptionsRequest, as a Hash
+    #   * :limit (Integer)
+    #   * :weights (Hash)
+    #     * :semantic_similarity (Float)
+    #     * :keywords (Float)
+    #   * :result_merging (Hash)
+    #     * :enabled (Boolean)
+    #   * :filters (Hash)
+    #     * :external_ids (Array<String>)
+    #     * :metadata (Hash)
+    #       * :combinator (METADATA_FILTER_RULE_COMBINATOR)
+    #       * :negated (Boolean)
+    #       * :rules (Array<MetadataFilterRuleRequest>)
+    #       * :field (String)
+    #       * :operator (LOGICAL_OPERATOR)
+    #       * :value (String)
+    # @param request_options [RequestOptions]
+    # @return [SearchResponse]
+    def search(query:, index_id: nil, index_name: nil, options: nil, request_options: nil)
+      response = @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          index_id: index_id,
+          index_name: index_name,
+          query: query,
+          options: options
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/search"
+      end
+      SearchResponse.from_json(json_object: response.body)
+    end
+
+    # Used to submit feedback regarding the quality of previously generated completions.
+    #
+    # **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param deployment_id [String] The ID of the deployment. Must provide either this or deployment_name.
+    # @param deployment_name [String] The name of the deployment. Must provide either this or deployment_id.
+    # @param actuals [Array<Hash>] Feedback regarding the quality of previously generated completionsRequest of type Array<SubmitCompletionActualRequest>, as a Hash
+    #   * :id (String)
+    #   * :external_id (String)
+    #   * :text (String)
+    #   * :quality (Float)
+    #   * :timestamp (DateTime)
+    # @param request_options [RequestOptions]
+    # @return [Void]
+    def submit_completion_actuals(actuals:, deployment_id: nil, deployment_name: nil, request_options: nil)
+      @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          deployment_id: deployment_id,
+          deployment_name: deployment_name,
+          actuals: actuals
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/submit-completion-actuals"
+      end
+    end
+
+    #     Used to submit feedback regarding the quality of previous workflow execution and its outputs.
+    #
+    #     **Note:** Uses a base url of `https://predict.vellum.ai`.
+    #
+    # @param actuals [Array<Hash>] Feedback regarding the quality of an output on a previously executed workflow.Request of type Array<SubmitWorkflowExecutionActualRequest>, as a Hash
+    # @param execution_id [String] The Vellum-generated ID of a previously executed workflow. Must provide either this or external_id.
+    # @param external_id [String] The external ID that was originally provided by when executing the workflow, if applicable, that you'd now like to submit actuals for. Must provide either this or execution_id.
+    # @param request_options [RequestOptions]
+    # @return [Void]
+    def submit_workflow_execution_actuals(actuals:, execution_id: nil, external_id: nil, request_options: nil)
+      @async_request_client.conn.post do |req|
+        req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
+        req.headers["X_API_KEY"] = request_options.api_key unless request_options&.api_key.nil?
+        req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
+        req.body = {
+          **(request_options&.additional_body_parameters || {}),
+          actuals: actuals,
+          execution_id: execution_id,
+          external_id: external_id
+        }.compact
+        req.url "#{@async_request_client.default_environment[:Predict]}/v1/submit-workflow-execution-actuals"
+      end
+    end
+  end
+end