Class ZCL_IBMX_WATSONX_AI_ML

Class ZCL_IBMX_WATSONX_AI_ML_V1

public inheriting from ZCL_IBMX_SERVICE_EXT create public

Documentation

watsonx.ai

No documentation available.

Types

Visibility and Level	Name	Documentation
public	tt_json_patch_operation TYPE STANDARD TABLE OF T_JSON_PATCH_OPERATION WITH NON-UNIQUE DEFAULT KEY	Array parameter type for method AI_SERVICES_UPDATE
public	t_aiservice_content_metadata (structured type)	The metadata related to the attachment.
public	t_aiservice_documentation (structured type)	The documentation of the AI service request body and response body.
public	t_aiservice_entity (structured type)	The details of the AI service to be created.
public	t_aiservice_request (structured type)	The details of the AI service to be created.
public	t_aiservice_resource (structured type)	The information for a flow.
public	t_aiservice_resources (structured type)	A paginated list of AI services.
public	t_aiservice_resource_entity (structured type)	The details of the AI service to be created.
public	t_api_error (structured type)	An error message.
public	t_api_error_response (structured type)	The data returned when an error is encountered.
public	t_api_error_target (structured type)	The target of the error.
public	t_asset_ref (structured type)	The field that identifies the asset.
public	t_at_arggnrtn_mdl_at_argcstm_1 (structured type)	Properties describing the custom foundation model.
public	t_at_arggnrtn_mdl_at_argmdl (structured type)	Properties describing the foundation model.
public	t_auto_aidata_location (structured type)	A reference to data.
public	t_auto_airagchunking (structured type)	The chunking details for an AutoAI RAG pattern,.
public	t_auto_airagconstraints (structured type)	The constraint parameters for an AutoAI RAG run.
public	t_auto_airagcontext (structured type)	No documentation available.
public	t_auto_airagcustom_model (structured type)	Properties describing the custom foundation model.
public	t_auto_airagembeddings (structured type)	The embeddings properties for an AutoAI RAG pattern.
public	t_auto_airagfoundation_models type STRING	The id of the foundation model. If not provided AutoAI auto-selects 3 top rated models.
public	t_auto_airaggeneration_model type JSONOBJECT	No documentation available.
public	t_auto_airagmetadata (structured type)	The request fields that are not part of the returned entity.
public	t_auto_airagmetric (structured type)	The metric for a given property.
public	t_auto_airagmetrics (structured type)	The AutoAI RAG metrics, this contains the list of calculated metrics on test data (provided in the request) and (optionally) synthetic data autogenerated. Metric value is mean value calculated over all records in the dataset.
public	t_auto_airagmodel (structured type)	Properties describing the foundation model.
public	t_auto_airagmodel_params (structured type)	Properties that control the model and response.
public	t_auto_airagoptimization_param (structured type)	The optimization parameters for an AutoAI RAG run.
public	t_auto_airagparameters (structured type)	The parameters for an AutoAI RAG run.
public	t_auto_airagpattern (structured type)	Describes the elements and settings found during the optimization of the RAG pattern.
public	t_auto_airagrequest (structured type)	The request entity for an AutoAI RAG run.
public	t_auto_airagrequest_entity (structured type)	The request entity for an AutoAI RAG run.
public	t_auto_airagresponse (structured type)	The response of an AutoAI RAG run.
public	t_auto_airagresponse_entity (structured type)	The status of an AutoAI RAG run.
public	t_auto_airagresponse_results (structured type)	The AutoAI RAG results.
public	t_auto_airagresults (structured type)	The AutoAI RAG results.
public	t_auto_airagresult_location (structured type)	The location of the different result files.
public	t_auto_airagretrieval (structured type)	The retrieval details for an AutoAI RAG pattern,.
public	t_auto_airagsettings (structured type)	The RAG pattern configuration settings that were found during the optimization process.
public	t_auto_airagstatus (structured type)	The status of an AutoAI RAG run.
public	t_auto_airagstatus_object (structured type)	Status of the training job.
public	t_auto_airagvector_store (structured type)	Properties that describe the AutoAI RAG vector store that contains the results.
public	t_auto_ragresult_resources (structured type)	A paginated list of training definitions.
public	t_base_model (structured type)	The model id of the base model for this job.
public	t_cai_kit_text_gen_properties (structured type)	Properties that control the model and response that are only supported in caikit.
public	t_chat_item (structured type)	No documentation available.
public	t_commit (structured type)	No documentation available.
public	t_common_patch_request_helper (structured type)	The common fields that can be patched. This is a helper for `cpdctl`.
public	t_connection_asset (structured type)	A reference to connection.
public	t_consumptions_limit (structured type)	The limits that may be set per request.
public	t_cos_data_connection (structured type)	Contains a set of location fields specific to each data source.
public	t_cos_data_location (structured type)	Contains a set of fields specific to each connection.
public	t_created_at type DATETIME	The time when the response was created in ISO 8601 format.
public	t_custom type JSONOBJECT	User defined properties specified as key-value pairs.
public	t_data_connection type JSONOBJECT	Contains a set of fields specific to each connection. See here for [details about specifying connections](#datareferences).
public	t_data_connection_reference (structured type)	A reference to data with an optional data schema. If necessary, it is possible to provide a data connection that contains just the data schema.
public	t_data_location type MAP	Contains a set of fields that describe the location of the data with respect to the `connection`.
public	t_data_schema (structured type)	The schema of the expected data, see [datarecord-metadata-v2-schema](https://raw.githubusercontent.com/elyra-ai/pipel ine-schemas/master/common-pipeline/datarecord-metadata/datarecord-metadata-v2-sc hema.json) for the schema definition.
public	t_deployment_entity (structured type)	The definition of the deployment.
public	t_deployment_entity_common (structured type)	The common fields between a request and the response.
public	t_deployment_resource (structured type)	A deployment resource.
public	t_deployment_resource_entity (structured type)	The properties specific to `watsonx.ai` deployments.
public	t_deployment_resource_patch (structured type)	The common fields that can be patched. This is a helper for `cpdctl`.
public	t_deployment_resrc_collection (structured type)	The deployment resources.
public	t_deployment_resrc_prototype (structured type)	The deployment request entity (this description is not used).
public	t_deployment_status (structured type)	Specifies the current status, additional information about the deployment and any failure messages in case of deployment failures.
public	t_deployment_system (structured type)	System details including warnings.
public	t_deployment_system_details (structured type)	Optional details provided by the service about statistics of the number of deployments created. The deployments that are counted will depend on the request parameters.
public	t_deployment_text_chat (structured type)	No documentation available.
public	t_deployment_text_chat_msg type JSONOBJECT	No documentation available.
public	t_deployment_text_gen (structured type)	No documentation available.
public	t_deployment_text_gen_prop (structured type)	The template properties if this request refers to a prompt template.
public	t_document_extraction_common (structured type)	The details needed to create document extraction job.
public	t_document_extraction_request (structured type)	The properties that are part of a request that supports spaces and projects. Either `space_id` or `project_id` has to be provided and is mandatory.
public	t_document_extraction_resource (structured type)	The response from getting a specified document extraction job.
public	t_document_extraction_response (structured type)	The document extraction job properties.
public	t_document_extraction_status (structured type)	Status of the document extraction job.
public	t_doc_extraction_object_loc (structured type)	A reference to data.
public	t_doc_extraction_resources (structured type)	The response of getting all document extraction jobs.
public	t_dplymnt_txt_cht_msg_txt_cht1 (structured type)	The definition of an assistant message.
public	t_dplymnt_txt_cht_msg_txt_cht2 (structured type)	The definition of a control message.
public	t_dplymnt_txt_cht_msg_txt_cht3 (structured type)	The definition of a tool message.
public	t_dplymnt_txt_cht_msg_txt_cht4 (structured type)	The definition of a user message.
public	t_embedding (structured type)	The embedding values for a text string. The `input` field is only set if the corresponding `return_option` is set.
public	t_embeddings_request (structured type)	The text input for a given model to be used to generate the embeddings.
public	t_embeddings_response (structured type)	System details.
public	t_embeddings_response_fields (structured type)	The embeddings per input.
public	t_embedding_input_result (structured type)	The input text, this is only output if `parameters.return_options.input_text` is set to `true` in the request.
public	t_embedding_model_id type STRING	The `id` of the model to be used for this request. Please refer to the [list of models](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-mod els-embed.html?context=wx&audience=wdp).
public	t_embedding_parameters (structured type)	Parameters for text embedding requests.
public	t_embedding_return_options (structured type)	The return options for text embeddings.
public	t_entity_request_space_body (structured type)	The properties that are part of a request that supports spaces.
public	t_entity_req_spc_project_body (structured type)	The properties that are part of a request that supports spaces and projects. Either `space_id` or `project_id` has to be provided and is mandatory.
public	t_entity_req_spc_project_only (structured type)	The properties that are part of a request that supports spaces and projects. Either `space_id` or `project_id` has to be provided and is mandatory.
public	t_error (structured type)	An error object.
public	t_error_response (structured type)	An error response.
public	t_error_target (structured type)	The target of the error.
public	t_external_information (structured type)	No documentation available.
public	t_external_store_settings (structured type)	No documentation available.
public	t_ext_info_external_model (structured type)	No documentation available.
public	t_ext_info_external_prompt (structured type)	No documentation available.
public	t_ext_prmpt_addtnl_info_item (structured type)	No documentation available.
public	t_ext_prompt_additional_info TYPE STANDARD TABLE OF T_EXT_PRMPT_ADDTNL_INFO_ITEM WITH NON-UNIQUE DEFAULT KEY	No documentation available.
public	t_ext_str_settings_schema_fld (structured type)	No documentation available.
public	t_file_paths (structured type)	No documentation available.
public	t_fine_tuning_entity (structured type)	Status of the training job.
public	t_fine_tuning_parameters (structured type)	This field must not be set while creating a fine tuning job with InstructLab. The parameters for the job. Note that if `verbalizer` is provided then `response_template` must also be provided (and vice versa).
public	t_fine_tuning_request (structured type)	The fine tuning resource.
public	t_fine_tuning_resource (structured type)	The response of a fine tuning job.
public	t_fine_tuning_resources (structured type)	System details.
public	t_fine_tuning_resource_entity (structured type)	The fine tuning resource.
public	t_fine_tuning_resource_list (structured type)	No documentation available.
public	t_fine_tuning_training_metrics type JSONOBJECT	The metrics that can be returned by a fine tuning job created with InstructLab.
public	t_foundation_model (structured type)	A supported foundation model.
public	t_foundation_models (structured type)	System details.
public	t_foundation_models_array TYPE STANDARD TABLE OF T_FOUNDATION_MODEL WITH NON-UNIQUE DEFAULT KEY	The supported foundation models.
public	t_foundation_model_limits (structured type)	Limits per plan that may be set per request.
public	t_foundation_model_task (structured type)	A task that is covered by some of the foundation models that are supported in the service.
public	t_foundation_model_tasks (structured type)	System details.
public	t_foundation_model_tasks_array TYPE STANDARD TABLE OF T_FOUNDATION_MODEL_TASK WITH NON-UNIQUE DEFAULT KEY	The supported foundation model tasks.
public	t_foundation_model_tier type STRING	The tier of the model, depending on the `tier` the billing will be different, refer to the plan for the details. Note that input tokens and output tokens may be charged differently.
public	t_foundation_model_version (structured type)	A minor or patch version for the model.
public	t_geospatial_trans_data (structured type)	A data location of the input or output data.
public	t_geospatial_trans_entity (structured type)	The inputs and outputs required to create a transformation for the given model.
public	t_geospatial_trans_metadata (structured type)	The specific fields for the geospatial transformation metadata fields.
public	t_geospatial_trans_model_id type STRING	The `id` of the model to be used for this request.
public	t_geospatial_trans_request (structured type)	The inputs and outputs required to create a transformation for the given model.
public	t_geospatial_trans_req_fields (structured type)	No documentation available.
public	t_geospatial_trans_resource (structured type)	The geospatial transformation resource.
public	t_geospatial_trans_resources (structured type)	A paginated list of resources.
public	t_geospatial_trans_resp_entity (structured type)	The transformation results.
public	t_geospatial_trans_resp_fields (structured type)	The transformation results.
public	t_geospatial_trans_results (structured type)	The transformation results.
public	t_get_prompt_input_response (structured type)	No documentation available.
public	t_gpu (structured type)	The name and number of GPUs used for the Fine Tuning job.
public	t_granite_guardian_properties (structured type)	The properties specific to Granite Guardian. This detector is in beta and may change.
public	t_gsptl_trans_metadata_fld (structured type)	The specific fields for the geospatial transformation metadata fields.
public	t_gsptl_trans_resrc_entity (structured type)	The inputs and outputs required to create a transformation for the given model.
public	t_hap_properties (structured type)	The properties specific to HAP.
public	t_hardware_request (structured type)	The requested hardware for deployment.
public	t_hardware_spec (structured type)	A hardware specification.
public	t_inference (structured type)	The details of an inference API.
public	t_input_token_count type INTEGER	The number of input tokens that were consumed.
public	t_in_memory_settings (structured type)	No documentation available.
public	t_jsoncontent_definition type MAP	The schema for a given content type. Each property defines the content type and the sub-object is the JSON schema that describes the content.
public	t_jsoncontent_schema type JSONOBJECT	A JSON schema, see the [JSON Schema reference](https://json-schema.org/learn/getting-started-step-by-step) for documentation about the format.
public	t_json_patch TYPE STANDARD TABLE OF T_JSON_PATCH_OPERATION WITH NON-UNIQUE DEFAULT KEY	Array of patch operations as defined in RFC 6902.
public	t_json_patch_operation (structured type)	This model represents an individual patch operation to be performed on a JSON document, as defined by RFC 6902.
public	t_life_cycle_state (structured type)	The lifecycle details.
public	t_mask_properties (structured type)	The properties specific to masking. If this object exists, even if it is empty, then masking will be applied.
public	t_mdrtn_granite_guardian_prop (structured type)	The properties specific to Granite Guardian. This detector is in beta and may change.
public	t_mdrtn_prop_without_threshold (structured type)	The properties for the moderation. Each type of moderation may have additional properties that are specific to that moderation.
public	t_message (structured type)	Optional messages related to the resource.
public	t_metrics_context (structured type)	Provides extra information for this training stage in the context of auto-ml.
public	t_model_asset_ref (structured type)	The field that identifies the asset.
public	t_model_limits (structured type)	The limits that are applied for the model, for all the plans.
public	t_model_rel (structured type)	A reference to a resource.
public	t_model_version type STRING	The model version (using semantic versioning) if set.
public	t_moderations (structured type)	Properties that control the moderations, for usages such as `Hate and profanity` (HAP) and `Personal identifiable information` (PII) filtering. This list can be extended with new types of moderations.
public	t_moderation_hap_input_prop (structured type)	The properties specific to HAP.
public	t_moderation_hap_properties (structured type)	The properties specific to HAP.
public	t_moderation_input_properties (structured type)	The properties for the moderation. Each type of moderation may have additional properties that are specific to that moderation.
public	t_moderation_pii_input_prop (structured type)	The properties specific to PII.
public	t_moderation_pii_properties (structured type)	The properties specific to PII.
public	t_moderation_properties (structured type)	The properties for the moderation. Each type of moderation may have additional properties that are specific to that moderation.
public	t_moderation_result (structured type)	A specific moderation result.
public	t_moderation_results (structured type)	The result of any detected moderations.
public	t_moderation_text_range (structured type)	A range of text.
public	t_notebook (structured type)	Notebook information as returned by a GET request.
public	t_notebooks_resource_list (structured type)	A list of notebook info as returned by a list query.
public	t_notebook_copy_body (structured type)	Payload for copying a notebook.
public	t_notebook_create_body_general (structured type)	Payload for creating a notebook.
public	t_notebook_create_response type JSONOBJECT	No documentation available.
public	t_notebook_cre_body_in_project (structured type)	Payload for creating a notebook in a project.
public	t_notebook_entity (structured type)	Entity of a notebook.
public	t_notebook_entity_definition (structured type)	Definition part of a notebook entity.
public	t_notebook_entity_def_for_copy (structured type)	Definition part of a notebook entity copied from a source.
public	t_notebook_entity_for_copy (structured type)	Entity of a notebook copied from a source.
public	t_notebook_for_copy (structured type)	Information of a copied notebook as returned by a GET request.
public	t_notebook_in_project (structured type)	Notebook information in a project as returned by a GET request.
public	t_notebook_kernel (structured type)	A notebook kernel.
public	t_notebook_list_body (structured type)	Payload for a notebook list request.
public	t_notebook_metadata (structured type)	Metadata of a notebook.
public	t_notebook_metadata_in_project (structured type)	Metadata of a notebook in a project.
public	t_notebook_origin (structured type)	The notebook origin.
public	t_notebook_origin_from_source (structured type)	The origin of a notebook from a source.
public	t_notebook_resource (structured type)	Notebook info returned in a listing.
public	t_notebook_resource_entity (structured type)	Entity of notebook info returned in a listing.
public	t_notebook_resource_metadata (structured type)	Metadata of notebook info returned in a listing.
public	t_notebook_resrc_entity_asset (structured type)	Asset API asset description returned with a notebook listing.
public	t_notebook_resrc_entity_rt (structured type)	Runtime info returned with a notebook listing.
public	t_notebook_revert_body (structured type)	Payload for a request to revert to a specific notebook version.
public	t_notebook_revert_response type JSONOBJECT	No documentation available.
public	t_notebook_runtime (structured type)	A notebook runtime.
public	t_notebook_update_body (structured type)	Payload for a notebook update request.
public	t_notebook_versions_lst_resp type JSONOBJECT	No documentation available.
public	t_notebook_version_entity (structured type)	A notebook version entity.
public	t_notebook_version_in_project (structured type)	A notebook version in a project.
public	t_notebook_version_metadata (structured type)	Notebook version metadata.
public	t_notebook_ver_create_response type JSONOBJECT	No documentation available.
public	t_notebook_ver_retrieve_resp type JSONOBJECT	No documentation available.
public	t_ntbk_cre_resp_ntbk_for_copy (structured type)	Information of a copied notebook as returned by a GET request.
public	t_ntbk_cre_resp_ntbk_in_prjct (structured type)	Notebook information in a project as returned by a GET request.
public	t_ntbk_rvrt_resp_ntbk_in_prjct (structured type)	Notebook information in a project as returned by a GET request.
public	t_ntbk_versions_lst_in_project (structured type)	A list of notebook versions in a project.
public	t_ntbk_ver_cre_resp_ntbk_ver_1 (structured type)	A notebook version in a project.
public	t_ntbk_ver_entity_in_project (structured type)	A notebook version entity in a project.
public	t_ntbk_ver_rtrv_resp_ntbk_ver1 (structured type)	A notebook version in a project.
public	t_ntbk_vrsns_lst_resp_ntbk_vr1 (structured type)	A list of notebook versions in a project.
public	t_object_location (structured type)	A reference to data.
public	t_object_location_github (structured type)	A reference to data.
public	t_object_loc_github_location (structured type)	Contains a set of fields that describe the location of the data with respect to the `connection`.
public	t_online_deployment (structured type)	Indicates that this is an online deployment. An object has to be specified but can be empty. The `serving_name` can be provided in the `online.parameters`.
public	t_online_deployment_parameters (structured type)	A set of key-value pairs that are used to configure the deployment.
public	t_pagination (structured type)	Information for paging when querying resources.
public	t_pagination_base (structured type)	No documentation available.
public	t_pagination_first (structured type)	The reference to the first item in the current page.
public	t_pagination_next (structured type)	A reference to the first item of the next page, if any.
public	t_pagination_tc (structured type)	Information for paging when querying resources.
public	t_pii_properties (structured type)	The properties specific to PII.
public	t_prmpt_tuning_metrics_context (structured type)	This field will not returned by fine tuning jobs created with InstructLab. The context for prompt tuning metrics.
public	t_prm_trnct_inpt_tkns_frm_strt type INTEGER	Represents the maximum number of input tokens accepted. This can be used to avoid requests failing due to input being longer than configured limits. If the text is truncated, then it truncates the start of the input (on the left), so the end of the input will remain the same. If this value exceeds the `maximum sequence length` (refer to the documentation to find this value for the model) then the call will fail if the total number of tokens exceeds the `maximum sequence length`.
public	t_prm_trnct_inpt_tkns_from_end type INTEGER	Represents the maximum number of tokens accepted per input. This can be used to avoid requests failing due to input being longer than configured limits. If the text is truncated, then it truncates the end of the input (on the right), so the start of the input will remain the same. If this value exceeds the `maximum sequence length` (refer to the documentation to find this value for the model) then the call will fail if the total number of tokens exceeds the `maximum sequence length`.
public	t_project_id type STRING	The project that contains the resource. Either `space_id` or `project_id` has to be given.
public	t_project_id_only type STRING	The project that contains the resource.
public	t_prompt (structured type)	No documentation available.
public	t_prompt_data (structured type)	No documentation available.
public	t_prompt_lock (structured type)	No documentation available.
public	t_prompt_model_parameters (structured type)	No documentation available.
public	t_prompt_template_variables (structured type)	The template properties if this request refers to a prompt template.
public	t_prompt_tuning (structured type)	Properties to control the prompt tuning.
public	t_prompt_variable type JSONOBJECT	No documentation available.
public	t_prompt_variables type MAP	The prompt variables.
public	t_prompt_variable_string type STRING	No documentation available.
public	t_prompt_with_external (structured type)	No documentation available.
public	t_prompt_with_ext_model_param (structured type)	No documentation available.
public	t_rel (structured type)	A reference to a resource.
public	t_reranked_results (structured type)	The ranking score for the input.
public	t_rerank_input (structured type)	The input text.
public	t_rerank_input_result (structured type)	The input text, this is only output if `parameters.return_options.inputs` is set to `true` in the request.
public	t_rerank_parameters (structured type)	The properties used for reranking.
public	t_rerank_query type STRING	The rank query.
public	t_rerank_request (structured type)	The request to rerank texts.
public	t_rerank_response (structured type)	System details.
public	t_rerank_response_fields (structured type)	The ranked results.
public	t_rerank_return_options (structured type)	The return options for text reranking.
public	t_resource_commit_info (structured type)	Information related to the revision.
public	t_resource_description type STRING	The description of the job.
public	t_resource_meta (structured type)	Common metadata for a resource where `project_id` or `space_id` must be present.
public	t_resource_meta_base (structured type)	Common metadata for a resource.
public	t_resource_meta_simple (structured type)	Common metadata for a simple resource.
public	t_resource_name type STRING	The name of the job.
public	t_resource_request_fields (structured type)	The request fields that are not part of the returned entity.
public	t_resrc_space_project_metadata (structured type)	Common metadata for a resource where `project_id` or `space_id` must be present.
public	t_results_location (structured type)	A reference to data.
public	t_results_reference_input (structured type)	No documentation available.
public	t_results_reference_output (structured type)	No documentation available.
public	t_return_option_properties (structured type)	Properties that control what is returned.
public	t_rev_entity_spc_project_req (structured type)	The details for the revision.
public	t_sdgnstrctrd_gen_base_entity (structured type)	Common platform parameters for creating an unstructured synthetic data generation job.
public	t_sdgobject_location (structured type)	A reference to data.
public	t_sdgobject_location_location (structured type)	The location of the data.
public	t_sdgunstructured_gen_entity (structured type)	The details needed to create unstructured synthetic data generation job. The `seed_data_reference.type` must be `container` and the `results_reference.type` must also be `container`.
public	t_sdgunstructured_gen_param (structured type)	The parameters to guide the generation.
public	t_sdgunstructured_gen_request (structured type)	The details needed to create unstructured synthetic data generation job. The `seed_data_reference.type` must be `container` and the `results_reference.type` must also be `container`.
public	t_sdgunstructured_gen_resource (structured type)	The response from getting a specified synthetic data generation job.
public	t_sdgunstructured_gen_response (structured type)	The synthetic data generation job properties.
public	t_sdgunstructured_gen_resp_job (structured type)	No documentation available.
public	t_service_error (structured type)	A service error message.
public	t_similarity_response (structured type)	System details.
public	t_similarity_response_fields (structured type)	The similarity scores per source string.
public	t_similarity_result (structured type)	The similarity results.
public	t_simple_rel (structured type)	A reference to a resource.
public	t_software_spec_rel (structured type)	A software specification.
public	t_space_id type STRING	The space that contains the resource. Either `space_id` or `project_id` has to be given.
public	t_space_id_only type STRING	The space that contains the resource.
public	t_stats (structured type)	The stats about deployments for a space.
public	t_synthetic_data_gen_context (structured type)	The Synthetic Data Generation context.
public	t_synthetic_data_gen_locations (structured type)	The Synthetic Data Generation location metrics.
public	t_synthetic_data_gen_metric (structured type)	The Synthetic Data Generation metrics.
public	t_synthetic_data_gen_metrics (structured type)	All the Synthetic Data Generation metrics.
public	t_synthetic_data_gen_request (structured type)	The details needed to create synthetic data generation job. The `data_reference.type` must be `taxonomy_asset` and the `results_reference.type` will normally be something like `connection_asset` or `data_asset`.
public	t_synthetic_data_gen_resource (structured type)	The response from getting a specified synthetic data generation job.
public	t_synthetic_data_gen_resources (structured type)	The response of getting all synthetic data generation jobs.
public	t_synthetic_data_gen_response (structured type)	The synthetic data generation job properties.
public	t_synthetic_data_gen_sample (structured type)	The Synthetic Data Generation sample metrics.
public	t_synthetic_data_gen_status (structured type)	The status of a Synthetic Data Generation job.
public	t_system (structured type)	System details.
public	t_system_details (structured type)	Optional details coming from the service and related to the API call or the associated resource.
public	t_tags type TT_STRING	A list of tags for this resource.
public	t_task_description (structured type)	The attributes of the task for this model.
public	t_task_rating (structured type)	The ratings for this task for this model.
public	t_taxonomy_request (structured type)	The request fields to create Taxonomy job. The `data_reference.type` must be set to `github`.
public	t_taxonomy_resource (structured type)	The response fields from a Taxonomy request.
public	t_taxonomy_resources (structured type)	The list of Taxonomy jobs in specified project or space.
public	t_taxonomy_response (structured type)	The Taxonomy entity. The `data_reference.type` will be `github` and the `results_reference.type` will be set to `taxonomy_asset`.
public	t_taxonomy_status (structured type)	The status of a Taxonomy job.
public	t_text_chat_finish_reason type STRING	The reason why the call stopped, can be one of: - `stop` - The model hit a natural stop point or a provided stop sequence. - `length` - The maximum number of tokens specified in the request was reached. - `tool_calls` - The model called a tool. - `time_limit`` - Time limit reached. - `cancelled`` - Request canceled by the client. - `error`` - Error encountered. - `null` - API response still in progress or incomplete.
public	t_text_chat_function_call (structured type)	The function call.
public	t_text_chat_message (structured type)	The base definition of a text chat message.
public	t_text_chat_messages type JSONOBJECT	No documentation available.
public	t_text_chat_message_assistant (structured type)	The definition of an assistant message.
public	t_text_chat_message_control (structured type)	The definition of a control message.
public	t_text_chat_message_field_name type STRING	An optional name for the participant. Provides the model information to differentiate between participants of the same role.
public	t_text_chat_message_system (structured type)	The definition of a system message.
public	t_text_chat_message_tool (structured type)	The definition of a tool message.
public	t_text_chat_message_user (structured type)	The definition of a user message.
public	t_text_chat_parameters (structured type)	The parameters specific to chat.
public	t_text_chat_parameter_function (structured type)	The parameters specific to chat.
public	t_text_chat_parameter_tools (structured type)	The chat tool parameters.
public	t_text_chat_property_tool type STRING	The tool type.
public	t_text_chat_request (structured type)	The parameters specific to chat.
public	t_text_chat_response (structured type)	System details.
public	t_text_chat_response_fields (structured type)	A chat completion choices.
public	t_text_chat_response_format (structured type)	The chat response format parameters.
public	t_text_chat_resp_fields_shared (structured type)	A chat completion.
public	t_text_chat_resp_fields_stream (structured type)	A chat completion choices.
public	t_text_chat_result_choice (structured type)	A tool related result.
public	t_text_chat_result_delta (structured type)	A message result.
public	t_text_chat_result_message (structured type)	A message result.
public	t_text_chat_res_choice_stream (structured type)	A tool related result.
public	t_text_chat_stream_item (structured type)	System details.
public	t_text_chat_stream_response TYPE STANDARD TABLE OF T_TEXT_CHAT_STREAM_ITEM WITH NON-UNIQUE DEFAULT KEY	A set of server sent events, each event contains a response for one or more tokens. The results will be an array of events of the form `data: {<json event>}` where the schema of the individual `json event` is described below.
public	t_text_chat_tool_call (structured type)	The tool call.
public	t_text_chat_tool_call_stream (structured type)	The tool call.
public	t_text_chat_tool_choice_option type STRING	Using `auto` means the model can pick between generating a message or calling one or more tools. Specify either `tool_choice_option` to allow the model to pick or `tool_choice` to force the model to call a tool.
public	t_text_chat_tool_choice_tool (structured type)	Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. Specify either `tool_choice_option` to allow the model to pick or `tool_choice` to force the model to call a tool.
public	t_text_chat_tool_function (structured type)	The named function.
public	t_text_chat_usage (structured type)	Usage statistics for the completion request.
public	t_text_chat_user_content (structured type)	The base definition of a text chat user content.
public	t_text_chat_user_contents type JSONOBJECT	No documentation available.
public	t_text_chat_user_image_url (structured type)	The definition of a user image content.
public	t_text_chat_user_text_content (structured type)	The definition of a user text content.
public	t_text_chat_user_video_url (structured type)	The definition of a user video content.
public	t_text_chat_usr_img_urlcontent (structured type)	The definition of a user image content.
public	t_text_detection_content_item (structured type)	The text that was detected.
public	t_text_detection_context_item (structured type)	Detection evidence.
public	t_text_detection_evidence_ref (structured type)	Detection evidence.
public	t_text_detection_score type FLOAT	The threshold probability that this is a real match.
public	t_text_extraction_data_ref (structured type)	A reference to data.
public	t_text_extraction_entity (structured type)	The document details for the text extraction.
public	t_text_extraction_metadata (structured type)	Common metadata for a resource where `project_id` or `space_id` must be present.
public	t_text_extraction_request (structured type)	The properties that are part of a request that supports spaces and projects. Either `space_id` or `project_id` has to be provided and is mandatory.
public	t_text_extraction_resource (structured type)	The text extraction resource.
public	t_text_extraction_resources (structured type)	A paginated list of resources.
public	t_text_extraction_response (structured type)	The text extraction response.
public	t_text_extraction_resrc_entity (structured type)	The document details for the text extraction.
public	t_text_extraction_results (structured type)	The current status of the text extraction.
public	t_text_extraction_steps (structured type)	The steps for the text extraction pipeline. Use `parameters` instead.
public	t_text_extraction_step_ocr (structured type)	The OCR text extraction step.
public	t_text_gen_common (structured type)	A prompt to be used to infer the next tokens. Each request expects a `project_id` or a `space_id`, and the `project` or `space` must have an associated WML instance that will be used for limits and billing (if a paid plan).
public	t_text_gen_length_penalty (structured type)	It can be used to exponentially increase the likelihood of the text generation terminating once a specified number of tokens have been generated.
public	t_text_gen_parameters (structured type)	Properties that control the model and response.
public	t_text_gen_parameters2 (structured type)	Properties that control the model and response that are only supported in caikit.
public	t_text_gen_request (structured type)	A prompt to be used to infer the next tokens. Each request expects a `project_id` or a `space_id`, and the `project` or `space` must have an associated WML instance that will be used for limits and billing (if a paid plan).
public	t_text_gen_response (structured type)	System details.
public	t_text_gen_response_fields (structured type)	The tokens that are inferred from the prompt. Note that the events are different between a request with moderation and a request without moderations. A request with moderation will have events that are on a sentence level and a request without moderations will have events that are on a token level.
public	t_text_gen_resp_fld_res_item (structured type)	No documentation available.
public	t_text_gen_result (structured type)	No documentation available.
public	t_text_gen_result_fields (structured type)	No documentation available.
public	t_text_gen_stop_reason type STRING	The reason why the call stopped, can be one of: - not_finished - Possibly more tokens to be streamed. - max_tokens - Maximum requested tokens reached. - eos_token - End of sequence token encountered. - cancelled - Request canceled by the client. - time_limit - Time limit reached. - stop_sequence - Stop sequence encountered. - token_limit - Token limit reached. - error - Error encountered. Note that these values will be lower-cased so test for values case insensitive.
public	t_text_gen_stream_response TYPE STANDARD TABLE OF T_TEXT_GEN_RESPONSE WITH NON-UNIQUE DEFAULT KEY	A set of server sent events, each event contains a response for one or more tokens. The results will be an array of events of the form `data: {<json event>}` where the schema of the individual `json event` is described below.
public	t_text_gen_token_info (structured type)	The generated token.
public	t_text_gen_top_token_info (structured type)	The top tokens.
public	t_text_input type STRING	The text input to the model.
public	t_text_moderation (structured type)	Properties that control the moderation on the text.
public	t_text_tokenize_parameters (structured type)	The parameters for text tokenization.
public	t_text_tokenize_request (structured type)	The input string to tokenize along with the associated model id and any parameters. One of `space_id` or `project_id` must be provided.
public	t_text_tokenize_response (structured type)	The tokenization result.
public	t_text_tokenize_result (structured type)	The result of tokenizing the input string.
public	t_tooling type JSONOBJECT	User defined properties specified as key-value pairs, which is propagated to the deployment.
public	t_tool_config type JSONOBJECT	Optional configuration options that can be passed for some tools. This must match the config schema for that tool.
public	t_training_accumulated_steps (structured type)	Number of steps to be used for gradient accumulation. Gradient accumulation refers to a method of collecting gradient for configured number of steps instead of updating the model variables at every step and then applying the update to model variables. This can be used as a tool to overcome smaller batch size limitation. Often also referred in conjunction with "effective batch size".
public	t_training_batch_size (structured type)	The batch size is a number of samples processed before the model is updated.
public	t_training_init_method (structured type)	Initialization methods for a training.
public	t_training_init_text (structured type)	Initialization text to be used if init_method is set to `text`, otherwise this will be ignored.
public	t_training_learning_rate (structured type)	Learning rate to be used for training.
public	t_training_max_input_tokens (structured type)	Maximum length of input tokens being considered.
public	t_training_max_output_tokens (structured type)	Maximum length of output tokens being predicted.
public	t_training_metric (structured type)	A metric.
public	t_training_metrics TYPE STANDARD TABLE OF T_TRAINING_METRIC WITH NON-UNIQUE DEFAULT KEY	Metrics that can be returned by an operation.
public	t_training_mlmetrics type MAP	The metrics.
public	t_training_num_epochs (structured type)	The number of epochs is the number of complete passes through the training dataset. The quality depends on the number of epochs.
public	t_training_num_virtual_tokens (structured type)	Number of virtual tokens to be used for training. In prompt tuning we are essentially learning the embedded representations for soft prompts, which are known as virtual tokens, via back propagation for a specific task(s) while keeping the rest of the model fixed. `num_virtual_tokens` is the number of dimensions for these virtual tokens.
public	t_training_parameters (structured type)	Training parameters for a given model.
public	t_training_resource (structured type)	Training resource.
public	t_training_resource_collection (structured type)	Information for paging when querying resources.
public	t_training_resource_details (structured type)	The training details required when creating the job.
public	t_training_resource_entity (structured type)	Status of the training job.
public	t_training_resource_prototype (structured type)	The `training_data_references` contain the training datasets and the `results_reference` the connection where results will be stored.
public	t_training_status (structured type)	Status of the training job.
public	t_training_status_output (structured type)	Status of the training job.
public	t_training_torch_dtype (structured type)	Datatype to use for training of the underlying text generation model. If no value is provided, we pull from torch_dtype in config. If an in memory resource is provided which does not match the specified data type, the model underpinning the resource will be converted in place to the correct torch dtype.
public	t_training_verbalizer (structured type)	Verbalizer template to be used for formatting data at train and inference time. This template may use brackets to indicate where fields from the data model TrainGenerationRecord must be rendered.
public	t_train_resource_entity_common (structured type)	No documentation available.
public	t_train_resrc_collection_sys (structured type)	Optional details coming from the service and related to the API call or the associated resource.
public	t_train_resrc_model_id_output (structured type)	No documentation available.
public	t_tsforecast_input_schema (structured type)	Contains metadata about your timeseries data input.
public	t_tsforecast_parameters (structured type)	The parameters for the forecast request.
public	t_tsforecast_request (structured type)	Input necessary for performing inference. These inputs identify things like which model to use, the data payload you are passing to the model, and other parameters which affect the behavior of the inference operation.
public	t_tsforecast_resource (structured type)	Input necessary for performing inference. These inputs identify things like which model to use, the data payload you are passing to the model, and other parameters which affect the behavior of the inference operation.
public	t_tsforecast_response (structured type)	The time series forecast response.
public	t_tsforecast_results type JSONOBJECT	Prediction results.
public	t_txt_cht_msg_txt_chat_msg_sys (structured type)	The definition of a system message.
public	t_txt_cht_msg_txt_chat_msg_usr (structured type)	The definition of a user message.
public	t_txt_cht_msg_txt_cht_msg_ass1 (structured type)	The definition of an assistant message.
public	t_txt_cht_msg_txt_cht_msg_cnt1 (structured type)	The definition of a control message.
public	t_txt_cht_msg_txt_cht_msg_tool (structured type)	The definition of a tool message.
public	t_txt_cht_usr_cntnts_txt_cht_1 (structured type)	The definition of a user text content.
public	t_txt_cht_usr_cntnts_txt_cht_2 (structured type)	The definition of a user image content.
public	t_txt_cht_usr_cntnts_txt_cht_3 (structured type)	The definition of a user video content.
public	t_txt_cht_usr_video_urlcontent (structured type)	The definition of a user video content.
public	t_txt_detection_child_evidence (structured type)	Child evidence.
public	t_txt_detection_detection_item (structured type)	Detection details.
public	t_txt_dtctn_context_position (structured type)	The text that was detected.
public	t_txt_dtctn_evidence_object (structured type)	The details for a given evidence.
public	t_txt_extraction_languages_lst type TT_STRING	Set of languages to be expected in the document. The language codes follow `ISO 639`. See the documentation for the currently supported languages.
public	t_txt_extraction_step_tab_proc (structured type)	The tables processing text extraction step.
public	t_txt_mdrtn_without_threshold (structured type)	Properties that control the moderation on the text.
public	t_utility_agent_tool (structured type)	No documentation available.
public	t_util_agnt_tl_strctrd_input (structured type)	No documentation available.
public	t_util_agnt_tl_unstrctrd_input (structured type)	No documentation available.
public	t_warning (structured type)	A warning message.
public	t_wx_prmpt_sssn_entry_lst_res1 (structured type)	No documentation available.
public	t_wx_prompt_input_request (structured type)	No documentation available.
public	t_wx_prompt_patch (structured type)	No documentation available.
public	t_wx_prompt_patch_model_ver (structured type)	No documentation available.
public	t_wx_prompt_post (structured type)	No documentation available.
public	t_wx_prompt_post_model_version (structured type)	No documentation available.
public	t_wx_prompt_response (structured type)	No documentation available.
public	t_wx_prompt_resp_model_version (structured type)	No documentation available.
public	t_wx_prompt_session (structured type)	No documentation available.
public	t_wx_prompt_session_entry (structured type)	No documentation available.
public	t_wx_prompt_session_entry_list (structured type)	No documentation available.
public	t_wx_util_agent_tools_response (structured type)	No documentation available.
public	t_wx_util_agent_tools_run_req type JSONOBJECT	No documentation available.
public	t_wx_util_agent_tools_run_resp (structured type)	No documentation available.
public	t_wx_util_agnt_tls_rn_req_uti1 (structured type)	No documentation available.
public	t_wx_util_agnt_tls_rn_req_uti2 (structured type)	No documentation available.

Constants

Visibility and Level	Name	Documentation
public static	c_abapname_dictionary (structured type)	Map ABAP identifiers to service identifiers.
public static	c_required_fields (structured type)	List of required fields per type.

Methods

Visibility and Level

Name

Documentation

public instance

ai_services_create
importing	i_aiservicerequest	type T_AISERVICE_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCE
raising	zcx_ibmx_service_exception

Create a new AI service

Create a new AI service with the given payload. A AI service is some code that can be deployed as a deployment.

Parameters

i_aiservicerequest	Payload for creating the AI service. Either `space_id` or `project_id` has to be provided and is mandatory.
e_response	Service return value of type T_AISERVICE_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_create_revision
importing	i_id	type STRING
	i_rvsnnttyspcprjctrqst	type T_REV_ENTITY_SPC_PROJECT_REQ
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCE
raising	zcx_ibmx_service_exception

Create a new AI service revision

Create a new AI service revision.
The current metadata and content for
`id` will be taken and a new revision created.
Either `space_id` or `project_id` has to be provided and is mandatory.

Parameters

i_id	AI service identifier.
i_rvsnnttyspcprjctrqst	No documentation available.
e_response	Service return value of type T_AISERVICE_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_delete
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
raising	zcx_ibmx_service_exception

Delete the AI service

Delete the AI service with the specified identifier. This will delete all revisions of this flow as well. For each revision all attachments will also be deleted.

Parameters

i_id	AI service identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_download_code
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_rev	type STRING optional
	i_accept	type STRING default 'application/zip'
exporting	e_response	type FILE
raising	zcx_ibmx_service_exception

Download the AI service code

Download the AI service code.
It is possible to download the `code` for a given revision of the `flow`.
AI services expect a zip file that contains the code files that make up the flow.

Parameters

i_id	AI service identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_rev	The revision number of the resource.
e_response	Service return value of type FILE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_get
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_rev	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCE
raising	zcx_ibmx_service_exception

Retrieve the AI service

Retrieve the AI service with the specified identifier. If `rev` query parameter is provided,
`rev=latest` will fetch the latest revision. A call with `rev={revision_number}` will fetch the given revision_number record. Either `space_id` or `project_id` has to be provided and is mandatory.

Parameters

i_id	AI service identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_rev	The revision number of the resource.
e_response	Service return value of type T_AISERVICE_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_list
importing	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_tag_value	type STRING optional
	i_search	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCES
raising	zcx_ibmx_service_exception

Retrieve the AI services

Retrieve the AI services for the specified space or project.

Parameters

i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
i_tag_value	Return only the resources with the given tag values, separated by `or` or `and` to support multiple tags.
i_search	Returns only resources that match this search string. The path to the field must be the complete path to the field, and this field must be one of the indexed fields for this resource type. Note that the search string must be URL encoded.
e_response	Service return value of type T_AISERVICE_RESOURCES

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_list_revisions
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCES
raising	zcx_ibmx_service_exception

Retrieve the AI service revisions

Retrieve the AI service revisions.

Parameters

i_id	AI service identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
e_response	Service return value of type T_AISERVICE_RESOURCES

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_update
importing	i_id	type STRING
	i_json_patch	type TT_JSON_PATCH_OPERATION
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_RESOURCE
raising	zcx_ibmx_service_exception

Update the AI service

Update the AI service with the provided patch data.
The following fields can be patched:
- `/tags`
- `/name`
- `/description`
- `/custom`

Parameters

i_id	AI service identifier.
i_json_patch	Input For Patch. This is the patch body which corresponds to the JavaScript Object Notation (JSON) Patch standard (RFC 6902).
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_AISERVICE_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

ai_services_upload_code
importing	i_id	type STRING
	i_upload_code	type FILE
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_contenttype	type STRING default 'application/gzip'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AISERVICE_CONTENT_METADATA
raising	zcx_ibmx_service_exception

Upload the AI service code

Upload the flow code. AI services expect a zip file that contains the code files that make up the flow.

Parameters

i_id	AI service identifier.
i_upload_code	A gzip file containing code files.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_AISERVICE_CONTENT_METADATA

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

create_autoai_rags
importing	i_autoairagrequest	type T_AUTO_AIRAGREQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AUTO_AIRAGRESPONSE
raising	zcx_ibmx_service_exception

Create a new AutoAI RAG run

Create a new AutoAI RAG that will find the best RAG pattern from the data that is provided in the request.

Parameters

i_autoairagrequest	The details of the AutoAI RAG run with the data used to find the best RAG patterns.
e_response	Service return value of type T_AUTO_AIRAGRESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

create_deployment
importing	i_deploymentresourceprototype	type T_DEPLOYMENT_RESRC_PROTOTYPE
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_DEPLOYMENT_RESOURCE
raising	zcx_ibmx_service_exception

Create a new watsonx.ai deployment

Create a new deployment, currently the only supported type is `online`.

If this is a deployment for a prompt tune then the `asset` object must exist
and the `id` must be the `id` of the `model` that was created after the
prompt training.

If this is a deployment for a prompt template then the `prompt_template`
object should
exist and the `id` must be the `id` of the prompt template to be deployed.

Parameters

i_deploymentresourceprototype

The deployment request entity.

The following important fields are described for each use case: 1. Prompt template:
- `base_model_id`: **required**
- `promt_template.id`: **required**
- `online`: **required**
- `hardware_spec`: **forbidden**
- `hardware_request`: **forbidden**
- response `deployed_asset_type`: `foundation_model` 1. Prompt tune:
- `asset.id`: **required**
- `online`: **required**
- `hardware_spec`: **forbidden**
- `hardware_request`: **forbidden**
- `base_model_id`: **forbidden**
- response `deployed_asset_type`: `prompt_tune` 1. Custom foundation model:
- `asset.id`: **required**
- `online`: **required**
- `online.parameters.foundation_model`: **optional**
- `hardware_spec`: **forbidden**
- `hardware_request`: **required**
- `base_model_id`: **forbidden**
- `base_deployment_id`: **forbidden**
- response `deployed_asset_type`: `custom_foundation_model` 1. Deploy on Demand model:
- `asset.id`: **required**
- `online`: **required**
- `online.parameters.foundation_model`: **forbidden**
- `hardware_spec`: **forbidden**
- `hardware_request`: **forbidden**
- `base_model_id`: **forbidden**
- `base_deployment_id`: **forbidden**
- `space_id`: **required**
- `project_id`: **forbidden**
- response `deployed_asset_type`: `curated_foundation_model`.

e_response

Service return value of type T_DEPLOYMENT_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

delete_autoai_rags
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_hard_delete	type BOOLEAN optional
raising	zcx_ibmx_service_exception

Cancel or delete an AutoAI RAG run

Cancel or delete the specified AutoAI RAG run, once deleted all trace of the run job is gone.

Parameters

i_id	The `id` is the identifier that was returned in the `metadata.id` field of the request.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_hard_delete	Set to true in order to also delete the job or request metadata.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

delete_prompt
importing	i_project_id	type STRING
	i_prompt_id	type STRING
	i_space_id	type STRING optional
raising	zcx_ibmx_service_exception

Delete a prompt

This deletes a prompt / prompt template with the given id.

Parameters

i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_prompt_id	Prompt ID.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_delete
importing	i_deployment_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
raising	zcx_ibmx_service_exception

Delete the deployment

Delete the deployment with the specified identifier.

Parameters

i_deployment_id	The deployment id.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_get
importing	i_deployment_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_DEPLOYMENT_RESOURCE
raising	zcx_ibmx_service_exception

Retrieve the deployment details

Retrieve the deployment details with the specified identifier.

Parameters

i_deployment_id	The deployment id.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_DEPLOYMENT_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_text_chat
importing	i_id_or_name	type STRING
	i_body	type T_DEPLOYMENT_TEXT_CHAT
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_CHAT_RESPONSE
raising	zcx_ibmx_service_exception

Infer text chat

Infer the next chat message for a given deployment. The deployment must reference a prompt template which has `input_mode` set to `chat`. The model to the chat request will be from the deployment `base_model_id`. Parameters to the chat request will be from the prompt template `model_parameters`. Related guides: [Deployment](https://cloud.ibm.com/apidocs/watsonx-ai#create-deployment), [Prompt template](https://cloud.ibm.com/apidocs/watsonx-ai#post-prompt), [Text chat](https://cloud.ibm.com/apidocs/watsonx-ai#text-chat).

If a `serving_name` is used then it must match the `serving_name` that is returned in the `inference` section when the deployment was created.

Parameters

i_id_or_name	The `id_or_name` can be either the `deployment_id` that identifies the deployment or a `serving_name` that allows a predefined URL to be used to post a prediction. The deployment must reference a prompt template with `input_mode` `chat`. The WML instance that is associated with the deployment will be used for limits and billing (if a paid plan).
i_body	From a given prompt, infer the next chat message.
e_response	Service return value of type T_TEXT_CHAT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_text_chat_stream
importing	i_id_or_name	type STRING
	i_body	type T_DEPLOYMENT_TEXT_CHAT
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'text/event-stream'
exporting	e_response	type T_ARRAY
raising	zcx_ibmx_service_exception

Infer text chat event stream

Infer the next chat message for a given deployment. This operation will return the output tokens as a stream of events. The deployment must reference a prompt template which has `input_mode` set to `chat`. The model to the chat request will be from the deployment `base_model_id`. Parameters to the chat request will be from the prompt template `model_parameters`. Related guides: [Deployment](https://cloud.ibm.com/apidocs/watsonx-ai#create-deployment), [Prompt template](https://cloud.ibm.com/apidocs/watsonx-ai#post-prompt), [Text chat](https://cloud.ibm.com/apidocs/watsonx-ai#text-chat).

If a `serving_name` is used then it must match the `serving_name` that is returned in the `inference` section when the deployment was created.

Parameters

i_id_or_name	The `id_or_name` can be either the `deployment_id` that identifies the deployment or a `serving_name` that allows a predefined URL to be used to post a prediction. The deployment must reference a prompt template with `input_mode` `chat`. The WML instance that is associated with the deployment will be used for limits and billing (if a paid plan).
i_body	From a given prompt, infer the next chat message in a server-sent events (SSE) stream.
e_response	Service return value of type T_Array

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_text_generation
importing	i_id_or_name	type STRING
	i_body	type T_DEPLOYMENT_TEXT_GEN
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_GEN_RESPONSE
raising	zcx_ibmx_service_exception

Infer text

Infer the next tokens for a given deployed model with a set of parameters.
If a `serving_name` is used then it must match the `serving_name` that is returned in the `inference` section when the deployment was created.

### Return options

Note that there is currently a limitation in this operation when using `return_options`,
for input only `input_text` will be returned if requested,
for output the `input_tokens` and `generated_tokens` will not be returned.

Parameters

i_id_or_name	The `id_or_name` can be either the `deployment_id` that identifies the deployment or a `serving_name` that allows a predefined URL to be used to post a prediction. The WML instance that is associated with the deployment will be used for limits and billing (if a paid plan).
i_body	From a given prompt, infer the next tokens.
e_response	Service return value of type T_TEXT_GEN_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_text_gen_stream
importing	i_id_or_name	type STRING
	i_body	type T_DEPLOYMENT_TEXT_GEN
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'text/event-stream'
exporting	e_response	type T_ARRAY
raising	zcx_ibmx_service_exception

Infer text event stream

Infer the next tokens for a given deployed model with a set of parameters.
This operation will return the output tokens as a stream of events.
If a `serving_name` is used then it must match the `serving_name` that is returned in the `inference` section when the deployment was created.

### Return options

Note that there is currently a limitation in this operation when using `return_options`,
for input only `input_text` will be returned if requested,
for output the `input_tokens` and `generated_tokens` will not be returned, also the
`rank` and `top_tokens` will not be returned.

Parameters

i_id_or_name	The `id_or_name` can be either the `deployment_id` that identifies the deployment or a `serving_name` that allows a predefined URL to be used to post a prediction. The WML instance that is associated with the deployment will be used for limits and billing (if a paid plan).
i_body	From a given prompt, infer the next tokens in a server-sent events (SSE) stream.
e_response	Service return value of type T_Array

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

deployments_update
importing	i_deployment_id	type STRING
	i_json_patch	type TT_JSON_PATCH_OPERATION
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_contenttype	type STRING default 'application/json-patch+json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_DEPLOYMENT_RESOURCE
raising	zcx_ibmx_service_exception

Update the deployment metadata

Update the deployment metadata.
The following parameters of deployment metadata are supported for the patch operation.

- `/name`
- `/description`
- `/tags`
- `/custom`
- `/online/parameters`
- `/asset` - `replace` only
- `/prompt_template` - `replace` only
- `/hardware_spec`
- `/hardware_request`
- `/base_model_id` - `replace` only (applicable only to prompt template deployments referring to IBM base foundation models)

The PATCH operation with path specified as `/online/parameters` can be used to update the `serving_name`.

Parameters

i_deployment_id	The deployment id.
i_json_patch	The json patch.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_DEPLOYMENT_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

get_appname redefinition

public instance

get_autoai_rags
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AUTO_AIRAGRESPONSE
raising	zcx_ibmx_service_exception

Get an AutoAI RAG run

Get the results of an AutoAI RAG run, or details if the job failed.

Parameters

i_id	The `id` is the identifier that was returned in the `metadata.id` field of the request.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_AUTO_AIRAGRESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

get_prompt
importing	i_project_id	type STRING
	i_prompt_id	type STRING
	i_space_id	type STRING optional
	i_restrict_model_parameters	type STRING default 'true'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_WX_PROMPT_RESPONSE
raising	zcx_ibmx_service_exception

Get a prompt

This retrieves a prompt / prompt template with the given id.

Parameters

i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_prompt_id	Prompt ID.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
i_restrict_model_parameters	Only return a set of model parameters compatiable with inferencing.
e_response	Service return value of type T_WX_PROMPT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

get_prompt_input
importing	i_prompt_id	type STRING
	i_project_id	type STRING
	i_wxpromptinputrequest	type T_WX_PROMPT_INPUT_REQUEST optional
	i_space_id	type STRING optional
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_GET_PROMPT_INPUT_RESPONSE
raising	zcx_ibmx_service_exception

Get the inference input string for a given prompt

Computes the inference input string based on state of a prompt. Optionally replaces template params

Parameters

i_prompt_id	Prompt ID.
i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_wxpromptinputrequest	No documentation available.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
e_response	Service return value of type T_GET_PROMPT_INPUT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

get_prompt_lock
importing	i_prompt_id	type STRING
	i_project_id	type STRING
	i_space_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_PROMPT_LOCK
raising	zcx_ibmx_service_exception

Get current prompt lock status

Retrieves the current locked state of a prompt.

Parameters

i_prompt_id	Prompt ID.
i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
e_response	Service return value of type T_PROMPT_LOCK

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

get_request_prop redefinition

public instance

get_sdk_version_date redefinition

public instance

list_autoai_rags
importing	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_AUTO_RAGRESULT_RESOURCES
raising	zcx_ibmx_service_exception

Retrieve the AutoAI RAG runs

Retrieve the list of AutoAI RAG requests for the specified space or project.

This operation does not save the history, any requests that were deleted or purged
will not appear in this list.

Parameters

i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
e_response	Service return value of type T_AUTO_RAGRESULT_RESOURCES

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

list_deployments
importing	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_serving_name	type STRING optional
	i_tag_value	type STRING optional
	i_asset_id	type STRING optional
	i_prompt_template_id	type STRING optional
	i_name	type STRING optional
	i_type	type STRING optional
	i_state	type STRING optional
	i_conflict	type BOOLEAN default C_BOOLEAN_FALSE
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_DEPLOYMENT_RESRC_COLLECTION
raising	zcx_ibmx_service_exception

Retrieve the deployments

Retrieve the list of deployments for the specified space or project.

Parameters

i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_serving_name	Retrieves the deployment, if any, that contains this `serving_name`.
i_tag_value	Retrieves only the resources with the given tag value.
i_asset_id	Retrieves only the resources with the given asset_id, asset_id would be the model id.
i_prompt_template_id	Retrieves only the resources with the given prompt_template_id.
i_name	Retrieves only the resources with the given name.
i_type	Retrieves the resources filtered with the given type. There are the deployment types as well as an additional `prompt_template` if the deployment type includes a prompt template. The supported deployment types are (see the description for `deployed_asset_type` in the deployment entity): 1. `prompt_tune` - when a prompt tuned model is deployed. 2. `foundation_model` - when a prompt template is used on a pre-deployed IBM provided model. 3. `custom_foundation_model` - when a custom foundation model is deployed. These can be combined with the flag `prompt_template` like this: 1. `type=prompt_tune` - return all prompt tuned model deployments. 2. `type=prompt_tune and prompt_template` - return all prompt tuned model deployments with a prompt template. 3. `type=foundation_model` - return all prompt template deployments. 4. `type=foundation_model and prompt_template` - return all prompt template deployments - this is the same as the previous query because a `foundation_model` can only exist with a prompt template. 5. `type=prompt_template` - return all deployments with a prompt template.
i_state	Retrieves the resources filtered by state. Allowed values are `initializing`, `updating`, `ready` and `failed`.
i_conflict	Returns whether `serving_name` is available for use or not. This query parameter cannot be combined with any other parameter except for `serving_name`.
e_response	Service return value of type T_DEPLOYMENT_RESRC_COLLECTION

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

list_foundation_model_specs
importing	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_filters	type STRING optional
	i_tech_preview	type BOOLEAN default C_BOOLEAN_FALSE
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_FOUNDATION_MODELS
raising	zcx_ibmx_service_exception

List the available foundation models

Retrieve the list of deployed foundation models.

Parameters

i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
i_filters	A set of filters to specify the list of models, filters are described as the `pattern` shown below. ```text pattern: tfilter[,tfilter][:(or\|and)] tfilter: filter \| !filter filter: Requires existence of the filter. !filter: Requires absence of the filter. filter: one of modelid_: Filters by model id. Namely, select a model with a specific model id. provider_: Filters by provider. Namely, select all models with a specific provider. source_: Filters by source. Namely, select all models with a specific source. input_tier_: Filters by input tier. Namely, select all models with a specific input tier. output_tier_: Filters by output tier. Namely, select all models with a specific output tier. tier_: Filters by tier. Namely, select all models with a specific input or output tier. task_: Filters by task id. Namely, select all models that support a specific task id. lifecycle_: Filters by lifecycle state. Namely, select all models that are currently in the specified lifecycle state. function_*: Filters by function. Namely, select all models that support a specific function. ```.
i_tech_preview	See all the `Tech Preview` models if entitled.
e_response	Service return value of type T_FOUNDATION_MODELS

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

list_foundation_model_tasks
importing	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_FOUNDATION_MODEL_TASKS
raising	zcx_ibmx_service_exception

List the supported tasks

Retrieve the list of tasks that are supported by the foundation models.

Parameters

i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
e_response	Service return value of type T_FOUNDATION_MODEL_TASKS

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

list_text_extractions
importing	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_EXTRACTION_RESOURCES
raising	zcx_ibmx_service_exception

Retrieve the text extraction requests

Retrieve the list of text extraction requests for the specified space or project.

This operation does not save the history, any requests that were deleted or purged
will not appear in this list.

Parameters

i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
e_response	Service return value of type T_TEXT_EXTRACTION_RESOURCES

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

patch_prompt
importing	i_project_id	type STRING
	i_prompt_id	type STRING
	i_wxpromptpatch	type T_WX_PROMPT_PATCH
	i_space_id	type STRING optional
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_WX_PROMPT_RESPONSE
raising	zcx_ibmx_service_exception

Update a prompt

This updates a prompt / prompt template with the given id.

Parameters

i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_prompt_id	Prompt ID.
i_wxpromptpatch	No documentation available.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
e_response	Service return value of type T_WX_PROMPT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

post_prompt
importing	i_project_id	type STRING
	i_wxpromptpost	type T_WX_PROMPT_POST
	i_space_id	type STRING optional
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_WX_PROMPT_RESPONSE
raising	zcx_ibmx_service_exception

Create a new prompt / prompt template

This creates a new prompt with the provided parameters.

Parameters

i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_wxpromptpost	No documentation available.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
e_response	Service return value of type T_WX_PROMPT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

put_prompt_lock
importing	i_prompt_id	type STRING
	i_project_id	type STRING
	i_promptlock	type T_PROMPT_LOCK
	i_space_id	type STRING optional
	i_force	type BOOLEAN optional
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_PROMPT_LOCK
raising	zcx_ibmx_service_exception

Prompt lock modifications

Modifies the current locked state of a prompt.

Parameters

i_prompt_id	Prompt ID.
i_project_id	[REQUIRED] Specifies the project ID as the target. One target must be supplied per request.
i_promptlock	No documentation available.
i_space_id	[REQUIRED] Specifies the space ID as the target. One target must be supplied per request.
i_force	Override a lock if it is currently taken.
e_response	Service return value of type T_PROMPT_LOCK

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_chat
importing	i_textchatrequest	type T_TEXT_CHAT_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_CHAT_RESPONSE
raising	zcx_ibmx_service_exception

Infer text

Infer the next tokens for a given deployed model with a set of parameters.

Parameters

i_textchatrequest	From a given prompt, infer the next tokens.
e_response	Service return value of type T_TEXT_CHAT_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_chat_stream
importing	i_textchatrequest	type T_TEXT_CHAT_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'text/event-stream'
exporting	e_response	type T_ARRAY
raising	zcx_ibmx_service_exception

Infer text event stream

Infer the next tokens for a given deployed model with a set of parameters.
This operation will return the output tokens as a stream of events.

Parameters

i_textchatrequest	From a given prompt, infer the next tokens in a server-sent events (SSE) stream.
e_response	Service return value of type T_Array

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_embeddings
importing	i_embeddingsrequest	type T_EMBEDDINGS_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_EMBEDDINGS_RESPONSE
raising	zcx_ibmx_service_exception

Generate embeddings

Generate embeddings from text input.

See the [documentation](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-dat a/fm-embed-overview.html?context=wx&audience=wdp)
for a description of text embeddings.

Parameters

i_embeddingsrequest	The text input for a given model to be used to generate the embeddings.
e_response	Service return value of type T_EMBEDDINGS_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_extraction
importing	i_textextractionrequest	type T_TEXT_EXTRACTION_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_EXTRACTION_RESPONSE
raising	zcx_ibmx_service_exception

Start a text extraction request

Start a request to extract text and metadata from documents.

See the [documentation](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-dat a/fm-api-text-extraction.html?context=wx&audience=wdp) for a description of text extraction.

Parameters

i_textextractionrequest	The input for the text extraction request.
e_response	Service return value of type T_TEXT_EXTRACTION_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_extraction_delete
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_hard_delete	type BOOLEAN optional
raising	zcx_ibmx_service_exception

Delete the request

Cancel the specified text extraction request and delete any associated results.

Parameters

i_id	The identifier of the extraction request.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_hard_delete	Set to true in order to also delete the job or request metadata.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_extraction_get
importing	i_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_EXTRACTION_RESPONSE
raising	zcx_ibmx_service_exception

Get the results of the request

Retrieve the text extraction request with the specified identifier.

Note that there is a retention period of 2 days. If this retention
period is exceeded then the request will be deleted and the results
no longer available. In this case this operation will return `404`.

Parameters

i_id	The identifier of the extraction request.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_TEXT_EXTRACTION_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_generation
importing	i_textgenrequest	type T_TEXT_GEN_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_GEN_RESPONSE
raising	zcx_ibmx_service_exception

Infer text

Infer the next tokens for a given deployed model with a set of parameters.

Parameters

i_textgenrequest	From a given prompt, infer the next tokens.
e_response	Service return value of type T_TEXT_GEN_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_generation_stream
importing	i_textgenrequest	type T_TEXT_GEN_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'text/event-stream'
exporting	e_response	type T_ARRAY
raising	zcx_ibmx_service_exception

Infer text event stream

Infer the next tokens for a given deployed model with a set of parameters.
This operation will return the output tokens as a stream of events.

Parameters

i_textgenrequest	From a given prompt, infer the next tokens in a server-sent events (SSE) stream.
e_response	Service return value of type T_Array

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_rerank
importing	i_rerankrequest	type T_RERANK_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_RERANK_RESPONSE
raising	zcx_ibmx_service_exception

Generate rerank

Rerank texts based on some queries.

Parameters

i_rerankrequest	The input texts and the queries for reranking.
e_response	Service return value of type T_RERANK_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

text_tokenization
importing	i_texttokenizerequest	type T_TEXT_TOKENIZE_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TEXT_TOKENIZE_RESPONSE
raising	zcx_ibmx_service_exception

Text tokenization

The text tokenize operation allows you to check the conversion of provided input to tokens for a given model.
It splits text into words or sub-words, which then are converted to ids through a look-up table (vocabulary).
Tokenization allows the model to have a reasonable vocabulary size.

Parameters

i_texttokenizerequest	The input string to tokenize.
e_response	Service return value of type T_TEXT_TOKENIZE_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

time_series_forecast
importing	i_tsforecastrequest	type T_TSFORECAST_REQUEST
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TSFORECAST_RESPONSE
raising	zcx_ibmx_service_exception

Time series forecast

Generate forecasts, or predictions for future time points, given historical time series data.

Parameters

i_tsforecastrequest	The forecast request.
e_response	Service return value of type T_TSFORECAST_RESPONSE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

trainings_create
importing	i_trainingresourceprototype	type T_TRAINING_RESOURCE_PROTOTYPE
	i_contenttype	type STRING default 'application/json'
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TRAINING_RESOURCE
raising	zcx_ibmx_service_exception

Create a new watsonx.ai training

Create a new watsonx.ai training in a project or a space.

The details of the base model and parameters for the training
must be provided in the `prompt_tuning` object.

In order to deploy the tuned model you need to follow the following steps:

1. Create a WML model asset, in a space or a project,
by providing the `request.json` as shown below:
```
curl -X POST "https://{cpd_cluster}/ml/v4/models?version=2024-01-29" \
-H "Authorization: Bearer <replace with your token>" \
-H "content-type: application/json" \
--data '{
"name": "replace_with_a_meaningful_name",
"space_id": "replace_with_your_space_id",
"type": "prompt_tune_1.0",
"software_spec": {
"name": "watsonx-textgen-fm-1.0"
},
"metrics": [ from the training job ],
"training": {
"id": "05859469-b25b-420e-aefe-4a5cb6b595eb",
"base_model": {
"model_id": "google/flan-t5-xl"
},
"task_id": "generation",
"verbalizer": "Input: {{input}} Output:"
},
"training_data_references": [
{
"connection": {
"id": "20933468-7e8a-4706-bc90-f0a09332b263"
},
"id": "file_to_tune1.json",
"location": {
"bucket": "wxproject-donotdelete-pr-xeyivy0rx3vrbl",
"path": "file_to_tune1.json"
},
"type": "connection_asset"
}
]
}'
```

**Notes:**

1. If you used the training request field `auto_update_model: true`
then you can skip this step as the model will have been saved at
the end of the training job.
1. Rather than creating the payload for the model you can use the
generated `request.json` that was stored in the `results_reference`
field, look for the path in the field
`entity.results_reference.location.model_request_path`.
1. The model `type` must be `prompt_tune_1.0`.
1. The software spec name must be `watsonx-textgen-fm-1.0`.

1. Create a tuned model deployment as described in the
[create deployment documentation](#create-deployment).

Parameters

i_trainingresourceprototype	No documentation available.
e_response	Service return value of type T_TRAINING_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

trainings_delete
importing	i_training_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_hard_delete	type BOOLEAN optional
raising	zcx_ibmx_service_exception

Cancel or delete the training

Cancel or delete the specified training, once deleted all trace of the job is gone.

Parameters

i_training_id	The training identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_hard_delete	Set to true in order to also delete the job or request metadata.

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

trainings_get
importing	i_training_id	type STRING
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TRAINING_RESOURCE
raising	zcx_ibmx_service_exception

Retrieve the training

Retrieve the training with the specified identifier.

Parameters

i_training_id	The training identifier.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_TRAINING_RESOURCE

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.

public instance

trainings_list
importing	i_start	type STRING optional
	i_limit	type INTEGER default 100
	i_total_count	type BOOLEAN optional
	i_tag_value	type STRING optional
	i_state	type STRING optional
	i_space_id	type STRING optional
	i_project_id	type STRING optional
	i_accept	type STRING default 'application/json'
exporting	e_response	type T_TRAINING_RESOURCE_COLLECTION
raising	zcx_ibmx_service_exception

Retrieve the list of trainings

Retrieve the list of trainings for the specified space or project.

Parameters

i_start	Token required for token-based pagination. This token cannot be determined by end user. It is generated by the service and it is set in the href available in the `next` field.
i_limit	How many resources should be returned. By default limit is 100. Max limit allowed is 200.
i_total_count	Compute the total count. May have performance impact.
i_tag_value	Return only the resources with the given tag value.
i_state	Filter based on on the training job state.
i_space_id	The space that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
i_project_id	The project that contains the resource. Either `space_id` or `project_id` query parameter has to be given.
e_response	Service return value of type T_TRAINING_RESOURCE_COLLECTION

Class-based Exceptions

zcx_ibmx_service_exception

Exception being raised in case of an error.