abacusai.api_class.deployment ============================= .. py:module:: abacusai.api_class.deployment Classes ------- .. autoapisummary:: abacusai.api_class.deployment.PredictionArguments abacusai.api_class.deployment.OptimizationPredictionArguments abacusai.api_class.deployment.TimeseriesAnomalyPredictionArguments abacusai.api_class.deployment.ChatLLMPredictionArguments abacusai.api_class.deployment.RegressionPredictionArguments abacusai.api_class.deployment.ForecastingPredictionArguments abacusai.api_class.deployment.CumulativeForecastingPredictionArguments abacusai.api_class.deployment.NaturalLanguageSearchPredictionArguments abacusai.api_class.deployment.FeatureStorePredictionArguments abacusai.api_class.deployment._PredictionArgumentsFactory Module Contents --------------- .. py:class:: PredictionArguments Bases: :py:obj:`abacusai.api_class.abstract.ApiClass` An abstract class for prediction arguments specific to problem type. .. py:attribute:: _support_kwargs :type: bool :value: True .. py:attribute:: kwargs :type: dict .. py:attribute:: problem_type :type: abacusai.api_class.enums.ProblemType :value: None .. py:method:: _get_builder() :classmethod: .. py:class:: OptimizationPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the OPTIMIZATION problem type :param forced_assignments: Set of assignments to force and resolve before returning query results. :type forced_assignments: dict :param solve_time_limit_seconds: Maximum time in seconds to spend solving the query. :type solve_time_limit_seconds: float :param include_all_assignments: If True, will return all assignments, including assignments with value 0. Default is False. :type include_all_assignments: bool .. py:attribute:: forced_assignments :type: dict :value: None .. py:attribute:: solve_time_limit_seconds :type: float :value: None .. py:attribute:: include_all_assignments :type: bool :value: None .. py:method:: __post_init__() .. py:class:: TimeseriesAnomalyPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the TS_ANOMALY problem type :param start_timestamp: Timestamp from which anomalies have to be detected in the training data :type start_timestamp: str :param end_timestamp: Timestamp to which anomalies have to be detected in the training data :type end_timestamp: str :param get_all_item_data: If True, anomaly detection has to be performed on all the data related to input ids :type get_all_item_data: bool .. py:attribute:: start_timestamp :type: str :value: None .. py:attribute:: end_timestamp :type: str :value: None .. py:attribute:: get_all_item_data :type: bool :value: None .. py:method:: __post_init__() .. py:class:: ChatLLMPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the CHAT_LLM problem type :param llm_name: Name of the specific LLM backend to use to power the chat experience. :type llm_name: str :param num_completion_tokens: Default for maximum number of tokens for chat answers. :type num_completion_tokens: int :param system_message: The generative LLM system message. :type system_message: str :param temperature: The generative LLM temperature. :type temperature: float :param search_score_cutoff: Cutoff for the document retriever score. Matching search results below this score will be ignored. :type search_score_cutoff: float :param ignore_documents: If True, will ignore any documents and search results, and only use the messages to generate a response. :type ignore_documents: bool .. py:attribute:: llm_name :type: str :value: None .. py:attribute:: num_completion_tokens :type: int :value: None .. py:attribute:: system_message :type: str :value: None .. py:attribute:: temperature :type: float :value: None .. py:attribute:: search_score_cutoff :type: float :value: None .. py:attribute:: ignore_documents :type: bool :value: None .. py:method:: __post_init__() .. py:class:: RegressionPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the PREDICTIVE_MODELING problem type :param explain_predictions: If true, will explain predictions. :type explain_predictions: bool :param explainer_type: Type of explainer to use for explanations. :type explainer_type: str .. py:attribute:: explain_predictions :type: bool :value: None .. py:attribute:: explainer_type :type: str :value: None .. py:method:: __post_init__() .. py:class:: ForecastingPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the FORECASTING problem type :param num_predictions: The number of timestamps to predict in the future. :type num_predictions: int :param prediction_start: The start date for predictions (e.g., "2015-08-01T00:00:00" as input for mid-night of 2015-08-01). :type prediction_start: str :param explain_predictions: If True, explain predictions for forecasting. :type explain_predictions: bool :param explainer_type: Type of explainer to use for explanations. :type explainer_type: str :param get_item_data: If True, will return the data corresponding to items as well. :type get_item_data: bool .. py:attribute:: num_predictions :type: int :value: None .. py:attribute:: prediction_start :type: str :value: None .. py:attribute:: explain_predictions :type: bool :value: None .. py:attribute:: explainer_type :type: str :value: None .. py:attribute:: get_item_data :type: bool :value: None .. py:method:: __post_init__() .. py:class:: CumulativeForecastingPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the CUMULATIVE_FORECASTING problem type :param num_predictions: The number of timestamps to predict in the future. :type num_predictions: int :param prediction_start: The start date for predictions (e.g., "2015-08-01T00:00:00" as input for mid-night of 2015-08-01). :type prediction_start: str :param explain_predictions: If True, explain predictions for forecasting. :type explain_predictions: bool :param explainer_type: Type of explainer to use for explanations. :type explainer_type: str :param get_item_data: If True, will return the data corresponding to items as well. :type get_item_data: bool .. py:attribute:: num_predictions :type: int :value: None .. py:attribute:: prediction_start :type: str :value: None .. py:attribute:: explain_predictions :type: bool :value: None .. py:attribute:: explainer_type :type: str :value: None .. py:attribute:: get_item_data :type: bool :value: None .. py:method:: __post_init__() .. py:class:: NaturalLanguageSearchPredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the NATURAL_LANGUAGE_SEARCH problem type :param llm_name: Name of the specific LLM backend to use to power the chat experience. :type llm_name: str :param num_completion_tokens: Default for maximum number of tokens for chat answers. :type num_completion_tokens: int :param system_message: The generative LLM system message. :type system_message: str :param temperature: The generative LLM temperature. :type temperature: float :param search_score_cutoff: Cutoff for the document retriever score. Matching search results below this score will be ignored. :type search_score_cutoff: float :param ignore_documents: If True, will ignore any documents and search results, and only use the messages to generate a response. :type ignore_documents: bool .. py:attribute:: llm_name :type: str :value: None .. py:attribute:: num_completion_tokens :type: int :value: None .. py:attribute:: system_message :type: str :value: None .. py:attribute:: temperature :type: float :value: None .. py:attribute:: search_score_cutoff :type: float :value: None .. py:attribute:: ignore_documents :type: bool :value: None .. py:method:: __post_init__() .. py:class:: FeatureStorePredictionArguments Bases: :py:obj:`PredictionArguments` Prediction arguments for the FEATURE_STORE problem type :param limit_results: If provided, will limit the number of results to the value specified. :type limit_results: int .. py:attribute:: limit_results :type: int :value: None .. py:method:: __post_init__() .. py:class:: _PredictionArgumentsFactory Bases: :py:obj:`abacusai.api_class.abstract._ApiClassFactory` Helper class that provides a standard way to create an ABC using inheritance. .. py:attribute:: config_abstract_class .. py:attribute:: config_class_key :value: 'problem_type' .. py:attribute:: config_class_map