Version 1.1.6

abacusai/__init__.py

@@ -4,4 +4,4 @@
 from .streaming_client import StreamingClient
 
 
-__version__ = "1.1.5"
+__version__ = "1.1.6"

abacusai/api_class/batch_prediction.py

@@ -24,9 +24,11 @@ class AnomalyOutliersBatchPredictionArgs(BatchPredictionArgs):
     Args:
         for_eval (bool): If True, the test fold which was created during training and used for metrics calculation will be used as input data. These predictions are hence, used for model evaluation.
         threshold (float): The threshold for detecting an anomaly. Range: [0.8, 0.99]
+        explain_predictions (bool): If True, calculates explanations for the predicted values along with predictions.
     """
     for_eval: bool = dataclasses.field(default=None)
     threshold: float = dataclasses.field(default=None)
+    explain_predictions: bool = dataclasses.field(default=None)
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.ANOMALY_OUTLIERS
@@ -44,7 +46,8 @@ class ForecastingBatchPredictionArgs(BatchPredictionArgs):
        start_date_offset (int): Sets prediction start date as this offset relative to the prediction start date.
        forecasting_horizon (int): The number of timestamps to predict in the future. Range: [1, 1000].
        item_attributes_to_include_in_the_result (list): List of columns to include in the prediction output.
-       explain_predictions (bool): If True, explain predictions for the forecast.
+       explain_predictions (bool): If True, calculates explanations for the forecasted values along with predictions.
+       automate_monitoring (bool): If True, creates a monitor to calculate the drift for the batch prediction.
     """
     for_eval: bool = dataclasses.field(default=None)
     predictions_start_date: str = dataclasses.field(default=None)
@@ -53,6 +56,7 @@ class ForecastingBatchPredictionArgs(BatchPredictionArgs):
     forecasting_horizon: int = dataclasses.field(default=None)
     item_attributes_to_include_in_the_result: list = dataclasses.field(default=None)
     explain_predictions: bool = dataclasses.field(default=None)
+    automate_monitoring: bool = dataclasses.field(default=None)
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.FORECASTING
@@ -110,6 +114,8 @@ class PredictiveModelingBatchPredictionArgs(BatchPredictionArgs):
        explanation_filter_upper_bound (float): If set explanations will be limited to predictions below this value, Range: [0, 1].
        bound_label (str): For classification problems specifies the label to which the explanation bounds are applied.
        output_columns (list): A list of column names to include in the prediction result.
+       explain_predictions (bool): If True, calculates explanations for the predicted values along with predictions.
+       automate_monitoring (bool): If True, creates a monitor to calculate the drift for the batch prediction.
     """
     for_eval: bool = dataclasses.field(default=None)
     explainer_type: enums.ExplainerType = dataclasses.field(default=None)
@@ -121,6 +127,8 @@ class PredictiveModelingBatchPredictionArgs(BatchPredictionArgs):
     explanation_filter_upper_bound: float = dataclasses.field(default=None)
     explanation_filter_label: str = dataclasses.field(default=None)
     output_columns: list = dataclasses.field(default=None)
+    explain_predictions: bool = dataclasses.field(default=None)
+    automate_monitoring: bool = dataclasses.field(default=None)
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.PREDICTIVE_MODELING
@@ -194,6 +202,21 @@ def __post_init__(self):
         self.problem_type = enums.ProblemType.CHAT_LLM
 
 
+@dataclasses.dataclass
+class TrainablePlugAndPlayBatchPredictionArgs(BatchPredictionArgs):
+    """
+    Batch Prediction Config for the TrainablePlugAndPlay problem type
+
+    Args:
+        automate_monitoring (bool): If True, creates a monitor to calculate the drift for the batch prediction.
+    """
+    for_eval: bool = dataclasses.field(default=None)
+    automate_monitoring: bool = dataclasses.field(default=None)
+
+    def __post_init__(self):
+        self.problem_type = enums.ProblemType.CUSTOM_ALGORITHM
+
+
 @dataclasses.dataclass
 class _BatchPredictionArgsFactory(_ApiClassFactory):
     config_abstract_class = BatchPredictionArgs
@@ -208,4 +231,5 @@ class _BatchPredictionArgsFactory(_ApiClassFactory):
         enums.ProblemType.SENTENCE_BOUNDARY_DETECTION: SentenceBoundaryDetectionBatchPredictionArgs,
         enums.ProblemType.THEME_ANALYSIS: ThemeAnalysisBatchPredictionArgs,
         enums.ProblemType.CHAT_LLM: ChatLLMBatchPredictionArgs,
+        enums.ProblemType.CUSTOM_ALGORITHM: TrainablePlugAndPlayBatchPredictionArgs,
     }

abacusai/api_class/document_retriever.py

@@ -14,11 +14,13 @@ class VectorStoreConfig(ApiClass):
         chunk_overlap_fraction (float): The fraction of overlap between chunks.
         text_encoder (VectorStoreTextEncoder): Encoder used to index texts from the documents.
         chunk_size_factors (list): Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
+        score_multiplier_column (str): If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
     """
     chunk_size: int = dataclasses.field(default=None)
     chunk_overlap_fraction: float = dataclasses.field(default=None)
     text_encoder: VectorStoreTextEncoder = dataclasses.field(default=None)
     chunk_size_factors: list = dataclasses.field(default=None)
+    score_multiplier_column: str = dataclasses.field(default=None)
 
 
 @dataclasses.dataclass

abacusai/api_class/enums.py

@@ -350,6 +350,7 @@ class ApplicationConnectorType(ApiEnum):
     SHAREPOINT = 'SHAREPOINT'
     TEAMS = 'TEAMS'
     ABACUSUSAGEMETRICS = 'ABACUSUSAGEMETRICS'
+    MICROSOFTAUTH = 'MICROSOFTAUTH'
 
 
 class PythonFunctionArgumentType(ApiEnum):
@@ -476,3 +477,22 @@ class OcrMode(ApiEnum):
     COMPREHENSIVE = 'COMPREHENSIVE'
     COMPREHENSIVE_V2 = 'COMPREHENSIVE_V2'
     COMPREHENSIVE_TABLE_MD = 'COMPREHENSIVE_TABLE_MD'
+
+
+class DataType(ApiEnum):
+    INTEGER = 'integer'
+    FLOAT = 'float'
+    STRING = 'string'
+    DATE = 'date'
+    DATETIME = 'datetime'
+    BOOLEAN = 'boolean'
+    LIST = 'list'
+    STRUCT = 'struct'
+    NULL = 'null'
+
+    @classmethod
+    def from_str(cls, value):
+        if not value:
+            return None
+        default_map = {val.value: val for val in DataType}
+        return default_map[value.lower()]

abacusai/api_class/model.py

@@ -453,6 +453,7 @@ class ChatLLMTrainingConfig(TrainingConfig):
         hide_generated_sql (bool): When running data queries, hides the generated SQL in the response and will just return the table.
         disable_data_summarization (bool): After executing a query summarize the reponse and reply back with only the table and query run.
         search_score_cutoff (float): Minimum search score to consider a document as a valid search result.
+        database_connector_id (str): Database connector id to use for the chatllm.
     """
     document_retrievers: List[str] = None
     num_completion_tokens: int = None
@@ -468,6 +469,7 @@ class ChatLLMTrainingConfig(TrainingConfig):
     hide_generated_sql: bool = None
     disable_data_summarization: bool = None
     search_score_cutoff: float = None
+    database_connector_id: str = None
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.CHAT_LLM