From bf6639758223afbd5734ff81f749b4497df07cdb Mon Sep 17 00:00:00 2001
From: Austin Zielman
Date: Thu, 29 Feb 2024 23:51:53 +0000
Subject: [PATCH] Version 1.1.6
---
abacusai/__init__.py | 2 +-
abacusai/api_class/batch_prediction.py | 26 +-
abacusai/api_class/document_retriever.py | 2 +
abacusai/api_class/enums.py | 20 ++
abacusai/api_class/model.py | 2 +
abacusai/batch_prediction.py | 25 +-
abacusai/batch_prediction_version.py | 22 +-
abacusai/client.py | 52 ++-
abacusai/dataset.py | 6 +-
abacusai/deployment.py | 7 +-
abacusai/document_retriever_config.py | 12 +-
abacusai/external_application.py | 18 +-
abacusai/feature_group.py | 17 +-
abacusai/feature_group_export.py | 4 -
abacusai/pipeline.py | 15 +-
abacusai/pipeline_version.py | 13 +-
abacusai/project.py | 22 --
abacusai/public.pem | 6 +-
.../api_class/batch_prediction/index.rst.txt | 55 ++-
.../document_retriever/index.rst.txt | 7 +
.../abacusai/api_class/enums/index.rst.txt | 65 ++++
.../autoapi/abacusai/api_class/index.rst.txt | 134 +++++++-
.../abacusai/api_class/model/index.rst.txt | 7 +
.../abacusai/batch_prediction/index.rst.txt | 14 +-
.../batch_prediction_version/index.rst.txt | 10 +-
.../autoapi/abacusai/client/index.rst.txt | 43 +--
.../autoapi/abacusai/dataset/index.rst.txt | 2 +-
.../autoapi/abacusai/deployment/index.rst.txt | 8 +-
.../document_retriever_config/index.rst.txt | 4 +-
.../external_application/index.rst.txt | 10 +-
.../abacusai/feature_group/index.rst.txt | 15 +-
.../feature_group_export/index.rst.txt | 3 -
docs/_sources/autoapi/abacusai/index.rst.txt | 177 ++++++++--
.../autoapi/abacusai/pipeline/index.rst.txt | 4 +-
.../abacusai/pipeline_version/index.rst.txt | 4 +-
.../autoapi/abacusai/project/index.rst.txt | 21 --
.../api_class/batch_prediction/index.html | 58 +++-
.../api_class/document_retriever/index.html | 6 +
.../abacusai/api_class/enums/index.html | 66 ++++
docs/autoapi/abacusai/api_class/index.html | 280 +++++++++++-----
.../abacusai/api_class/model/index.html | 6 +
.../abacusai/batch_prediction/index.html | 13 +-
.../batch_prediction_version/index.html | 10 +-
docs/autoapi/abacusai/client/index.html | 45 +--
docs/autoapi/abacusai/dataset/index.html | 2 +-
docs/autoapi/abacusai/deployment/index.html | 7 +-
.../document_retriever_config/index.html | 3 +-
.../abacusai/external_application/index.html | 7 +-
.../autoapi/abacusai/feature_group/index.html | 22 +-
.../abacusai/feature_group_export/index.html | 5 -
docs/autoapi/abacusai/index.html | 313 ++++++++++++------
docs/autoapi/abacusai/pipeline/index.html | 3 +-
.../abacusai/pipeline_version/index.html | 3 +-
docs/autoapi/abacusai/project/index.html | 31 --
docs/genindex.html | 208 +++++++++---
docs/objects.inv | Bin 47609 -> 48060 bytes
docs/searchindex.js | 2 +-
setup.py | 2 +-
58 files changed, 1364 insertions(+), 582 deletions(-)
diff --git a/abacusai/__init__.py b/abacusai/__init__.py
index 45423432c..b7389d2ff 100644
--- a/abacusai/__init__.py
+++ b/abacusai/__init__.py
@@ -4,4 +4,4 @@
from .streaming_client import StreamingClient
-__version__ = "1.1.5"
+__version__ = "1.1.6"
diff --git a/abacusai/api_class/batch_prediction.py b/abacusai/api_class/batch_prediction.py
index dc3de2a57..7e228132b 100644
--- a/abacusai/api_class/batch_prediction.py
+++ b/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,
}
diff --git a/abacusai/api_class/document_retriever.py b/abacusai/api_class/document_retriever.py
index 2efc7b430..4d8e8681d 100644
--- a/abacusai/api_class/document_retriever.py
+++ b/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
diff --git a/abacusai/api_class/enums.py b/abacusai/api_class/enums.py
index 944370e76..a034f629f 100644
--- a/abacusai/api_class/enums.py
+++ b/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()]
diff --git a/abacusai/api_class/model.py b/abacusai/api_class/model.py
index f6505f84d..3f3448835 100644
--- a/abacusai/api_class/model.py
+++ b/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
diff --git a/abacusai/batch_prediction.py b/abacusai/batch_prediction.py
index 0fb2a8a13..5241ed4b2 100644
--- a/abacusai/batch_prediction.py
+++ b/abacusai/batch_prediction.py
@@ -21,11 +21,11 @@ class BatchPrediction(AbstractApiClass):
fileConnectorOutputLocation (str): Contains information about where the batch predictions are written to.
databaseConnectorId (str): The database connector to write the results to.
databaseOutputConfiguration (dict): Contains information about where the batch predictions are written to.
- explanations (bool): If true, explanations for each prediction will be created.
+ explanations (bool):
fileOutputFormat (str): The format of the batch prediction output (CSV or JSON).
connectorType (str): Null if writing to internal console, else FEATURE_GROUP | FILE_CONNECTOR | DATABASE_CONNECTOR.
legacyInputLocation (str): The location of the input data.
- outputFeatureGroupId (str): The BP output feature group id if applicable
+ outputFeatureGroupId (str): The Batch Prediction output feature group ID if applicable
featureGroupTableName (str): The table name of the Batch Prediction output feature group.
outputFeatureGroupTableName (str): The table name of the Batch Prediction output feature group.
summaryFeatureGroupTableName (str): The table name of the metrics summary feature group output by Batch Prediction.
@@ -43,7 +43,7 @@ class BatchPrediction(AbstractApiClass):
inputFeatureGroups (PredictionFeatureGroup): List of prediction feature groups.
"""
- def __init__(self, client, batchPredictionId=None, createdAt=None, name=None, deploymentId=None, fileConnectorOutputLocation=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, outputFeatureGroupId=None, featureGroupTableName=None, outputFeatureGroupTableName=None, summaryFeatureGroupTableName=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorId=None, modelVersion=None, algorithm=None, batchInputs={}, latestBatchPredictionVersion={}, refreshSchedules={}, inputFeatureGroups={}, globalPredictionArgs={}):
+ def __init__(self, client, batchPredictionId=None, createdAt=None, name=None, deploymentId=None, fileConnectorOutputLocation=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, outputFeatureGroupId=None, featureGroupTableName=None, outputFeatureGroupTableName=None, summaryFeatureGroupTableName=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorId=None, modelVersion=None, algorithm=None, batchInputs={}, latestBatchPredictionVersion={}, refreshSchedules={}, inputFeatureGroups={}, globalPredictionArgs={}, batchPredictionArgs={}):
super().__init__(client, batchPredictionId)
self.batch_prediction_id = batchPredictionId
self.created_at = createdAt
@@ -77,11 +77,13 @@ def __init__(self, client, batchPredictionId=None, createdAt=None, name=None, de
PredictionFeatureGroup, inputFeatureGroups)
self.global_prediction_args = client._build_class(
BatchPredictionArgs, globalPredictionArgs)
- self.deprecated_keys = {}
+ self.batch_prediction_args = client._build_class(
+ BatchPredictionArgs, batchPredictionArgs)
+ self.deprecated_keys = {'global_prediction_args', 'explanations'}
def __repr__(self):
- repr_dict = {f'batch_prediction_id': repr(self.batch_prediction_id), f'created_at': repr(self.created_at), f'name': repr(self.name), f'deployment_id': repr(self.deployment_id), f'file_connector_output_location': repr(self.file_connector_output_location), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(self.legacy_input_location), f'output_feature_group_id': repr(self.output_feature_group_id), f'feature_group_table_name': repr(self.feature_group_table_name), f'output_feature_group_table_name': repr(
- self.output_feature_group_table_name), f'summary_feature_group_table_name': repr(self.summary_feature_group_table_name), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_id': repr(self.model_monitor_id), f'model_version': repr(self.model_version), f'algorithm': repr(self.algorithm), f'batch_inputs': repr(self.batch_inputs), f'latest_batch_prediction_version': repr(self.latest_batch_prediction_version), f'refresh_schedules': repr(self.refresh_schedules), f'input_feature_groups': repr(self.input_feature_groups), f'global_prediction_args': repr(self.global_prediction_args)}
+ repr_dict = {f'batch_prediction_id': repr(self.batch_prediction_id), f'created_at': repr(self.created_at), f'name': repr(self.name), f'deployment_id': repr(self.deployment_id), f'file_connector_output_location': repr(self.file_connector_output_location), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(self.legacy_input_location), f'output_feature_group_id': repr(self.output_feature_group_id), f'feature_group_table_name': repr(self.feature_group_table_name), f'output_feature_group_table_name': repr(self.output_feature_group_table_name), f'summary_feature_group_table_name': repr(
+ self.summary_feature_group_table_name), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_id': repr(self.model_monitor_id), f'model_version': repr(self.model_version), f'algorithm': repr(self.algorithm), f'batch_inputs': repr(self.batch_inputs), f'latest_batch_prediction_version': repr(self.latest_batch_prediction_version), f'refresh_schedules': repr(self.refresh_schedules), f'input_feature_groups': repr(self.input_feature_groups), f'global_prediction_args': repr(self.global_prediction_args), f'batch_prediction_args': repr(self.batch_prediction_args)}
class_name = "BatchPrediction"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -94,8 +96,8 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'batch_prediction_id': self.batch_prediction_id, 'created_at': self.created_at, 'name': self.name, 'deployment_id': self.deployment_id, 'file_connector_output_location': self.file_connector_output_location, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'output_feature_group_id': self.output_feature_group_id, 'feature_group_table_name': self.feature_group_table_name, 'output_feature_group_table_name': self.output_feature_group_table_name, 'summary_feature_group_table_name': self.summary_feature_group_table_name,
- 'csv_input_prefix': self.csv_input_prefix, 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_id': self.model_monitor_id, 'model_version': self.model_version, 'algorithm': self.algorithm, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'latest_batch_prediction_version': self._get_attribute_as_dict(self.latest_batch_prediction_version), 'refresh_schedules': self._get_attribute_as_dict(self.refresh_schedules), 'input_feature_groups': self._get_attribute_as_dict(self.input_feature_groups), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
+ resp = {'batch_prediction_id': self.batch_prediction_id, 'created_at': self.created_at, 'name': self.name, 'deployment_id': self.deployment_id, 'file_connector_output_location': self.file_connector_output_location, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'output_feature_group_id': self.output_feature_group_id, 'feature_group_table_name': self.feature_group_table_name, 'output_feature_group_table_name': self.output_feature_group_table_name, 'summary_feature_group_table_name': self.summary_feature_group_table_name, 'csv_input_prefix': self.csv_input_prefix,
+ 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_id': self.model_monitor_id, 'model_version': self.model_version, 'algorithm': self.algorithm, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'latest_batch_prediction_version': self._get_attribute_as_dict(self.latest_batch_prediction_version), 'refresh_schedules': self._get_attribute_as_dict(self.refresh_schedules), 'input_feature_groups': self._get_attribute_as_dict(self.input_feature_groups), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args), 'batch_prediction_args': self._get_attribute_as_dict(self.batch_prediction_args)}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
def start(self):
@@ -145,14 +147,13 @@ def list_versions(self, limit: int = 100, start_after_version: str = None):
"""
return self.client.list_batch_prediction_versions(self.batch_prediction_id, limit, start_after_version)
- def update(self, deployment_id: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = None, output_format: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, name: str = None):
+ def update(self, deployment_id: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, batch_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = None, output_format: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, name: str = None):
"""
Update a batch prediction job description.
Args:
deployment_id (str): Unique identifier of the deployment.
- global_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
- explanations (bool): If True, SHAP explanations for each prediction will be provided, if supported by the use case.
+ batch_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
output_format (str): If specified, sets the format of the batch prediction output (CSV or JSON).
csv_input_prefix (str): Prefix to prepend to the input columns, only applies when output format is CSV.
csv_prediction_prefix (str): Prefix to prepend to the prediction columns, only applies when output format is CSV.
@@ -164,7 +165,7 @@ def update(self, deployment_id: str = None, global_prediction_args: Union[dict,
Returns:
BatchPrediction: The batch prediction.
"""
- return self.client.update_batch_prediction(self.batch_prediction_id, deployment_id, global_prediction_args, explanations, output_format, csv_input_prefix, csv_prediction_prefix, csv_explanations_prefix, output_includes_metadata, result_input_columns, name)
+ return self.client.update_batch_prediction(self.batch_prediction_id, deployment_id, global_prediction_args, batch_prediction_args, explanations, output_format, csv_input_prefix, csv_prediction_prefix, csv_explanations_prefix, output_includes_metadata, result_input_columns, name)
def set_file_connector_output(self, output_format: str = None, output_location: str = None):
"""
diff --git a/abacusai/batch_prediction_version.py b/abacusai/batch_prediction_version.py
index 10482e140..bc3d1c7b3 100644
--- a/abacusai/batch_prediction_version.py
+++ b/abacusai/batch_prediction_version.py
@@ -24,7 +24,7 @@ class BatchPredictionVersion(AbstractApiClass):
failedPredictions (int): Number of predictions that failed
databaseConnectorId (str): The database connector to write the results to
databaseOutputConfiguration (dict): Contains information about where the batch predictions are written to
- explanations (bool): If true, explanations for each prediction were created
+ explanations (bool):
fileConnectorOutputLocation (str): Contains information about where the batch predictions are written to
fileOutputFormat (str): The format of the batch prediction output (CSV or JSON)
connectorType (str): Null if writing to internal console, else FEATURE_GROUP | FILE_CONNECTOR | DATABASE_CONNECTOR
@@ -42,15 +42,15 @@ class BatchPredictionVersion(AbstractApiClass):
modelMonitorVersion (str): The version of the model monitor
algoName (str): The name of the algorithm used to train the model
algorithm (str): The algorithm that is currently deployed.
- outputFeatureGroupId (str): The BP output feature group id if applicable
- outputFeatureGroupVersion (str): The BP output feature group version if applicable
- outputFeatureGroupTableName (str): The BP output feature group name if applicable
+ outputFeatureGroupId (str): The Batch Prediction output feature group ID if applicable
+ outputFeatureGroupVersion (str): The Batch Prediction output feature group version if applicable
+ outputFeatureGroupTableName (str): The Batch Prediction output feature group name if applicable
batchPredictionWarnings (str): Relevant warnings if any issues are found
batchInputs (PredictionInput): Inputs to the batch prediction
inputFeatureGroups (PredictionFeatureGroup): List of prediction feature groups
"""
- def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupId=None, outputFeatureGroupVersion=None, outputFeatureGroupTableName=None, batchPredictionWarnings=None, batchInputs={}, inputFeatureGroups={}, globalPredictionArgs={}):
+ def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupId=None, outputFeatureGroupVersion=None, outputFeatureGroupTableName=None, batchPredictionWarnings=None, batchInputs={}, inputFeatureGroups={}, globalPredictionArgs={}, batchPredictionArgs={}):
super().__init__(client, batchPredictionVersion)
self.batch_prediction_version = batchPredictionVersion
self.batch_prediction_id = batchPredictionId
@@ -93,11 +93,13 @@ def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None,
PredictionFeatureGroup, inputFeatureGroups)
self.global_prediction_args = client._build_class(
BatchPredictionArgs, globalPredictionArgs)
- self.deprecated_keys = {}
+ self.batch_prediction_args = client._build_class(
+ BatchPredictionArgs, batchPredictionArgs)
+ self.deprecated_keys = {'global_prediction_args', 'explanations'}
def __repr__(self):
- repr_dict = {f'batch_prediction_version': repr(self.batch_prediction_version), f'batch_prediction_id': repr(self.batch_prediction_id), f'status': repr(self.status), f'drift_monitor_status': repr(self.drift_monitor_status), f'deployment_id': repr(self.deployment_id), f'model_id': repr(self.model_id), f'model_version': repr(self.model_version), f'predictions_started_at': repr(self.predictions_started_at), f'predictions_completed_at': repr(self.predictions_completed_at), f'database_output_error': repr(self.database_output_error), f'total_predictions': repr(self.total_predictions), f'failed_predictions': repr(self.failed_predictions), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_connector_output_location': repr(self.file_connector_output_location), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(self.legacy_input_location), f'error': repr(self.error), f'drift_monitor_error': repr(
- self.drift_monitor_error), f'monitor_warnings': repr(self.monitor_warnings), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'database_output_total_writes': repr(self.database_output_total_writes), f'database_output_failed_writes': repr(self.database_output_failed_writes), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_version': repr(self.model_monitor_version), f'algo_name': repr(self.algo_name), f'algorithm': repr(self.algorithm), f'output_feature_group_id': repr(self.output_feature_group_id), f'output_feature_group_version': repr(self.output_feature_group_version), f'output_feature_group_table_name': repr(self.output_feature_group_table_name), f'batch_prediction_warnings': repr(self.batch_prediction_warnings), f'batch_inputs': repr(self.batch_inputs), f'input_feature_groups': repr(self.input_feature_groups), f'global_prediction_args': repr(self.global_prediction_args)}
+ repr_dict = {f'batch_prediction_version': repr(self.batch_prediction_version), f'batch_prediction_id': repr(self.batch_prediction_id), f'status': repr(self.status), f'drift_monitor_status': repr(self.drift_monitor_status), f'deployment_id': repr(self.deployment_id), f'model_id': repr(self.model_id), f'model_version': repr(self.model_version), f'predictions_started_at': repr(self.predictions_started_at), f'predictions_completed_at': repr(self.predictions_completed_at), f'database_output_error': repr(self.database_output_error), f'total_predictions': repr(self.total_predictions), f'failed_predictions': repr(self.failed_predictions), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_connector_output_location': repr(self.file_connector_output_location), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(self.legacy_input_location), f'error': repr(self.error), f'drift_monitor_error': repr(self.drift_monitor_error), f'monitor_warnings': repr(
+ self.monitor_warnings), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'database_output_total_writes': repr(self.database_output_total_writes), f'database_output_failed_writes': repr(self.database_output_failed_writes), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_version': repr(self.model_monitor_version), f'algo_name': repr(self.algo_name), f'algorithm': repr(self.algorithm), f'output_feature_group_id': repr(self.output_feature_group_id), f'output_feature_group_version': repr(self.output_feature_group_version), f'output_feature_group_table_name': repr(self.output_feature_group_table_name), f'batch_prediction_warnings': repr(self.batch_prediction_warnings), f'batch_inputs': repr(self.batch_inputs), f'input_feature_groups': repr(self.input_feature_groups), f'global_prediction_args': repr(self.global_prediction_args), f'batch_prediction_args': repr(self.batch_prediction_args)}
class_name = "BatchPredictionVersion"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -110,8 +112,8 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'batch_prediction_version': self.batch_prediction_version, 'batch_prediction_id': self.batch_prediction_id, 'status': self.status, 'drift_monitor_status': self.drift_monitor_status, 'deployment_id': self.deployment_id, 'model_id': self.model_id, 'model_version': self.model_version, 'predictions_started_at': self.predictions_started_at, 'predictions_completed_at': self.predictions_completed_at, 'database_output_error': self.database_output_error, 'total_predictions': self.total_predictions, 'failed_predictions': self.failed_predictions, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_connector_output_location': self.file_connector_output_location, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'error': self.error, 'drift_monitor_error': self.drift_monitor_error, 'monitor_warnings': self.monitor_warnings,
- 'csv_input_prefix': self.csv_input_prefix, 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'database_output_total_writes': self.database_output_total_writes, 'database_output_failed_writes': self.database_output_failed_writes, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_version': self.model_monitor_version, 'algo_name': self.algo_name, 'algorithm': self.algorithm, 'output_feature_group_id': self.output_feature_group_id, 'output_feature_group_version': self.output_feature_group_version, 'output_feature_group_table_name': self.output_feature_group_table_name, 'batch_prediction_warnings': self.batch_prediction_warnings, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'input_feature_groups': self._get_attribute_as_dict(self.input_feature_groups), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
+ resp = {'batch_prediction_version': self.batch_prediction_version, 'batch_prediction_id': self.batch_prediction_id, 'status': self.status, 'drift_monitor_status': self.drift_monitor_status, 'deployment_id': self.deployment_id, 'model_id': self.model_id, 'model_version': self.model_version, 'predictions_started_at': self.predictions_started_at, 'predictions_completed_at': self.predictions_completed_at, 'database_output_error': self.database_output_error, 'total_predictions': self.total_predictions, 'failed_predictions': self.failed_predictions, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_connector_output_location': self.file_connector_output_location, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'error': self.error, 'drift_monitor_error': self.drift_monitor_error, 'monitor_warnings': self.monitor_warnings, 'csv_input_prefix': self.csv_input_prefix,
+ 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'database_output_total_writes': self.database_output_total_writes, 'database_output_failed_writes': self.database_output_failed_writes, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_version': self.model_monitor_version, 'algo_name': self.algo_name, 'algorithm': self.algorithm, 'output_feature_group_id': self.output_feature_group_id, 'output_feature_group_version': self.output_feature_group_version, 'output_feature_group_table_name': self.output_feature_group_table_name, 'batch_prediction_warnings': self.batch_prediction_warnings, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'input_feature_groups': self._get_attribute_as_dict(self.input_feature_groups), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args), 'batch_prediction_args': self._get_attribute_as_dict(self.batch_prediction_args)}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
def download_batch_prediction_result_chunk(self, offset: int = 0, chunk_size: int = 10485760):
diff --git a/abacusai/client.py b/abacusai/client.py
index 2c50afe2a..057318c78 100644
--- a/abacusai/client.py
+++ b/abacusai/client.py
@@ -33,11 +33,11 @@
from .annotations_status import AnnotationsStatus
from .api_class import (
AlertActionConfig, AlertConditionConfig, ApiClass, ApiEnum,
- BatchPredictionArgs, BlobInput, DatasetConfig, DocumentProcessingConfig,
- DocumentRetrieverConfig, EvalArtifactType, FeatureGroupExportConfig,
- ForecastingMonitorConfig, IncrementalDatabaseConnectorConfig, LLMName,
- MergeConfig, ParsingConfig, ProblemType, PythonFunctionType,
- SamplingConfig, TrainingConfig
+ BatchPredictionArgs, BlobInput, DatasetConfig, DataType,
+ DocumentProcessingConfig, DocumentRetrieverConfig, EvalArtifactType,
+ FeatureGroupExportConfig, ForecastingMonitorConfig,
+ IncrementalDatabaseConnectorConfig, LLMName, MergeConfig, ParsingConfig,
+ ProblemType, PythonFunctionType, SamplingConfig, TrainingConfig
)
from .api_client_utils import (
INVALID_PANDAS_COLUMN_NAME_CHARACTERS, StreamingHandler, clean_column_name,
@@ -575,7 +575,7 @@ class BaseApiClient:
client_options (ClientOptions): Optional API client configurations
skip_version_check (bool): If true, will skip checking the server's current API version on initializing the client
"""
- client_version = '1.1.5'
+ client_version = '1.1.6'
def __init__(self, api_key: str = None, server: str = None, client_options: ClientOptions = None, skip_version_check: bool = False):
self.api_key = api_key
@@ -5026,13 +5026,13 @@ def snapshot_streaming_data(self, dataset_id: str) -> DatasetVersion:
DatasetVersion: The new Dataset Version created by taking a snapshot of the current data in the streaming dataset."""
return self._call_api('snapshotStreamingData', 'POST', query_params={'datasetId': dataset_id}, body={}, parse_type=DatasetVersion)
- def set_dataset_column_data_type(self, dataset_id: str, column: str, data_type: str) -> Dataset:
+ def set_dataset_column_data_type(self, dataset_id: str, column: str, data_type: Union[DataType, str]) -> Dataset:
"""Set a Dataset's column type.
Args:
dataset_id (str): The unique ID associated with the dataset.
column (str): The name of the column.
- data_type (str): The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
+ data_type (DataType): The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
Returns:
Dataset: The dataset and schema after the data type has been set."""
@@ -6717,15 +6717,14 @@ def execute_agent_with_binary_data(self, deployment_token: str, deployment_id: s
deployment_id, deployment_token) if deployment_token else None
return self._call_api('executeAgentWithBinaryData', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, data={'arguments': json.dumps(arguments) if (arguments is not None and not isinstance(arguments, str)) else arguments, 'keywordArguments': json.dumps(keyword_arguments) if (keyword_arguments is not None and not isinstance(keyword_arguments, str)) else keyword_arguments, 'deploymentConversationId': json.dumps(deployment_conversation_id) if (deployment_conversation_id is not None and not isinstance(deployment_conversation_id, str)) else deployment_conversation_id, 'externalSessionId': json.dumps(external_session_id) if (external_session_id is not None and not isinstance(external_session_id, str)) else external_session_id}, parse_type=AgentDataExecutionResult, files=blobs, server_override=prediction_url, timeout=1500)
- def create_batch_prediction(self, deployment_id: str, table_name: str = None, name: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = False, output_format: str = None, output_location: str = None, database_connector_id: str = None, database_output_config: dict = None, refresh_schedule: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, input_feature_groups: dict = None) -> BatchPrediction:
+ def create_batch_prediction(self, deployment_id: str, table_name: str = None, name: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, batch_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = False, output_format: str = None, output_location: str = None, database_connector_id: str = None, database_output_config: dict = None, refresh_schedule: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, input_feature_groups: dict = None) -> BatchPrediction:
"""Creates a batch prediction job description for the given deployment.
Args:
deployment_id (str): Unique string identifier for the deployment.
table_name (str): Name of the feature group table to write the results of the batch prediction. Can only be specified if outputLocation and databaseConnectorId are not specified. If tableName is specified, the outputType will be enforced as CSV.
name (str): Name of the batch prediction job.
- global_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
- explanations (bool): If true, SHAP explanations will be provided for each prediction, if supported by the use case.
+ batch_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
output_format (str): Format of the batch prediction output (CSV or JSON).
output_location (str): Location to write the prediction results. Otherwise, results will be stored in Abacus.AI.
database_connector_id (str): Unique identifier of a Database Connection to write predictions to. Cannot be specified in conjunction with outputLocation.
@@ -6740,7 +6739,7 @@ def create_batch_prediction(self, deployment_id: str, table_name: str = None, na
Returns:
BatchPrediction: The batch prediction description."""
- return self._call_api('createBatchPrediction', 'POST', query_params={'deploymentId': deployment_id}, body={'tableName': table_name, 'name': name, 'globalPredictionArgs': global_prediction_args, 'explanations': explanations, 'outputFormat': output_format, 'outputLocation': output_location, 'databaseConnectorId': database_connector_id, 'databaseOutputConfig': database_output_config, 'refreshSchedule': refresh_schedule, 'csvInputPrefix': csv_input_prefix, 'csvPredictionPrefix': csv_prediction_prefix, 'csvExplanationsPrefix': csv_explanations_prefix, 'outputIncludesMetadata': output_includes_metadata, 'resultInputColumns': result_input_columns, 'inputFeatureGroups': input_feature_groups}, parse_type=BatchPrediction)
+ return self._call_api('createBatchPrediction', 'POST', query_params={'deploymentId': deployment_id}, body={'tableName': table_name, 'name': name, 'globalPredictionArgs': global_prediction_args, 'batchPredictionArgs': batch_prediction_args, 'explanations': explanations, 'outputFormat': output_format, 'outputLocation': output_location, 'databaseConnectorId': database_connector_id, 'databaseOutputConfig': database_output_config, 'refreshSchedule': refresh_schedule, 'csvInputPrefix': csv_input_prefix, 'csvPredictionPrefix': csv_prediction_prefix, 'csvExplanationsPrefix': csv_explanations_prefix, 'outputIncludesMetadata': output_includes_metadata, 'resultInputColumns': result_input_columns, 'inputFeatureGroups': input_feature_groups}, parse_type=BatchPrediction)
def start_batch_prediction(self, batch_prediction_id: str) -> BatchPredictionVersion:
"""Creates a new batch prediction version job for a given batch prediction job description.
@@ -6752,14 +6751,13 @@ def start_batch_prediction(self, batch_prediction_id: str) -> BatchPredictionVer
BatchPredictionVersion: The batch prediction version started by this method call."""
return self._call_api('startBatchPrediction', 'POST', query_params={}, body={'batchPredictionId': batch_prediction_id}, parse_type=BatchPredictionVersion)
- def update_batch_prediction(self, batch_prediction_id: str, deployment_id: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = None, output_format: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, name: str = None) -> BatchPrediction:
+ def update_batch_prediction(self, batch_prediction_id: str, deployment_id: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, batch_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = None, output_format: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, name: str = None) -> BatchPrediction:
"""Update a batch prediction job description.
Args:
batch_prediction_id (str): Unique identifier of the batch prediction.
deployment_id (str): Unique identifier of the deployment.
- global_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
- explanations (bool): If True, SHAP explanations for each prediction will be provided, if supported by the use case.
+ batch_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
output_format (str): If specified, sets the format of the batch prediction output (CSV or JSON).
csv_input_prefix (str): Prefix to prepend to the input columns, only applies when output format is CSV.
csv_prediction_prefix (str): Prefix to prepend to the prediction columns, only applies when output format is CSV.
@@ -6770,7 +6768,7 @@ def update_batch_prediction(self, batch_prediction_id: str, deployment_id: str =
Returns:
BatchPrediction: The batch prediction."""
- return self._call_api('updateBatchPrediction', 'POST', query_params={'deploymentId': deployment_id}, body={'batchPredictionId': batch_prediction_id, 'globalPredictionArgs': global_prediction_args, 'explanations': explanations, 'outputFormat': output_format, 'csvInputPrefix': csv_input_prefix, 'csvPredictionPrefix': csv_prediction_prefix, 'csvExplanationsPrefix': csv_explanations_prefix, 'outputIncludesMetadata': output_includes_metadata, 'resultInputColumns': result_input_columns, 'name': name}, parse_type=BatchPrediction)
+ return self._call_api('updateBatchPrediction', 'POST', query_params={'deploymentId': deployment_id}, body={'batchPredictionId': batch_prediction_id, 'globalPredictionArgs': global_prediction_args, 'batchPredictionArgs': batch_prediction_args, 'explanations': explanations, 'outputFormat': output_format, 'csvInputPrefix': csv_input_prefix, 'csvPredictionPrefix': csv_prediction_prefix, 'csvExplanationsPrefix': csv_explanations_prefix, 'outputIncludesMetadata': output_includes_metadata, 'resultInputColumns': result_input_columns, 'name': name}, parse_type=BatchPrediction)
def set_batch_prediction_file_connector_output(self, batch_prediction_id: str, output_format: str = None, output_location: str = None) -> BatchPrediction:
"""Updates the file connector output configuration of the batch prediction
@@ -6983,19 +6981,7 @@ def append_multiple_data(self, feature_group_id: str, streaming_token: str, data
streaming_token, feature_group_id=feature_group_id)
return self._call_api('appendMultipleData', 'POST', query_params={'streamingToken': streaming_token}, body={'featureGroupId': feature_group_id, 'data': data}, server_override=prediction_url)
- def upsert_data(self, feature_group_id: str, streaming_token: str = None, data: dict = None) -> FeatureGroupRow:
- """Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
-
- Args:
- feature_group_id (str): A unique string identifier of the streaming feature group to record data to.
- streaming_token (str): Optional streaming token for authenticating requests if upserting to streaming FG.
- data (dict): The data to record, in JSON format.
-
- Returns:
- FeatureGroupRow: The feature group row that was upserted."""
- return self._proxy_request('upsertData', 'POST', query_params={'streamingToken': streaming_token}, body={'featureGroupId': feature_group_id, 'data': data}, parse_type=FeatureGroupRow, is_sync=True)
-
- def upsert_online_data(self, feature_group_id: str, data: dict, streaming_token: str = None) -> FeatureGroupRow:
+ def upsert_data(self, feature_group_id: str, data: dict, streaming_token: str = None) -> FeatureGroupRow:
"""Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
Args:
@@ -7005,7 +6991,7 @@ def upsert_online_data(self, feature_group_id: str, data: dict, streaming_token:
Returns:
FeatureGroupRow: The feature group row that was upserted."""
- return self._proxy_request('upsertOnlineData', 'POST', query_params={'streamingToken': streaming_token}, body={'featureGroupId': feature_group_id, 'data': data}, parse_type=FeatureGroupRow, is_sync=True)
+ return self._proxy_request('upsertData', 'POST', query_params={'streamingToken': streaming_token}, body={'featureGroupId': feature_group_id, 'data': data}, parse_type=FeatureGroupRow, is_sync=True)
def delete_data(self, feature_group_id: str, primary_key: str):
"""Deletes a row from the feature group given the primary key
@@ -7764,7 +7750,7 @@ def create_external_application(self, deployment_id: str, name: str = None, logo
ExternalApplication: The newly created External Application."""
return self._call_api('createExternalApplication', 'POST', query_params={'deploymentId': deployment_id}, body={'name': name, 'logo': logo, 'theme': theme}, parse_type=ExternalApplication)
- def update_external_application(self, external_application_id: str, name: str = None, theme: dict = None, deployment_id: str = None) -> ExternalApplication:
+ def update_external_application(self, external_application_id: str, name: str = None, theme: dict = None, deployment_id: str = None, deployment_conversation_retention_hours: int = None, reset_retention_policy: bool = False) -> ExternalApplication:
"""Updates an External Application.
Args:
@@ -7772,10 +7758,12 @@ def update_external_application(self, external_application_id: str, name: str =
name (str): The name of the External Application.
theme (dict): The visual theme of the External Application.
deployment_id (str): The ID of the deployment to use.
+ deployment_conversation_retention_hours (int): The number of hours to retain the conversations for.
+ reset_retention_policy (bool): If true, the retention policy will be removed.
Returns:
ExternalApplication: The updated External Application."""
- return self._call_api('updateExternalApplication', 'POST', query_params={'deploymentId': deployment_id}, body={'externalApplicationId': external_application_id, 'name': name, 'theme': theme}, parse_type=ExternalApplication)
+ return self._call_api('updateExternalApplication', 'POST', query_params={'deploymentId': deployment_id}, body={'externalApplicationId': external_application_id, 'name': name, 'theme': theme, 'deploymentConversationRetentionHours': deployment_conversation_retention_hours, 'resetRetentionPolicy': reset_retention_policy}, parse_type=ExternalApplication)
def delete_external_application(self, external_application_id: str):
"""Deletes an External Application.
diff --git a/abacusai/dataset.py b/abacusai/dataset.py
index 66352ca39..2c4d107ca 100644
--- a/abacusai/dataset.py
+++ b/abacusai/dataset.py
@@ -1,6 +1,6 @@
from typing import Union
-from .api_class import DatasetConfig, DocumentProcessingConfig, ParsingConfig
+from .api_class import DatasetConfig, DataType, DocumentProcessingConfig, ParsingConfig
from .dataset_column import DatasetColumn
from .dataset_version import DatasetVersion
from .refresh_schedule import RefreshSchedule
@@ -152,13 +152,13 @@ def snapshot_streaming_data(self):
"""
return self.client.snapshot_streaming_data(self.dataset_id)
- def set_column_data_type(self, column: str, data_type: str):
+ def set_column_data_type(self, column: str, data_type: Union[dict, DataType]):
"""
Set a Dataset's column type.
Args:
column (str): The name of the column.
- data_type (str): The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
+ data_type (DataType): The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
Returns:
Dataset: The dataset and schema after the data type has been set.
diff --git a/abacusai/deployment.py b/abacusai/deployment.py
index 96186fb2a..290b18207 100644
--- a/abacusai/deployment.py
+++ b/abacusai/deployment.py
@@ -334,15 +334,14 @@ def get_conversation_response_with_binary_data(self, deployment_token: str, mess
"""
return self.client.get_conversation_response_with_binary_data(self.deployment_id, deployment_token, message, deployment_conversation_id, external_session_id, llm_name, num_completion_tokens, system_message, temperature, filter_key_values, search_score_cutoff, chat_config, ignore_documents, attachments)
- def create_batch_prediction(self, table_name: str = None, name: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = False, output_format: str = None, output_location: str = None, database_connector_id: str = None, database_output_config: dict = None, refresh_schedule: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, input_feature_groups: dict = None):
+ def create_batch_prediction(self, table_name: str = None, name: str = None, global_prediction_args: Union[dict, BatchPredictionArgs] = None, batch_prediction_args: Union[dict, BatchPredictionArgs] = None, explanations: bool = False, output_format: str = None, output_location: str = None, database_connector_id: str = None, database_output_config: dict = None, refresh_schedule: str = None, csv_input_prefix: str = None, csv_prediction_prefix: str = None, csv_explanations_prefix: str = None, output_includes_metadata: bool = None, result_input_columns: list = None, input_feature_groups: dict = None):
"""
Creates a batch prediction job description for the given deployment.
Args:
table_name (str): Name of the feature group table to write the results of the batch prediction. Can only be specified if outputLocation and databaseConnectorId are not specified. If tableName is specified, the outputType will be enforced as CSV.
name (str): Name of the batch prediction job.
- global_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
- explanations (bool): If true, SHAP explanations will be provided for each prediction, if supported by the use case.
+ batch_prediction_args (BatchPredictionArgs): Batch Prediction args specific to problem type.
output_format (str): Format of the batch prediction output (CSV or JSON).
output_location (str): Location to write the prediction results. Otherwise, results will be stored in Abacus.AI.
database_connector_id (str): Unique identifier of a Database Connection to write predictions to. Cannot be specified in conjunction with outputLocation.
@@ -358,7 +357,7 @@ def create_batch_prediction(self, table_name: str = None, name: str = None, glob
Returns:
BatchPrediction: The batch prediction description.
"""
- return self.client.create_batch_prediction(self.deployment_id, table_name, name, global_prediction_args, explanations, output_format, output_location, database_connector_id, database_output_config, refresh_schedule, csv_input_prefix, csv_prediction_prefix, csv_explanations_prefix, output_includes_metadata, result_input_columns, input_feature_groups)
+ return self.client.create_batch_prediction(self.deployment_id, table_name, name, global_prediction_args, batch_prediction_args, explanations, output_format, output_location, database_connector_id, database_output_config, refresh_schedule, csv_input_prefix, csv_prediction_prefix, csv_explanations_prefix, output_includes_metadata, result_input_columns, input_feature_groups)
def describe_feature_group_row_process_by_key(self, primary_key_value: str):
"""
diff --git a/abacusai/document_retriever_config.py b/abacusai/document_retriever_config.py
index 4a58867be..c4b695d60 100644
--- a/abacusai/document_retriever_config.py
+++ b/abacusai/document_retriever_config.py
@@ -11,18 +11,20 @@ class DocumentRetrieverConfig(AbstractApiClass):
chunkSize (int): The size of chunks for vector store, i.e., maximum number of words in the chunk.
chunkOverlapFraction (float): The fraction of overlap between two consecutive chunks.
textEncoder (str): The text encoder used to encode texts in the vector store.
+ scoreMultiplierColumn (str): The values in this metadata column are used to modify the relevance scores of returned chunks.
"""
- def __init__(self, client, chunkSize=None, chunkOverlapFraction=None, textEncoder=None):
+ def __init__(self, client, chunkSize=None, chunkOverlapFraction=None, textEncoder=None, scoreMultiplierColumn=None):
super().__init__(client, None)
self.chunk_size = chunkSize
self.chunk_overlap_fraction = chunkOverlapFraction
self.text_encoder = textEncoder
+ self.score_multiplier_column = scoreMultiplierColumn
self.deprecated_keys = {}
def __repr__(self):
- repr_dict = {f'chunk_size': repr(self.chunk_size), f'chunk_overlap_fraction': repr(
- self.chunk_overlap_fraction), f'text_encoder': repr(self.text_encoder)}
+ repr_dict = {f'chunk_size': repr(self.chunk_size), f'chunk_overlap_fraction': repr(self.chunk_overlap_fraction), f'text_encoder': repr(
+ self.text_encoder), f'score_multiplier_column': repr(self.score_multiplier_column)}
class_name = "DocumentRetrieverConfig"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -35,6 +37,6 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'chunk_size': self.chunk_size, 'chunk_overlap_fraction':
- self.chunk_overlap_fraction, 'text_encoder': self.text_encoder}
+ resp = {'chunk_size': self.chunk_size, 'chunk_overlap_fraction': self.chunk_overlap_fraction,
+ 'text_encoder': self.text_encoder, 'score_multiplier_column': self.score_multiplier_column}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
diff --git a/abacusai/external_application.py b/abacusai/external_application.py
index e292e5d5e..069ab4644 100644
--- a/abacusai/external_application.py
+++ b/abacusai/external_application.py
@@ -15,9 +15,10 @@ class ExternalApplication(AbstractApiClass):
userGroupIds (list): A list of App User Groups with access to this external application
useCase (str): Use Case of the project of this deployment
status (str): The status of the deployment.
+ deploymentConversationRetentionHours (int): The retention policy for the external application.
"""
- def __init__(self, client, name=None, externalApplicationId=None, deploymentId=None, logo=None, theme=None, userGroupIds=None, useCase=None, status=None):
+ def __init__(self, client, name=None, externalApplicationId=None, deploymentId=None, logo=None, theme=None, userGroupIds=None, useCase=None, status=None, deploymentConversationRetentionHours=None):
super().__init__(client, externalApplicationId)
self.name = name
self.external_application_id = externalApplicationId
@@ -27,11 +28,12 @@ def __init__(self, client, name=None, externalApplicationId=None, deploymentId=N
self.user_group_ids = userGroupIds
self.use_case = useCase
self.status = status
+ self.deployment_conversation_retention_hours = deploymentConversationRetentionHours
self.deprecated_keys = {}
def __repr__(self):
- repr_dict = {f'name': repr(self.name), f'external_application_id': repr(self.external_application_id), f'deployment_id': repr(self.deployment_id), f'logo': repr(
- self.logo), f'theme': repr(self.theme), f'user_group_ids': repr(self.user_group_ids), f'use_case': repr(self.use_case), f'status': repr(self.status)}
+ repr_dict = {f'name': repr(self.name), f'external_application_id': repr(self.external_application_id), f'deployment_id': repr(self.deployment_id), f'logo': repr(self.logo), f'theme': repr(
+ self.theme), f'user_group_ids': repr(self.user_group_ids), f'use_case': repr(self.use_case), f'status': repr(self.status), f'deployment_conversation_retention_hours': repr(self.deployment_conversation_retention_hours)}
class_name = "ExternalApplication"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -44,11 +46,11 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'name': self.name, 'external_application_id': self.external_application_id, 'deployment_id': self.deployment_id,
- 'logo': self.logo, 'theme': self.theme, 'user_group_ids': self.user_group_ids, 'use_case': self.use_case, 'status': self.status}
+ resp = {'name': self.name, 'external_application_id': self.external_application_id, 'deployment_id': self.deployment_id, 'logo': self.logo, 'theme': self.theme,
+ 'user_group_ids': self.user_group_ids, 'use_case': self.use_case, 'status': self.status, 'deployment_conversation_retention_hours': self.deployment_conversation_retention_hours}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
- def update(self, name: str = None, theme: dict = None, deployment_id: str = None):
+ def update(self, name: str = None, theme: dict = None, deployment_id: str = None, deployment_conversation_retention_hours: int = None, reset_retention_policy: bool = False):
"""
Updates an External Application.
@@ -56,11 +58,13 @@ def update(self, name: str = None, theme: dict = None, deployment_id: str = None
name (str): The name of the External Application.
theme (dict): The visual theme of the External Application.
deployment_id (str): The ID of the deployment to use.
+ deployment_conversation_retention_hours (int): The number of hours to retain the conversations for.
+ reset_retention_policy (bool): If true, the retention policy will be removed.
Returns:
ExternalApplication: The updated External Application.
"""
- return self.client.update_external_application(self.external_application_id, name, theme, deployment_id)
+ return self.client.update_external_application(self.external_application_id, name, theme, deployment_id, deployment_conversation_retention_hours, reset_retention_policy)
def refresh(self):
"""
diff --git a/abacusai/feature_group.py b/abacusai/feature_group.py
index fe36b166e..21c19ac27 100644
--- a/abacusai/feature_group.py
+++ b/abacusai/feature_group.py
@@ -1049,20 +1049,7 @@ def append_multiple_data(self, streaming_token: str, data: list):
"""
return self.client.append_multiple_data(self.feature_group_id, streaming_token, data)
- def upsert_data(self, streaming_token: str = None, data: dict = None):
- """
- Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
-
- Args:
- streaming_token (str): Optional streaming token for authenticating requests if upserting to streaming FG.
- data (dict): The data to record, in JSON format.
-
- Returns:
- FeatureGroupRow: The feature group row that was upserted.
- """
- return self.client.upsert_data(self.feature_group_id, streaming_token, data)
-
- def upsert_online_data(self, data: dict, streaming_token: str = None):
+ def upsert_data(self, data: dict, streaming_token: str = None):
"""
Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
@@ -1073,7 +1060,7 @@ def upsert_online_data(self, data: dict, streaming_token: str = None):
Returns:
FeatureGroupRow: The feature group row that was upserted.
"""
- return self.client.upsert_online_data(self.feature_group_id, data, streaming_token)
+ return self.client.upsert_data(self.feature_group_id, data, streaming_token)
def delete_data(self, primary_key: str):
"""
diff --git a/abacusai/feature_group_export.py b/abacusai/feature_group_export.py
index d2769efef..47780ea53 100644
--- a/abacusai/feature_group_export.py
+++ b/abacusai/feature_group_export.py
@@ -140,7 +140,3 @@ def get_status(self):
str: A string describing the status of a feature group export (pending, complete, etc.).
"""
return self.describe().status
-
- # to be deleted
- def get_results(self):
- return self.client.get_export_result(self.feature_group_export_id)
diff --git a/abacusai/pipeline.py b/abacusai/pipeline.py
index be5b16e73..6bb5f7b9d 100644
--- a/abacusai/pipeline.py
+++ b/abacusai/pipeline.py
@@ -1,3 +1,4 @@
+from .api_class import PythonFunctionArgument
from .code_source import CodeSource
from .pipeline_reference import PipelineReference
from .pipeline_step import PipelineStep
@@ -14,7 +15,6 @@ class Pipeline(AbstractApiClass):
pipelineName (str): The name of the pipeline this step is a part of.
pipelineId (str): The reference to the pipeline this step belongs to.
createdAt (str): The date and time which the pipeline was created.
- pipelineVariableMappings (dict): A description of the function variables into the pipeline.
notebookId (str): The reference to the notebook this pipeline belongs to.
cron (str): A cron-style string that describes when this refresh policy is to be executed in UTC
nextRunTime (str): The next time this pipeline will be run.
@@ -27,12 +27,11 @@ class Pipeline(AbstractApiClass):
codeSource (CodeSource): information on the source code
"""
- def __init__(self, client, pipelineName=None, pipelineId=None, createdAt=None, pipelineVariableMappings=None, notebookId=None, cron=None, nextRunTime=None, isProd=None, warning=None, createdBy=None, steps={}, pipelineReferences={}, latestPipelineVersion={}, codeSource={}):
+ def __init__(self, client, pipelineName=None, pipelineId=None, createdAt=None, notebookId=None, cron=None, nextRunTime=None, isProd=None, warning=None, createdBy=None, steps={}, pipelineReferences={}, latestPipelineVersion={}, codeSource={}, pipelineVariableMappings={}):
super().__init__(client, pipelineId)
self.pipeline_name = pipelineName
self.pipeline_id = pipelineId
self.created_at = createdAt
- self.pipeline_variable_mappings = pipelineVariableMappings
self.notebook_id = notebookId
self.cron = cron
self.next_run_time = nextRunTime
@@ -45,11 +44,13 @@ def __init__(self, client, pipelineName=None, pipelineId=None, createdAt=None, p
self.latest_pipeline_version = client._build_class(
PipelineVersion, latestPipelineVersion)
self.code_source = client._build_class(CodeSource, codeSource)
+ self.pipeline_variable_mappings = client._build_class(
+ PythonFunctionArgument, pipelineVariableMappings)
self.deprecated_keys = {}
def __repr__(self):
- repr_dict = {f'pipeline_name': repr(self.pipeline_name), f'pipeline_id': repr(self.pipeline_id), f'created_at': repr(self.created_at), f'pipeline_variable_mappings': repr(self.pipeline_variable_mappings), f'notebook_id': repr(self.notebook_id), f'cron': repr(self.cron), f'next_run_time': repr(
- self.next_run_time), f'is_prod': repr(self.is_prod), f'warning': repr(self.warning), f'created_by': repr(self.created_by), f'steps': repr(self.steps), f'pipeline_references': repr(self.pipeline_references), f'latest_pipeline_version': repr(self.latest_pipeline_version), f'code_source': repr(self.code_source)}
+ repr_dict = {f'pipeline_name': repr(self.pipeline_name), f'pipeline_id': repr(self.pipeline_id), f'created_at': repr(self.created_at), f'notebook_id': repr(self.notebook_id), f'cron': repr(self.cron), f'next_run_time': repr(self.next_run_time), f'is_prod': repr(self.is_prod), f'warning': repr(
+ self.warning), f'created_by': repr(self.created_by), f'steps': repr(self.steps), f'pipeline_references': repr(self.pipeline_references), f'latest_pipeline_version': repr(self.latest_pipeline_version), f'code_source': repr(self.code_source), f'pipeline_variable_mappings': repr(self.pipeline_variable_mappings)}
class_name = "Pipeline"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -62,8 +63,8 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'pipeline_name': self.pipeline_name, 'pipeline_id': self.pipeline_id, 'created_at': self.created_at, 'pipeline_variable_mappings': self.pipeline_variable_mappings, 'notebook_id': self.notebook_id, 'cron': self.cron, 'next_run_time': self.next_run_time, 'is_prod': self.is_prod, 'warning': self.warning,
- 'created_by': self.created_by, 'steps': self._get_attribute_as_dict(self.steps), 'pipeline_references': self._get_attribute_as_dict(self.pipeline_references), 'latest_pipeline_version': self._get_attribute_as_dict(self.latest_pipeline_version), 'code_source': self._get_attribute_as_dict(self.code_source)}
+ resp = {'pipeline_name': self.pipeline_name, 'pipeline_id': self.pipeline_id, 'created_at': self.created_at, 'notebook_id': self.notebook_id, 'cron': self.cron, 'next_run_time': self.next_run_time, 'is_prod': self.is_prod, 'warning': self.warning, 'created_by': self.created_by, 'steps': self._get_attribute_as_dict(
+ self.steps), 'pipeline_references': self._get_attribute_as_dict(self.pipeline_references), 'latest_pipeline_version': self._get_attribute_as_dict(self.latest_pipeline_version), 'code_source': self._get_attribute_as_dict(self.code_source), 'pipeline_variable_mappings': self._get_attribute_as_dict(self.pipeline_variable_mappings)}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
def refresh(self):
diff --git a/abacusai/pipeline_version.py b/abacusai/pipeline_version.py
index 29e40f6ba..d4ca29268 100644
--- a/abacusai/pipeline_version.py
+++ b/abacusai/pipeline_version.py
@@ -1,3 +1,4 @@
+from .api_class import PythonFunctionArgument
from .code_source import CodeSource
from .pipeline_step_version import PipelineStepVersion
from .return_class import AbstractApiClass
@@ -17,12 +18,11 @@ class PipelineVersion(AbstractApiClass):
completedAt (str): The date and time which this pipeline version was updated.
status (str): The status of the pipeline version.
error (str): The relevant error, if the status is FAILED.
- pipelineVariableMappings (dict): A description of the function variables into the pipeline.
stepVersions (PipelineStepVersion): A list of the pipeline step versions.
codeSource (CodeSource): information on the source code
"""
- def __init__(self, client, pipelineName=None, pipelineId=None, pipelineVersion=None, createdAt=None, updatedAt=None, completedAt=None, status=None, error=None, pipelineVariableMappings=None, stepVersions={}, codeSource={}):
+ def __init__(self, client, pipelineName=None, pipelineId=None, pipelineVersion=None, createdAt=None, updatedAt=None, completedAt=None, status=None, error=None, stepVersions={}, codeSource={}, pipelineVariableMappings={}):
super().__init__(client, pipelineVersion)
self.pipeline_name = pipelineName
self.pipeline_id = pipelineId
@@ -32,15 +32,16 @@ def __init__(self, client, pipelineName=None, pipelineId=None, pipelineVersion=N
self.completed_at = completedAt
self.status = status
self.error = error
- self.pipeline_variable_mappings = pipelineVariableMappings
self.step_versions = client._build_class(
PipelineStepVersion, stepVersions)
self.code_source = client._build_class(CodeSource, codeSource)
+ self.pipeline_variable_mappings = client._build_class(
+ PythonFunctionArgument, pipelineVariableMappings)
self.deprecated_keys = {}
def __repr__(self):
repr_dict = {f'pipeline_name': repr(self.pipeline_name), f'pipeline_id': repr(self.pipeline_id), f'pipeline_version': repr(self.pipeline_version), f'created_at': repr(self.created_at), f'updated_at': repr(self.updated_at), f'completed_at': repr(
- self.completed_at), f'status': repr(self.status), f'error': repr(self.error), f'pipeline_variable_mappings': repr(self.pipeline_variable_mappings), f'step_versions': repr(self.step_versions), f'code_source': repr(self.code_source)}
+ self.completed_at), f'status': repr(self.status), f'error': repr(self.error), f'step_versions': repr(self.step_versions), f'code_source': repr(self.code_source), f'pipeline_variable_mappings': repr(self.pipeline_variable_mappings)}
class_name = "PipelineVersion"
repr_str = ',\n '.join([f'{key}={value}' for key, value in repr_dict.items(
) if getattr(self, key, None) is not None and key not in self.deprecated_keys])
@@ -53,8 +54,8 @@ def to_dict(self):
Returns:
dict: The dict value representation of the class parameters
"""
- resp = {'pipeline_name': self.pipeline_name, 'pipeline_id': self.pipeline_id, 'pipeline_version': self.pipeline_version, 'created_at': self.created_at, 'updated_at': self.updated_at, 'completed_at': self.completed_at,
- 'status': self.status, 'error': self.error, 'pipeline_variable_mappings': self.pipeline_variable_mappings, 'step_versions': self._get_attribute_as_dict(self.step_versions), 'code_source': self._get_attribute_as_dict(self.code_source)}
+ resp = {'pipeline_name': self.pipeline_name, 'pipeline_id': self.pipeline_id, 'pipeline_version': self.pipeline_version, 'created_at': self.created_at, 'updated_at': self.updated_at, 'completed_at': self.completed_at, 'status': self.status,
+ 'error': self.error, 'step_versions': self._get_attribute_as_dict(self.step_versions), 'code_source': self._get_attribute_as_dict(self.code_source), 'pipeline_variable_mappings': self._get_attribute_as_dict(self.pipeline_variable_mappings)}
return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}
def refresh(self):
diff --git a/abacusai/project.py b/abacusai/project.py
index 732934b8f..749040bc6 100644
--- a/abacusai/project.py
+++ b/abacusai/project.py
@@ -643,28 +643,6 @@ def list_document_retrievers(self, limit: int = 100, start_after_id: str = None)
"""
return self.client.list_document_retrievers(self.project_id, limit, start_after_id)
- def attach_dataset(self, dataset_id, project_dataset_type):
- """
- Attaches dataset to the project.
-
- Args:
- dataset_id (unique string identifier): A unique identifier for the dataset.
- project_dataset_type (enum of type string): The unique use case specific dataset type that might be required or recommended for the specific use case.
-
- Returns:
- Schema: The schema of the attached dataset.
- """
- return self.client.attach_dataset_to_project(dataset_id, self.project_id, project_dataset_type)
-
- def remove_dataset(self, dataset_id):
- """
- Removes dataset from the project.
-
- Args:
- dataset_id (unique string identifier): A unique identifier for the dataset.
- """
- return self.client.remove_dataset_from_project(dataset_id, self.project_id)
-
def create_model_from_functions(self, train_function: callable, predict_function: callable = None, training_input_tables: list = None, predict_many_function: callable = None, initialize_function: callable = None, cpu_size: str = None, memory: int = None, training_config: dict = None, exclusive_run: bool = False):
"""
Creates a model using python.
diff --git a/abacusai/public.pem b/abacusai/public.pem
index 21352214d..2c1ac3929 100644
--- a/abacusai/public.pem
+++ b/abacusai/public.pem
@@ -1,5 +1,5 @@
-----BEGIN RSA PUBLIC KEY-----
-MIGJAoGBAMIl9DR1FJ2VDzIn4ywL93//RDkAQD+ll92RSmqJ7FpwJP0Uzd+a5wvC
-4n9Y7xRvDuLF88qVDwZx4/SCdn8E8QKg1Avn5j8WF3SDjYH/3oLOHHyUDX3zYYsN
-5RCfwHb2ErmvtFvZf+6i/diSTUxypy7+szQnDB2y2FbbSMMGnHwbAgMBAAE=
+MIGJAoGBAJDNVZuidY2kTpX1JCqE/T4cVZ3NVjm29QMrkPqsvgNS1joltn0wCGi/
+cw/TLAgvbSIf3YiYRPKGTHhVxhIS6lWFc9O8WaD+8eWW/Mv/m0QWUr6RW3bCYArd
+gyyRURjK4cFGkHzpnFkwc7424MVj8FliJVbDg7W6PuBJAuduC7FtAgMBAAE=
-----END RSA PUBLIC KEY-----
diff --git a/docs/_sources/autoapi/abacusai/api_class/batch_prediction/index.rst.txt b/docs/_sources/autoapi/abacusai/api_class/batch_prediction/index.rst.txt
index 52d494a37..96c9ad382 100644
--- a/docs/_sources/autoapi/abacusai/api_class/batch_prediction/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/api_class/batch_prediction/index.rst.txt
@@ -22,6 +22,7 @@ Classes
abacusai.api_class.batch_prediction.SentenceBoundaryDetectionBatchPredictionArgs
abacusai.api_class.batch_prediction.ThemeAnalysisBatchPredictionArgs
abacusai.api_class.batch_prediction.ChatLLMBatchPredictionArgs
+ abacusai.api_class.batch_prediction.TrainablePlugAndPlayBatchPredictionArgs
abacusai.api_class.batch_prediction._BatchPredictionArgsFactory
@@ -66,6 +67,8 @@ Classes
:type for_eval: bool
:param threshold: The threshold for detecting an anomaly. Range: [0.8, 0.99]
:type threshold: float
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
.. py:attribute:: for_eval
:type: bool
@@ -77,6 +80,11 @@ Classes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -100,8 +108,10 @@ Classes
:type forecasting_horizon: int
:param item_attributes_to_include_in_the_result: List of columns to include in the prediction output.
:type item_attributes_to_include_in_the_result: list
- :param explain_predictions: If True, explain predictions for the forecast.
+ :param explain_predictions: If True, calculates explanations for the forecasted values along with predictions.
:type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -138,6 +148,11 @@ Classes
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -235,6 +250,10 @@ Classes
:type bound_label: str
:param output_columns: A list of column names to include in the prediction result.
:type output_columns: list
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -286,6 +305,16 @@ Classes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -408,6 +437,30 @@ Classes
+.. py:class:: TrainablePlugAndPlayBatchPredictionArgs
+
+
+ Bases: :py:obj:`BatchPredictionArgs`
+
+ Batch Prediction Config for the TrainablePlugAndPlay problem type
+
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
+
+ .. py:attribute:: for_eval
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
+ .. py:method:: __post_init__()
+
+
+
.. py:class:: _BatchPredictionArgsFactory
diff --git a/docs/_sources/autoapi/abacusai/api_class/document_retriever/index.rst.txt b/docs/_sources/autoapi/abacusai/api_class/document_retriever/index.rst.txt
index 280083e90..9391e963f 100644
--- a/docs/_sources/autoapi/abacusai/api_class/document_retriever/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/api_class/document_retriever/index.rst.txt
@@ -33,6 +33,8 @@ Classes
:type text_encoder: VectorStoreTextEncoder
:param chunk_size_factors: Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
:type chunk_size_factors: list
+ :param score_multiplier_column: If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
+ :type score_multiplier_column: str
.. py:attribute:: chunk_size
:type: int
@@ -54,6 +56,11 @@ Classes
+ .. py:attribute:: score_multiplier_column
+ :type: str
+
+
+
.. py:class:: DocumentRetrieverConfig
diff --git a/docs/_sources/autoapi/abacusai/api_class/enums/index.rst.txt b/docs/_sources/autoapi/abacusai/api_class/enums/index.rst.txt
index f4d27dceb..017f1788e 100644
--- a/docs/_sources/autoapi/abacusai/api_class/enums/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/api_class/enums/index.rst.txt
@@ -61,6 +61,7 @@ Classes
abacusai.api_class.enums.EvalArtifactType
abacusai.api_class.enums.FieldDescriptorType
abacusai.api_class.enums.OcrMode
+ abacusai.api_class.enums.DataType
@@ -1544,6 +1545,11 @@ Classes
+ .. py:attribute:: MICROSOFTAUTH
+ :value: 'MICROSOFTAUTH'
+
+
+
.. py:class:: PythonFunctionArgumentType
@@ -2110,3 +2116,62 @@ Classes
+.. py:class:: DataType
+
+
+ Bases: :py:obj:`ApiEnum`
+
+ Generic enumeration.
+
+ Derive from this class to define new enumerations.
+
+ .. py:attribute:: INTEGER
+ :value: 'integer'
+
+
+
+ .. py:attribute:: FLOAT
+ :value: 'float'
+
+
+
+ .. py:attribute:: STRING
+ :value: 'string'
+
+
+
+ .. py:attribute:: DATE
+ :value: 'date'
+
+
+
+ .. py:attribute:: DATETIME
+ :value: 'datetime'
+
+
+
+ .. py:attribute:: BOOLEAN
+ :value: 'boolean'
+
+
+
+ .. py:attribute:: LIST
+ :value: 'list'
+
+
+
+ .. py:attribute:: STRUCT
+ :value: 'struct'
+
+
+
+ .. py:attribute:: NULL
+ :value: 'null'
+
+
+
+ .. py:method:: from_str(value)
+ :classmethod:
+
+
+
diff --git a/docs/_sources/autoapi/abacusai/api_class/index.rst.txt b/docs/_sources/autoapi/abacusai/api_class/index.rst.txt
index 88cd4130e..e42d4c41b 100644
--- a/docs/_sources/autoapi/abacusai/api_class/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/api_class/index.rst.txt
@@ -52,6 +52,7 @@ Classes
abacusai.api_class.SentenceBoundaryDetectionBatchPredictionArgs
abacusai.api_class.ThemeAnalysisBatchPredictionArgs
abacusai.api_class.ChatLLMBatchPredictionArgs
+ abacusai.api_class.TrainablePlugAndPlayBatchPredictionArgs
abacusai.api_class._BatchPredictionArgsFactory
abacusai.api_class.ApiClass
abacusai.api_class.BlobInput
@@ -125,6 +126,7 @@ Classes
abacusai.api_class.EvalArtifactType
abacusai.api_class.FieldDescriptorType
abacusai.api_class.OcrMode
+ abacusai.api_class.DataType
abacusai.api_class.ApiClass
abacusai.api_class._ApiClassFactory
abacusai.api_class.SamplingConfig
@@ -498,6 +500,8 @@ Classes
:type for_eval: bool
:param threshold: The threshold for detecting an anomaly. Range: [0.8, 0.99]
:type threshold: float
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
.. py:attribute:: for_eval
:type: bool
@@ -509,6 +513,11 @@ Classes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -532,8 +541,10 @@ Classes
:type forecasting_horizon: int
:param item_attributes_to_include_in_the_result: List of columns to include in the prediction output.
:type item_attributes_to_include_in_the_result: list
- :param explain_predictions: If True, explain predictions for the forecast.
+ :param explain_predictions: If True, calculates explanations for the forecasted values along with predictions.
:type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -570,6 +581,11 @@ Classes
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -667,6 +683,10 @@ Classes
:type bound_label: str
:param output_columns: A list of column names to include in the prediction result.
:type output_columns: list
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -718,6 +738,16 @@ Classes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -840,6 +870,30 @@ Classes
+.. py:class:: TrainablePlugAndPlayBatchPredictionArgs
+
+
+ Bases: :py:obj:`BatchPredictionArgs`
+
+ Batch Prediction Config for the TrainablePlugAndPlay problem type
+
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
+
+ .. py:attribute:: for_eval
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
+ .. py:method:: __post_init__()
+
+
+
.. py:class:: _BatchPredictionArgsFactory
@@ -1661,6 +1715,8 @@ Classes
:type text_encoder: VectorStoreTextEncoder
:param chunk_size_factors: Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
:type chunk_size_factors: list
+ :param score_multiplier_column: If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
+ :type score_multiplier_column: str
.. py:attribute:: chunk_size
:type: int
@@ -1682,6 +1738,11 @@ Classes
+ .. py:attribute:: score_multiplier_column
+ :type: str
+
+
+
.. py:class:: DocumentRetrieverConfig
@@ -3170,6 +3231,11 @@ Classes
+ .. py:attribute:: MICROSOFTAUTH
+ :value: 'MICROSOFTAUTH'
+
+
+
.. py:class:: PythonFunctionArgumentType
@@ -3736,6 +3802,65 @@ Classes
+.. py:class:: DataType
+
+
+ Bases: :py:obj:`ApiEnum`
+
+ Generic enumeration.
+
+ Derive from this class to define new enumerations.
+
+ .. py:attribute:: INTEGER
+ :value: 'integer'
+
+
+
+ .. py:attribute:: FLOAT
+ :value: 'float'
+
+
+
+ .. py:attribute:: STRING
+ :value: 'string'
+
+
+
+ .. py:attribute:: DATE
+ :value: 'date'
+
+
+
+ .. py:attribute:: DATETIME
+ :value: 'datetime'
+
+
+
+ .. py:attribute:: BOOLEAN
+ :value: 'boolean'
+
+
+
+ .. py:attribute:: LIST
+ :value: 'list'
+
+
+
+ .. py:attribute:: STRUCT
+ :value: 'struct'
+
+
+
+ .. py:attribute:: NULL
+ :value: 'null'
+
+
+
+ .. py:method:: from_str(value)
+ :classmethod:
+
+
+
.. py:class:: ApiClass
@@ -5337,6 +5462,8 @@ Classes
:type disable_data_summarization: bool
:param search_score_cutoff: Minimum search score to consider a document as a valid search result.
:type search_score_cutoff: float
+ :param database_connector_id: Database connector id to use for the chatllm.
+ :type database_connector_id: str
.. py:attribute:: document_retrievers
:type: List[str]
@@ -5408,6 +5535,11 @@ Classes
+ .. py:attribute:: database_connector_id
+ :type: str
+
+
+
.. py:method:: __post_init__()
diff --git a/docs/_sources/autoapi/abacusai/api_class/model/index.rst.txt b/docs/_sources/autoapi/abacusai/api_class/model/index.rst.txt
index e51c62319..ef9f548d0 100644
--- a/docs/_sources/autoapi/abacusai/api_class/model/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/api_class/model/index.rst.txt
@@ -1268,6 +1268,8 @@ Classes
:type disable_data_summarization: bool
:param search_score_cutoff: Minimum search score to consider a document as a valid search result.
:type search_score_cutoff: float
+ :param database_connector_id: Database connector id to use for the chatllm.
+ :type database_connector_id: str
.. py:attribute:: document_retrievers
:type: List[str]
@@ -1339,6 +1341,11 @@ Classes
+ .. py:attribute:: database_connector_id
+ :type: str
+
+
+
.. py:method:: __post_init__()
diff --git a/docs/_sources/autoapi/abacusai/batch_prediction/index.rst.txt b/docs/_sources/autoapi/abacusai/batch_prediction/index.rst.txt
index c4a3e771a..a76d45c57 100644
--- a/docs/_sources/autoapi/abacusai/batch_prediction/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/batch_prediction/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: BatchPrediction(client, batchPredictionId=None, createdAt=None, name=None, deploymentId=None, fileConnectorOutputLocation=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, outputFeatureGroupId=None, featureGroupTableName=None, outputFeatureGroupTableName=None, summaryFeatureGroupTableName=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorId=None, modelVersion=None, algorithm=None, batchInputs={}, latestBatchPredictionVersion={}, refreshSchedules={}, inputFeatureGroups={}, globalPredictionArgs={})
+.. py:class:: BatchPrediction(client, batchPredictionId=None, createdAt=None, name=None, deploymentId=None, fileConnectorOutputLocation=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, outputFeatureGroupId=None, featureGroupTableName=None, outputFeatureGroupTableName=None, summaryFeatureGroupTableName=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorId=None, modelVersion=None, algorithm=None, batchInputs={}, latestBatchPredictionVersion={}, refreshSchedules={}, inputFeatureGroups={}, globalPredictionArgs={}, batchPredictionArgs={})
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -40,7 +40,7 @@ Classes
:type databaseConnectorId: str
:param databaseOutputConfiguration: Contains information about where the batch predictions are written to.
:type databaseOutputConfiguration: dict
- :param explanations: If true, explanations for each prediction will be created.
+ :param explanations:
:type explanations: bool
:param fileOutputFormat: The format of the batch prediction output (CSV or JSON).
:type fileOutputFormat: str
@@ -48,7 +48,7 @@ Classes
:type connectorType: str
:param legacyInputLocation: The location of the input data.
:type legacyInputLocation: str
- :param outputFeatureGroupId: The BP output feature group id if applicable
+ :param outputFeatureGroupId: The Batch Prediction output feature group ID if applicable
:type outputFeatureGroupId: str
:param featureGroupTableName: The table name of the Batch Prediction output feature group.
:type featureGroupTableName: str
@@ -137,16 +137,14 @@ Classes
:rtype: list[BatchPredictionVersion]
- .. py:method:: update(deployment_id = None, global_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
+ .. py:method:: update(deployment_id = None, global_prediction_args = None, batch_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
Update a batch prediction job description.
:param deployment_id: Unique identifier of the deployment.
:type deployment_id: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If True, SHAP explanations for each prediction will be provided, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: If specified, sets the format of the batch prediction output (CSV or JSON).
:type output_format: str
:param csv_input_prefix: Prefix to prepend to the input columns, only applies when output format is CSV.
diff --git a/docs/_sources/autoapi/abacusai/batch_prediction_version/index.rst.txt b/docs/_sources/autoapi/abacusai/batch_prediction_version/index.rst.txt
index e7d900498..b76d072ad 100644
--- a/docs/_sources/autoapi/abacusai/batch_prediction_version/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/batch_prediction_version/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: BatchPredictionVersion(client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupId=None, outputFeatureGroupVersion=None, outputFeatureGroupTableName=None, batchPredictionWarnings=None, batchInputs={}, inputFeatureGroups={}, globalPredictionArgs={})
+.. py:class:: BatchPredictionVersion(client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupId=None, outputFeatureGroupVersion=None, outputFeatureGroupTableName=None, batchPredictionWarnings=None, batchInputs={}, inputFeatureGroups={}, globalPredictionArgs={}, batchPredictionArgs={})
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -54,7 +54,7 @@ Classes
:type databaseConnectorId: str
:param databaseOutputConfiguration: Contains information about where the batch predictions are written to
:type databaseOutputConfiguration: dict
- :param explanations: If true, explanations for each prediction were created
+ :param explanations:
:type explanations: bool
:param fileConnectorOutputLocation: Contains information about where the batch predictions are written to
:type fileConnectorOutputLocation: str
@@ -90,11 +90,11 @@ Classes
:type algoName: str
:param algorithm: The algorithm that is currently deployed.
:type algorithm: str
- :param outputFeatureGroupId: The BP output feature group id if applicable
+ :param outputFeatureGroupId: The Batch Prediction output feature group ID if applicable
:type outputFeatureGroupId: str
- :param outputFeatureGroupVersion: The BP output feature group version if applicable
+ :param outputFeatureGroupVersion: The Batch Prediction output feature group version if applicable
:type outputFeatureGroupVersion: str
- :param outputFeatureGroupTableName: The BP output feature group name if applicable
+ :param outputFeatureGroupTableName: The Batch Prediction output feature group name if applicable
:type outputFeatureGroupTableName: str
:param batchPredictionWarnings: Relevant warnings if any issues are found
:type batchPredictionWarnings: str
diff --git a/docs/_sources/autoapi/abacusai/client/index.rst.txt b/docs/_sources/autoapi/abacusai/client/index.rst.txt
index 80cc570e0..7e25cc3bd 100644
--- a/docs/_sources/autoapi/abacusai/client/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/client/index.rst.txt
@@ -487,7 +487,7 @@ Attributes
:type skip_version_check: bool
.. py:attribute:: client_version
- :value: '1.1.5'
+ :value: '1.1.6'
@@ -5084,7 +5084,7 @@ Attributes
:param column: The name of the column.
:type column: str
:param data_type: The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
- :type data_type: str
+ :type data_type: DataType
:returns: The dataset and schema after the data type has been set.
:rtype: Dataset
@@ -7267,7 +7267,7 @@ Attributes
:rtype: AgentDataExecutionResult
- .. py:method:: create_batch_prediction(deployment_id, table_name = None, name = None, global_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
+ .. py:method:: create_batch_prediction(deployment_id, table_name = None, name = None, global_prediction_args = None, batch_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
Creates a batch prediction job description for the given deployment.
@@ -7277,10 +7277,8 @@ Attributes
:type table_name: str
:param name: Name of the batch prediction job.
:type name: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If true, SHAP explanations will be provided for each prediction, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: Format of the batch prediction output (CSV or JSON).
:type output_format: str
:param output_location: Location to write the prediction results. Otherwise, results will be stored in Abacus.AI.
@@ -7319,7 +7317,7 @@ Attributes
:rtype: BatchPredictionVersion
- .. py:method:: update_batch_prediction(batch_prediction_id, deployment_id = None, global_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
+ .. py:method:: update_batch_prediction(batch_prediction_id, deployment_id = None, global_prediction_args = None, batch_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
Update a batch prediction job description.
@@ -7327,10 +7325,8 @@ Attributes
:type batch_prediction_id: str
:param deployment_id: Unique identifier of the deployment.
:type deployment_id: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If True, SHAP explanations for each prediction will be provided, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: If specified, sets the format of the batch prediction output (CSV or JSON).
:type output_format: str
:param csv_input_prefix: Prefix to prepend to the input columns, only applies when output format is CSV.
@@ -7610,22 +7606,7 @@ Attributes
:type data: list
- .. py:method:: upsert_data(feature_group_id, streaming_token = None, data = None)
-
- Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
-
- :param feature_group_id: A unique string identifier of the streaming feature group to record data to.
- :type feature_group_id: str
- :param streaming_token: Optional streaming token for authenticating requests if upserting to streaming FG.
- :type streaming_token: str
- :param data: The data to record, in JSON format.
- :type data: dict
-
- :returns: The feature group row that was upserted.
- :rtype: FeatureGroupRow
-
-
- .. py:method:: upsert_online_data(feature_group_id, data, streaming_token = None)
+ .. py:method:: upsert_data(feature_group_id, data, streaming_token = None)
Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
@@ -8599,7 +8580,7 @@ Attributes
:rtype: ExternalApplication
- .. py:method:: update_external_application(external_application_id, name = None, theme = None, deployment_id = None)
+ .. py:method:: update_external_application(external_application_id, name = None, theme = None, deployment_id = None, deployment_conversation_retention_hours = None, reset_retention_policy = False)
Updates an External Application.
@@ -8611,6 +8592,10 @@ Attributes
:type theme: dict
:param deployment_id: The ID of the deployment to use.
:type deployment_id: str
+ :param deployment_conversation_retention_hours: The number of hours to retain the conversations for.
+ :type deployment_conversation_retention_hours: int
+ :param reset_retention_policy: If true, the retention policy will be removed.
+ :type reset_retention_policy: bool
:returns: The updated External Application.
:rtype: ExternalApplication
diff --git a/docs/_sources/autoapi/abacusai/dataset/index.rst.txt b/docs/_sources/autoapi/abacusai/dataset/index.rst.txt
index feb858401..f39a3add0 100644
--- a/docs/_sources/autoapi/abacusai/dataset/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/dataset/index.rst.txt
@@ -158,7 +158,7 @@ Classes
:param column: The name of the column.
:type column: str
:param data_type: The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
- :type data_type: str
+ :type data_type: DataType
:returns: The dataset and schema after the data type has been set.
:rtype: Dataset
diff --git a/docs/_sources/autoapi/abacusai/deployment/index.rst.txt b/docs/_sources/autoapi/abacusai/deployment/index.rst.txt
index 84ab328ee..470ef6d7e 100644
--- a/docs/_sources/autoapi/abacusai/deployment/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/deployment/index.rst.txt
@@ -351,7 +351,7 @@ Classes
:type attachments: None
- .. py:method:: create_batch_prediction(table_name = None, name = None, global_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
+ .. py:method:: create_batch_prediction(table_name = None, name = None, global_prediction_args = None, batch_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
Creates a batch prediction job description for the given deployment.
@@ -359,10 +359,8 @@ Classes
:type table_name: str
:param name: Name of the batch prediction job.
:type name: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If true, SHAP explanations will be provided for each prediction, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: Format of the batch prediction output (CSV or JSON).
:type output_format: str
:param output_location: Location to write the prediction results. Otherwise, results will be stored in Abacus.AI.
diff --git a/docs/_sources/autoapi/abacusai/document_retriever_config/index.rst.txt b/docs/_sources/autoapi/abacusai/document_retriever_config/index.rst.txt
index 90b3ab5e2..b15d03f73 100644
--- a/docs/_sources/autoapi/abacusai/document_retriever_config/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/document_retriever_config/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: DocumentRetrieverConfig(client, chunkSize=None, chunkOverlapFraction=None, textEncoder=None)
+.. py:class:: DocumentRetrieverConfig(client, chunkSize=None, chunkOverlapFraction=None, textEncoder=None, scoreMultiplierColumn=None)
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -32,6 +32,8 @@ Classes
:type chunkOverlapFraction: float
:param textEncoder: The text encoder used to encode texts in the vector store.
:type textEncoder: str
+ :param scoreMultiplierColumn: The values in this metadata column are used to modify the relevance scores of returned chunks.
+ :type scoreMultiplierColumn: str
.. py:method:: __repr__()
diff --git a/docs/_sources/autoapi/abacusai/external_application/index.rst.txt b/docs/_sources/autoapi/abacusai/external_application/index.rst.txt
index 146bdc5d3..8fb43d43a 100644
--- a/docs/_sources/autoapi/abacusai/external_application/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/external_application/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: ExternalApplication(client, name=None, externalApplicationId=None, deploymentId=None, logo=None, theme=None, userGroupIds=None, useCase=None, status=None)
+.. py:class:: ExternalApplication(client, name=None, externalApplicationId=None, deploymentId=None, logo=None, theme=None, userGroupIds=None, useCase=None, status=None, deploymentConversationRetentionHours=None)
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -42,6 +42,8 @@ Classes
:type useCase: str
:param status: The status of the deployment.
:type status: str
+ :param deploymentConversationRetentionHours: The retention policy for the external application.
+ :type deploymentConversationRetentionHours: int
.. py:method:: __repr__()
@@ -56,7 +58,7 @@ Classes
:rtype: dict
- .. py:method:: update(name = None, theme = None, deployment_id = None)
+ .. py:method:: update(name = None, theme = None, deployment_id = None, deployment_conversation_retention_hours = None, reset_retention_policy = False)
Updates an External Application.
@@ -66,6 +68,10 @@ Classes
:type theme: dict
:param deployment_id: The ID of the deployment to use.
:type deployment_id: str
+ :param deployment_conversation_retention_hours: The number of hours to retain the conversations for.
+ :type deployment_conversation_retention_hours: int
+ :param reset_retention_policy: If true, the retention policy will be removed.
+ :type reset_retention_policy: bool
:returns: The updated External Application.
:rtype: ExternalApplication
diff --git a/docs/_sources/autoapi/abacusai/feature_group/index.rst.txt b/docs/_sources/autoapi/abacusai/feature_group/index.rst.txt
index df82c993b..4de91922f 100644
--- a/docs/_sources/autoapi/abacusai/feature_group/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/feature_group/index.rst.txt
@@ -1067,20 +1067,7 @@ Classes
:type data: list
- .. py:method:: upsert_data(streaming_token = None, data = None)
-
- Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
-
- :param streaming_token: Optional streaming token for authenticating requests if upserting to streaming FG.
- :type streaming_token: str
- :param data: The data to record, in JSON format.
- :type data: dict
-
- :returns: The feature group row that was upserted.
- :rtype: FeatureGroupRow
-
-
- .. py:method:: upsert_online_data(data, streaming_token = None)
+ .. py:method:: upsert_data(data, streaming_token = None)
Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
diff --git a/docs/_sources/autoapi/abacusai/feature_group_export/index.rst.txt b/docs/_sources/autoapi/abacusai/feature_group_export/index.rst.txt
index 3506de56f..e6b247b3a 100644
--- a/docs/_sources/autoapi/abacusai/feature_group_export/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/feature_group_export/index.rst.txt
@@ -140,7 +140,4 @@ Classes
:rtype: str
- .. py:method:: get_results()
-
-
diff --git a/docs/_sources/autoapi/abacusai/index.rst.txt b/docs/_sources/autoapi/abacusai/index.rst.txt
index 97e24f022..3dd258d96 100644
--- a/docs/_sources/autoapi/abacusai/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/index.rst.txt
@@ -244,6 +244,7 @@ Classes
abacusai.SentenceBoundaryDetectionBatchPredictionArgs
abacusai.ThemeAnalysisBatchPredictionArgs
abacusai.ChatLLMBatchPredictionArgs
+ abacusai.TrainablePlugAndPlayBatchPredictionArgs
abacusai._BatchPredictionArgsFactory
abacusai.BlobInput
abacusai.OcrMode
@@ -310,6 +311,7 @@ Classes
abacusai.PythonFunctionType
abacusai.EvalArtifactType
abacusai.FieldDescriptorType
+ abacusai.DataType
abacusai.SamplingConfig
abacusai.NSamplingConfig
abacusai.PercentSamplingConfig
@@ -567,6 +569,8 @@ Attributes
:type for_eval: bool
:param threshold: The threshold for detecting an anomaly. Range: [0.8, 0.99]
:type threshold: float
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
.. py:attribute:: for_eval
:type: bool
@@ -578,6 +582,11 @@ Attributes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -601,8 +610,10 @@ Attributes
:type forecasting_horizon: int
:param item_attributes_to_include_in_the_result: List of columns to include in the prediction output.
:type item_attributes_to_include_in_the_result: list
- :param explain_predictions: If True, explain predictions for the forecast.
+ :param explain_predictions: If True, calculates explanations for the forecasted values along with predictions.
:type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -639,6 +650,11 @@ Attributes
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -736,6 +752,10 @@ Attributes
:type bound_label: str
:param output_columns: A list of column names to include in the prediction result.
:type output_columns: list
+ :param explain_predictions: If True, calculates explanations for the predicted values along with predictions.
+ :type explain_predictions: bool
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
.. py:attribute:: for_eval
:type: bool
@@ -787,6 +807,16 @@ Attributes
+ .. py:attribute:: explain_predictions
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
.. py:method:: __post_init__()
@@ -909,6 +939,30 @@ Attributes
+.. py:class:: TrainablePlugAndPlayBatchPredictionArgs
+
+
+ Bases: :py:obj:`BatchPredictionArgs`
+
+ Batch Prediction Config for the TrainablePlugAndPlay problem type
+
+ :param automate_monitoring: If True, creates a monitor to calculate the drift for the batch prediction.
+ :type automate_monitoring: bool
+
+ .. py:attribute:: for_eval
+ :type: bool
+
+
+
+ .. py:attribute:: automate_monitoring
+ :type: bool
+
+
+
+ .. py:method:: __post_init__()
+
+
+
.. py:class:: _BatchPredictionArgsFactory
@@ -1465,6 +1519,8 @@ Attributes
:type text_encoder: VectorStoreTextEncoder
:param chunk_size_factors: Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
:type chunk_size_factors: list
+ :param score_multiplier_column: If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
+ :type score_multiplier_column: str
.. py:attribute:: chunk_size
:type: int
@@ -1486,6 +1542,11 @@ Attributes
+ .. py:attribute:: score_multiplier_column
+ :type: str
+
+
+
.. py:class:: DocumentRetrieverConfig
@@ -2974,6 +3035,11 @@ Attributes
+ .. py:attribute:: MICROSOFTAUTH
+ :value: 'MICROSOFTAUTH'
+
+
+
.. py:class:: PythonFunctionArgumentType
@@ -3470,6 +3536,65 @@ Attributes
+.. py:class:: DataType
+
+
+ Bases: :py:obj:`ApiEnum`
+
+ Generic enumeration.
+
+ Derive from this class to define new enumerations.
+
+ .. py:attribute:: INTEGER
+ :value: 'integer'
+
+
+
+ .. py:attribute:: FLOAT
+ :value: 'float'
+
+
+
+ .. py:attribute:: STRING
+ :value: 'string'
+
+
+
+ .. py:attribute:: DATE
+ :value: 'date'
+
+
+
+ .. py:attribute:: DATETIME
+ :value: 'datetime'
+
+
+
+ .. py:attribute:: BOOLEAN
+ :value: 'boolean'
+
+
+
+ .. py:attribute:: LIST
+ :value: 'list'
+
+
+
+ .. py:attribute:: STRUCT
+ :value: 'struct'
+
+
+
+ .. py:attribute:: NULL
+ :value: 'null'
+
+
+
+ .. py:method:: from_str(value)
+ :classmethod:
+
+
+
.. py:class:: SamplingConfig
@@ -4901,6 +5026,8 @@ Attributes
:type disable_data_summarization: bool
:param search_score_cutoff: Minimum search score to consider a document as a valid search result.
:type search_score_cutoff: float
+ :param database_connector_id: Database connector id to use for the chatllm.
+ :type database_connector_id: str
.. py:attribute:: document_retrievers
:type: List[str]
@@ -4972,6 +5099,11 @@ Attributes
+ .. py:attribute:: database_connector_id
+ :type: str
+
+
+
.. py:method:: __post_init__()
@@ -8703,7 +8835,7 @@ Attributes
:param column: The name of the column.
:type column: str
:param data_type: The type of the data in the column. Note: Some ColumnMappings may restrict the options or explicitly set the DataType.
- :type data_type: str
+ :type data_type: DataType
:returns: The dataset and schema after the data type has been set.
:rtype: Dataset
@@ -10886,7 +11018,7 @@ Attributes
:rtype: AgentDataExecutionResult
- .. py:method:: create_batch_prediction(deployment_id, table_name = None, name = None, global_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
+ .. py:method:: create_batch_prediction(deployment_id, table_name = None, name = None, global_prediction_args = None, batch_prediction_args = None, explanations = False, output_format = None, output_location = None, database_connector_id = None, database_output_config = None, refresh_schedule = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, input_feature_groups = None)
Creates a batch prediction job description for the given deployment.
@@ -10896,10 +11028,8 @@ Attributes
:type table_name: str
:param name: Name of the batch prediction job.
:type name: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If true, SHAP explanations will be provided for each prediction, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: Format of the batch prediction output (CSV or JSON).
:type output_format: str
:param output_location: Location to write the prediction results. Otherwise, results will be stored in Abacus.AI.
@@ -10938,7 +11068,7 @@ Attributes
:rtype: BatchPredictionVersion
- .. py:method:: update_batch_prediction(batch_prediction_id, deployment_id = None, global_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
+ .. py:method:: update_batch_prediction(batch_prediction_id, deployment_id = None, global_prediction_args = None, batch_prediction_args = None, explanations = None, output_format = None, csv_input_prefix = None, csv_prediction_prefix = None, csv_explanations_prefix = None, output_includes_metadata = None, result_input_columns = None, name = None)
Update a batch prediction job description.
@@ -10946,10 +11076,8 @@ Attributes
:type batch_prediction_id: str
:param deployment_id: Unique identifier of the deployment.
:type deployment_id: str
- :param global_prediction_args: Batch Prediction args specific to problem type.
- :type global_prediction_args: BatchPredictionArgs
- :param explanations: If True, SHAP explanations for each prediction will be provided, if supported by the use case.
- :type explanations: bool
+ :param batch_prediction_args: Batch Prediction args specific to problem type.
+ :type batch_prediction_args: BatchPredictionArgs
:param output_format: If specified, sets the format of the batch prediction output (CSV or JSON).
:type output_format: str
:param csv_input_prefix: Prefix to prepend to the input columns, only applies when output format is CSV.
@@ -11229,22 +11357,7 @@ Attributes
:type data: list
- .. py:method:: upsert_data(feature_group_id, streaming_token = None, data = None)
-
- Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
-
- :param feature_group_id: A unique string identifier of the streaming feature group to record data to.
- :type feature_group_id: str
- :param streaming_token: Optional streaming token for authenticating requests if upserting to streaming FG.
- :type streaming_token: str
- :param data: The data to record, in JSON format.
- :type data: dict
-
- :returns: The feature group row that was upserted.
- :rtype: FeatureGroupRow
-
-
- .. py:method:: upsert_online_data(feature_group_id, data, streaming_token = None)
+ .. py:method:: upsert_data(feature_group_id, data, streaming_token = None)
Update new data into the feature group for a given lookup key record ID if the record ID is found; otherwise, insert new data into the feature group.
@@ -12218,7 +12331,7 @@ Attributes
:rtype: ExternalApplication
- .. py:method:: update_external_application(external_application_id, name = None, theme = None, deployment_id = None)
+ .. py:method:: update_external_application(external_application_id, name = None, theme = None, deployment_id = None, deployment_conversation_retention_hours = None, reset_retention_policy = False)
Updates an External Application.
@@ -12230,6 +12343,10 @@ Attributes
:type theme: dict
:param deployment_id: The ID of the deployment to use.
:type deployment_id: str
+ :param deployment_conversation_retention_hours: The number of hours to retain the conversations for.
+ :type deployment_conversation_retention_hours: int
+ :param reset_retention_policy: If true, the retention policy will be removed.
+ :type reset_retention_policy: bool
:returns: The updated External Application.
:rtype: ExternalApplication
@@ -15611,7 +15728,7 @@ Attributes
.. py:data:: __version__
- :value: '1.1.5'
+ :value: '1.1.6'
diff --git a/docs/_sources/autoapi/abacusai/pipeline/index.rst.txt b/docs/_sources/autoapi/abacusai/pipeline/index.rst.txt
index f6643b0fc..f01680264 100644
--- a/docs/_sources/autoapi/abacusai/pipeline/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/pipeline/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: Pipeline(client, pipelineName=None, pipelineId=None, createdAt=None, pipelineVariableMappings=None, notebookId=None, cron=None, nextRunTime=None, isProd=None, warning=None, createdBy=None, steps={}, pipelineReferences={}, latestPipelineVersion={}, codeSource={})
+.. py:class:: Pipeline(client, pipelineName=None, pipelineId=None, createdAt=None, notebookId=None, cron=None, nextRunTime=None, isProd=None, warning=None, createdBy=None, steps={}, pipelineReferences={}, latestPipelineVersion={}, codeSource={}, pipelineVariableMappings={})
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -32,8 +32,6 @@ Classes
:type pipelineId: str
:param createdAt: The date and time which the pipeline was created.
:type createdAt: str
- :param pipelineVariableMappings: A description of the function variables into the pipeline.
- :type pipelineVariableMappings: dict
:param notebookId: The reference to the notebook this pipeline belongs to.
:type notebookId: str
:param cron: A cron-style string that describes when this refresh policy is to be executed in UTC
diff --git a/docs/_sources/autoapi/abacusai/pipeline_version/index.rst.txt b/docs/_sources/autoapi/abacusai/pipeline_version/index.rst.txt
index 1418cdd63..059de0709 100644
--- a/docs/_sources/autoapi/abacusai/pipeline_version/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/pipeline_version/index.rst.txt
@@ -17,7 +17,7 @@ Classes
-.. py:class:: PipelineVersion(client, pipelineName=None, pipelineId=None, pipelineVersion=None, createdAt=None, updatedAt=None, completedAt=None, status=None, error=None, pipelineVariableMappings=None, stepVersions={}, codeSource={})
+.. py:class:: PipelineVersion(client, pipelineName=None, pipelineId=None, pipelineVersion=None, createdAt=None, updatedAt=None, completedAt=None, status=None, error=None, stepVersions={}, codeSource={}, pipelineVariableMappings={})
Bases: :py:obj:`abacusai.return_class.AbstractApiClass`
@@ -42,8 +42,6 @@ Classes
:type status: str
:param error: The relevant error, if the status is FAILED.
:type error: str
- :param pipelineVariableMappings: A description of the function variables into the pipeline.
- :type pipelineVariableMappings: dict
:param stepVersions: A list of the pipeline step versions.
:type stepVersions: PipelineStepVersion
:param codeSource: information on the source code
diff --git a/docs/_sources/autoapi/abacusai/project/index.rst.txt b/docs/_sources/autoapi/abacusai/project/index.rst.txt
index c46dd17f4..256582061 100644
--- a/docs/_sources/autoapi/abacusai/project/index.rst.txt
+++ b/docs/_sources/autoapi/abacusai/project/index.rst.txt
@@ -702,27 +702,6 @@ Classes
:rtype: list[DocumentRetriever]
- .. py:method:: attach_dataset(dataset_id, project_dataset_type)
-
- Attaches dataset to the project.
-
- :param dataset_id: A unique identifier for the dataset.
- :type dataset_id: unique string identifier
- :param project_dataset_type: The unique use case specific dataset type that might be required or recommended for the specific use case.
- :type project_dataset_type: enum of type string
-
- :returns: The schema of the attached dataset.
- :rtype: Schema
-
-
- .. py:method:: remove_dataset(dataset_id)
-
- Removes dataset from the project.
-
- :param dataset_id: A unique identifier for the dataset.
- :type dataset_id: unique string identifier
-
-
.. py:method:: create_model_from_functions(train_function, predict_function = None, training_input_tables = None, predict_many_function = None, initialize_function = None, cpu_size = None, memory = None, training_config = None, exclusive_run = False)
Creates a model using python.
diff --git a/docs/autoapi/abacusai/api_class/batch_prediction/index.html b/docs/autoapi/abacusai/api_class/batch_prediction/index.html
index bb35297ba..ddde95f8f 100644
--- a/docs/autoapi/abacusai/api_class/batch_prediction/index.html
+++ b/docs/autoapi/abacusai/api_class/batch_prediction/index.html
@@ -123,7 +123,10 @@
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.
@@ -239,6 +249,11 @@ Classes
+
+-
+automate_monitoring: bool
+
+
-
__post_init__()
@@ -336,6 +351,8 @@ Classes) – 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.
@@ -389,6 +406,16 @@ Classes
+
+-
+explain_predictions: bool
+
+
+
+-
+automate_monitoring: bool
+
+
-
__post_init__()
@@ -526,6 +553,33 @@ Classes
+
-
class abacusai.api_class.batch_prediction._BatchPredictionArgsFactory
diff --git a/docs/autoapi/abacusai/api_class/document_retriever/index.html b/docs/autoapi/abacusai/api_class/document_retriever/index.html
index 78d7fb51d..afd77d055 100644
--- a/docs/autoapi/abacusai/api_class/document_retriever/index.html
+++ b/docs/autoapi/abacusai/api_class/document_retriever/index.html
@@ -113,6 +113,7 @@ Classes) – 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.
@@ -136,6 +137,11 @@ Classes
+
+-
+score_multiplier_column: str
+
+
diff --git a/docs/autoapi/abacusai/api_class/enums/index.html b/docs/autoapi/abacusai/api_class/enums/index.html
index 382b3e741..5531e4b09 100644
--- a/docs/autoapi/abacusai/api_class/enums/index.html
+++ b/docs/autoapi/abacusai/api_class/enums/index.html
@@ -240,6 +240,9 @@ ClassesOcrMode
|
Generic enumeration. |
+DataType
|
+Generic enumeration. |
+
@@ -1650,6 +1653,11 @@ Classes
+
+-
+MICROSOFTAUTH = 'MICROSOFTAUTH'
+
+
@@ -2191,6 +2199,64 @@ Classes
+
diff --git a/docs/autoapi/abacusai/api_class/index.html b/docs/autoapi/abacusai/api_class/index.html
index ed0bd4d8e..c8e00fbde 100644
--- a/docs/autoapi/abacusai/api_class/index.html
+++ b/docs/autoapi/abacusai/api_class/index.html
@@ -163,223 +163,229 @@ ClassesChatLLMBatchPredictionArgs
|
Batch Prediction Config for the ChatLLM problem type |
-_BatchPredictionArgsFactory
|
+
TrainablePlugAndPlayBatchPredictionArgs
|
+Batch Prediction Config for the TrainablePlugAndPlay problem type |
+
+_BatchPredictionArgsFactory
|
Helper class that provides a standard way to create an ABC using |
-ApiClass
|
+
ApiClass
|
Helper class that provides a standard way to create an ABC using |
-BlobInput
|
+
BlobInput
|
Binary large object input data. |
-ApiClass
|
+
ApiClass
|
Helper class that provides a standard way to create an ABC using |
-OcrMode
|
+
OcrMode
|
Generic enumeration. |
-ParsingConfig
|
+
ParsingConfig
|
Helper class that provides a standard way to create an ABC using |
-DocumentProcessingConfig
|
+
DocumentProcessingConfig
|
Document processing configuration. |
-IncrementalDatabaseConnectorConfig
|
+
IncrementalDatabaseConnectorConfig
|
Config information for incremental datasets from database connectors |
-ApiClass
|
+
ApiClass
|
Helper class that provides a standard way to create an ABC using |
-_ApiClassFactory
|
+
_ApiClassFactory
|
Helper class that provides a standard way to create an ABC using |
-DatasetConfig
|
+
DatasetConfig
|
Helper class that provides a standard way to create an ABC using |
-ConfluenceDatasetConfig
|
+
ConfluenceDatasetConfig
|
Dataset config for Confluence Application Connector |
-GoogleAnalyticsDatasetConfig
|
+
GoogleAnalyticsDatasetConfig
|
Dataset config for Google Analytics Application Connector |
-GoogleDriveDatasetConfig
|
+
GoogleDriveDatasetConfig
|
Dataset config for Google Drive Application Connector |
-JiraDatasetConfig
|
+
JiraDatasetConfig
|
Dataset config for Jira Application Connector |
-OneDriveDatasetConfig
|
+
OneDriveDatasetConfig
|
Dataset config for OneDrive Application Connector |
-SharepointDatasetConfig
|
+
SharepointDatasetConfig
|
Dataset config for Sharepoint Application Connector |
-ZendeskDatasetConfig
|
+
ZendeskDatasetConfig
|
Dataset config for Zendesk Application Connector |
-AbacusUsageMetricsDatasetConfig
|
+
AbacusUsageMetricsDatasetConfig
|
Dataset config for Abacus Usage Metrics Application Connector |
-_DatasetConfigFactory
|
+
_DatasetConfigFactory
|
Helper class that provides a standard way to create an ABC using |
-ApiClass
|
+
ApiClass
|
Helper class that provides a standard way to create an ABC using |
-VectorStoreTextEncoder
|
+
VectorStoreTextEncoder
|
Generic enumeration. |
-VectorStoreConfig
|
+
VectorStoreConfig
|
Configs for vector store indexing. |
-DocumentRetrieverConfig
|
+
DocumentRetrieverConfig
|
Configs for document retriever. |
-ApiEnum
|
+
ApiEnum
|
Generic enumeration. |
-ProblemType
|
+
ProblemType
|
Generic enumeration. |
-RegressionObjective
|
+
RegressionObjective
|
Generic enumeration. |
-RegressionTreeHPOMode
|
+
RegressionTreeHPOMode
|
Generic enumeration. |
-PartialDependenceAnalysis
|
+
PartialDependenceAnalysis
|
Generic enumeration. |
-RegressionAugmentationStrategy
|
+
RegressionAugmentationStrategy
|
Generic enumeration. |
-RegressionTargetTransform
|
+
RegressionTargetTransform
|
Generic enumeration. |
-RegressionTypeOfSplit
|
+
RegressionTypeOfSplit
|
Generic enumeration. |
-RegressionTimeSplitMethod
|
+
RegressionTimeSplitMethod
|
Generic enumeration. |
-RegressionLossFunction
|
+
RegressionLossFunction
|
Generic enumeration. |
-ExplainerType
|
+
ExplainerType
|
Generic enumeration. |
-SamplingMethodType
|
+
SamplingMethodType
|
Generic enumeration. |
-MergeMode
|
+
MergeMode
|
Generic enumeration. |
-FillLogic
|
+
FillLogic
|
Generic enumeration. |
-BatchSize
|
+
BatchSize
|
Generic enumeration. |
-HolidayCalendars
|
+
HolidayCalendars
|
Generic enumeration. |
-FileFormat
|
+
FileFormat
|
Generic enumeration. |
-ExperimentationMode
|
+
ExperimentationMode
|
Generic enumeration. |
-PersonalizationTrainingMode
|
+
PersonalizationTrainingMode
|
Generic enumeration. |
-PersonalizationObjective
|
+
PersonalizationObjective
|
Generic enumeration. |
-ForecastingObjective
|
+
ForecastingObjective
|
Generic enumeration. |
-ForecastingFrequency
|
+
ForecastingFrequency
|
Generic enumeration. |
-ForecastingDataSplitType
|
+
ForecastingDataSplitType
|
Generic enumeration. |
-ForecastingLossFunction
|
+
ForecastingLossFunction
|
Generic enumeration. |
-ForecastingLocalScaling
|
+
ForecastingLocalScaling
|
Generic enumeration. |
-ForecastingFillMethod
|
+
ForecastingFillMethod
|
Generic enumeration. |
-ForecastingQuanitlesExtensionMethod
|
+
ForecastingQuanitlesExtensionMethod
|
Generic enumeration. |
-TimeseriesAnomalyDataSplitType
|
+
TimeseriesAnomalyDataSplitType
|
Generic enumeration. |
-TimeseriesAnomalyTypeOfAnomaly
|
+
TimeseriesAnomalyTypeOfAnomaly
|
Generic enumeration. |
-NERObjective
|
+
NERObjective
|
Generic enumeration. |
-NERModelType
|
+
NERModelType
|
Generic enumeration. |
-NLPDocumentFormat
|
+
NLPDocumentFormat
|
Generic enumeration. |
-SentimentType
|
+
SentimentType
|
Generic enumeration. |
-ClusteringImputationMethod
|
+
ClusteringImputationMethod
|
Generic enumeration. |
-ConnectorType
|
+
ConnectorType
|
Generic enumeration. |
-ApplicationConnectorType
|
+
ApplicationConnectorType
|
Generic enumeration. |
-PythonFunctionArgumentType
|
+
PythonFunctionArgumentType
|
Generic enumeration. |
-PythonFunctionOutputArgumentType
|
+
PythonFunctionOutputArgumentType
|
Generic enumeration. |
-VectorStoreTextEncoder
|
+
VectorStoreTextEncoder
|
Generic enumeration. |
-LLMName
|
+
LLMName
|
Generic enumeration. |
-MonitorAlertType
|
+
MonitorAlertType
|
Generic enumeration. |
-FeatureDriftType
|
+
FeatureDriftType
|
Generic enumeration. |
-DataIntegrityViolationType
|
+
DataIntegrityViolationType
|
Generic enumeration. |
-BiasType
|
+
BiasType
|
Generic enumeration. |
-AlertActionType
|
+
AlertActionType
|
Generic enumeration. |
-PythonFunctionType
|
+
PythonFunctionType
|
Generic enumeration. |
-EvalArtifactType
|
+
EvalArtifactType
|
Generic enumeration. |
-FieldDescriptorType
|
+
FieldDescriptorType
|
Generic enumeration. |
-OcrMode
|
+
OcrMode
|
+Generic enumeration. |
+
+DataType
|
Generic enumeration. |
ApiClass
|
@@ -1063,6 +1069,7 @@ Classes
-_BatchPredictionArgsFactory
|
+
TrainablePlugAndPlayBatchPredictionArgs
|
+Batch Prediction Config for the TrainablePlugAndPlay problem type |
+
+_BatchPredictionArgsFactory
|
Helper class that provides a standard way to create an ABC using |
-BlobInput
|
+
BlobInput
|
Binary large object input data. |
-OcrMode
|
+
OcrMode
|
Generic enumeration. |
-ParsingConfig
|
+
ParsingConfig
|
Helper class that provides a standard way to create an ABC using |
-DocumentProcessingConfig
|
+
DocumentProcessingConfig
|
Document processing configuration. |
-IncrementalDatabaseConnectorConfig
|
+
IncrementalDatabaseConnectorConfig
|
Config information for incremental datasets from database connectors |
-DatasetConfig
|
+
DatasetConfig
|
Helper class that provides a standard way to create an ABC using |
-ConfluenceDatasetConfig
|
+
ConfluenceDatasetConfig
|
Dataset config for Confluence Application Connector |
-GoogleAnalyticsDatasetConfig
|
+
GoogleAnalyticsDatasetConfig
|
Dataset config for Google Analytics Application Connector |
-GoogleDriveDatasetConfig
|
+
GoogleDriveDatasetConfig
|
Dataset config for Google Drive Application Connector |
-JiraDatasetConfig
|
+
JiraDatasetConfig
|
Dataset config for Jira Application Connector |
-OneDriveDatasetConfig
|
+
OneDriveDatasetConfig
|
Dataset config for OneDrive Application Connector |
-SharepointDatasetConfig
|
+
SharepointDatasetConfig
|
Dataset config for Sharepoint Application Connector |
-ZendeskDatasetConfig
|
+
ZendeskDatasetConfig
|
Dataset config for Zendesk Application Connector |
-AbacusUsageMetricsDatasetConfig
|
+
AbacusUsageMetricsDatasetConfig
|
Dataset config for Abacus Usage Metrics Application Connector |
-_DatasetConfigFactory
|
+
_DatasetConfigFactory
|
Helper class that provides a standard way to create an ABC using |
-VectorStoreTextEncoder
|
+
VectorStoreTextEncoder
|
Generic enumeration. |
-VectorStoreConfig
|
+
VectorStoreConfig
|
Configs for vector store indexing. |
-DocumentRetrieverConfig
|
+
DocumentRetrieverConfig
|
Configs for document retriever. |
-ApiEnum
|
+
ApiEnum
|
+Generic enumeration. |
+
+ProblemType
|
Generic enumeration. |
-ProblemType
|
+
RegressionObjective
|
Generic enumeration. |
-RegressionObjective
|
+
RegressionTreeHPOMode
|
Generic enumeration. |
-RegressionTreeHPOMode
|
+
PartialDependenceAnalysis
|
Generic enumeration. |
-PartialDependenceAnalysis
|
+
RegressionAugmentationStrategy
|
Generic enumeration. |
-RegressionAugmentationStrategy
|
+
RegressionTargetTransform
|
Generic enumeration. |
-RegressionTargetTransform
|
+
RegressionTypeOfSplit
|
Generic enumeration. |
-RegressionTypeOfSplit
|
+
RegressionTimeSplitMethod
|
Generic enumeration. |
-RegressionTimeSplitMethod
|
+
RegressionLossFunction
|
Generic enumeration. |
-RegressionLossFunction
|
+
ExplainerType
|
Generic enumeration. |
-ExplainerType
|
+
SamplingMethodType
|
Generic enumeration. |
-SamplingMethodType
|
+
MergeMode
|
Generic enumeration. |
-MergeMode
|
+
FillLogic
|
Generic enumeration. |
-FillLogic
|
+
BatchSize
|
Generic enumeration. |
-BatchSize
|
+
HolidayCalendars
|
Generic enumeration. |
-HolidayCalendars
|
+
FileFormat
|
Generic enumeration. |
-FileFormat
|
+
ExperimentationMode
|
Generic enumeration. |
-ExperimentationMode
|
+
PersonalizationTrainingMode
|
Generic enumeration. |
-PersonalizationTrainingMode
|
+
PersonalizationObjective
|
Generic enumeration. |
-PersonalizationObjective
|
+
ForecastingObjective
|
Generic enumeration. |
-ForecastingObjective
|
+
ForecastingFrequency
|
Generic enumeration. |
-ForecastingFrequency
|
+
ForecastingDataSplitType
|
Generic enumeration. |
-ForecastingDataSplitType
|
+
ForecastingLossFunction
|
Generic enumeration. |
-ForecastingLossFunction
|
+
ForecastingLocalScaling
|
Generic enumeration. |
-ForecastingLocalScaling
|
+
ForecastingFillMethod
|
Generic enumeration. |
-ForecastingFillMethod
|
+
ForecastingQuanitlesExtensionMethod
|
Generic enumeration. |
-ForecastingQuanitlesExtensionMethod
|
+
TimeseriesAnomalyDataSplitType
|
Generic enumeration. |
-TimeseriesAnomalyDataSplitType
|
+
TimeseriesAnomalyTypeOfAnomaly
|
Generic enumeration. |
-TimeseriesAnomalyTypeOfAnomaly
|
+
NERObjective
|
Generic enumeration. |
-NERObjective
|
+
NERModelType
|
Generic enumeration. |
-NERModelType
|
+
NLPDocumentFormat
|
Generic enumeration. |
-NLPDocumentFormat
|
+
SentimentType
|
Generic enumeration. |
-SentimentType
|
+
ClusteringImputationMethod
|
Generic enumeration. |
-ClusteringImputationMethod
|
+
ConnectorType
|
Generic enumeration. |
-ConnectorType
|
+
ApplicationConnectorType
|
Generic enumeration. |
-ApplicationConnectorType
|
+
PythonFunctionArgumentType
|
Generic enumeration. |
-PythonFunctionArgumentType
|
+
PythonFunctionOutputArgumentType
|
Generic enumeration. |
-PythonFunctionOutputArgumentType
|
+
LLMName
|
Generic enumeration. |
-LLMName
|
+
MonitorAlertType
|
Generic enumeration. |
-MonitorAlertType
|
+
FeatureDriftType
|
Generic enumeration. |
-FeatureDriftType
|
+
DataIntegrityViolationType
|
Generic enumeration. |
-DataIntegrityViolationType
|
+
BiasType
|
Generic enumeration. |
-BiasType
|
+
AlertActionType
|
Generic enumeration. |
-AlertActionType
|
+
PythonFunctionType
|
Generic enumeration. |
-PythonFunctionType
|
+
EvalArtifactType
|
Generic enumeration. |
-EvalArtifactType
|
+
FieldDescriptorType
|
Generic enumeration. |
-FieldDescriptorType
|
+
DataType
|
Generic enumeration. |
SamplingConfig
|
@@ -1360,6 +1368,7 @@ Attributes