Version 0.78.5

Author: Brandon Lefore

abacusai/__init__.py

@@ -4,4 +4,4 @@
 from .streaming_client import StreamingClient
 
 
-__version__ = "0.78.0"
+__version__ = "0.78.5"

abacusai/agent.py

@@ -18,11 +18,12 @@ class Agent(AbstractApiClass):
             sourceCode (str): Python code used to make the agent.
             agentConfig (dict): The config options used to create this agent.
             memory (int): Memory in GB specified for the deployment resources for the agent.
+            trainingRequired (bool): Whether training is required to deploy the latest agent code.
             latestAgentVersion (AgentVersion): The latest agent version.
             codeSource (CodeSource): If a python model, information on the source code
     """
 
-    def __init__(self, client, name=None, agentId=None, createdAt=None, projectId=None, notebookId=None, predictFunctionName=None, sourceCode=None, agentConfig=None, memory=None, codeSource={}, latestAgentVersion={}):
+    def __init__(self, client, name=None, agentId=None, createdAt=None, projectId=None, notebookId=None, predictFunctionName=None, sourceCode=None, agentConfig=None, memory=None, trainingRequired=None, codeSource={}, latestAgentVersion={}):
         super().__init__(client, agentId)
         self.name = name
         self.agent_id = agentId
@@ -33,13 +34,14 @@ def __init__(self, client, name=None, agentId=None, createdAt=None, projectId=No
         self.source_code = sourceCode
         self.agent_config = agentConfig
         self.memory = memory
+        self.training_required = trainingRequired
         self.code_source = client._build_class(CodeSource, codeSource)
         self.latest_agent_version = client._build_class(
             AgentVersion, latestAgentVersion)
 
     def __repr__(self):
-        repr_dict = {f'name': repr(self.name), f'agent_id': repr(self.agent_id), f'created_at': repr(self.created_at), f'project_id': repr(self.project_id), f'notebook_id': repr(self.notebook_id), f'predict_function_name': repr(
-            self.predict_function_name), f'source_code': repr(self.source_code), f'agent_config': repr(self.agent_config), f'memory': repr(self.memory), f'code_source': repr(self.code_source), f'latest_agent_version': repr(self.latest_agent_version)}
+        repr_dict = {f'name': repr(self.name), f'agent_id': repr(self.agent_id), f'created_at': repr(self.created_at), f'project_id': repr(self.project_id), f'notebook_id': repr(self.notebook_id), f'predict_function_name': repr(self.predict_function_name), f'source_code': repr(
+            self.source_code), f'agent_config': repr(self.agent_config), f'memory': repr(self.memory), f'training_required': repr(self.training_required), f'code_source': repr(self.code_source), f'latest_agent_version': repr(self.latest_agent_version)}
         class_name = "Agent"
         repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
         ) if getattr(self, key, None) is not None])
@@ -52,8 +54,8 @@ def to_dict(self):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        resp = {'name': self.name, 'agent_id': self.agent_id, 'created_at': self.created_at, 'project_id': self.project_id, 'notebook_id': self.notebook_id, 'predict_function_name': self.predict_function_name,
-                'source_code': self.source_code, 'agent_config': self.agent_config, 'memory': self.memory, 'code_source': self._get_attribute_as_dict(self.code_source), 'latest_agent_version': self._get_attribute_as_dict(self.latest_agent_version)}
+        resp = {'name': self.name, 'agent_id': self.agent_id, 'created_at': self.created_at, 'project_id': self.project_id, 'notebook_id': self.notebook_id, 'predict_function_name': self.predict_function_name, 'source_code': self.source_code,
+                'agent_config': self.agent_config, 'memory': self.memory, 'training_required': self.training_required, 'code_source': self._get_attribute_as_dict(self.code_source), 'latest_agent_version': self._get_attribute_as_dict(self.latest_agent_version)}
         return {key: value for key, value in resp.items() if value is not None}
 
     def refresh(self):

abacusai/ai_building_task.py

@@ -3,7 +3,7 @@
 
 class AiBuildingTask(AbstractApiClass):
     """
-        A task for AI Chat to help build AI.
+        A task for Data Science Co-pilot to help build AI.
 
         Args:
             client (ApiClient): An authenticated API Client instance

abacusai/api_class/__init__.py

@@ -1,6 +1,7 @@
 from .batch_prediction import *
 from .blob_input import *
 from .dataset import *
+from .dataset_application_connector import *
 from .document_retriever import *
 from .enums import *
 from .feature_group import *

abacusai/api_class/abstract.py

@@ -154,7 +154,10 @@ def from_dict(cls, config: dict) -> ApiClass:
         support_kwargs = cls.config_abstract_class and cls.config_abstract_class._support_kwargs
         config_class_key = cls.config_class_key if (cls.config_abstract_class and not cls.config_abstract_class._upper_snake_case_keys) else camel_case(cls.config_class_key)
         if not support_kwargs and config_class_key not in (config or {}):
-            raise KeyError(f'Could not find {config_class_key} in {config}')
+            if camel_case(config_class_key) in (config or {}):
+                config_class_key = camel_case(config_class_key)
+            else:
+                raise KeyError(f'Could not find {config_class_key} in {config}')
         config_class_type = config.get(config_class_key, None)
         if isinstance(config_class_type, str):
             config_class_type = config_class_type.upper()

abacusai/api_class/batch_prediction.py

@@ -203,10 +203,8 @@ class ChatLLMBatchPredictionArgs(BatchPredictionArgs):
     Batch Prediction Config for the ChatLLM problem type
     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.
-        product (bool): Generate a response for every question and chunk combination
     """
     for_eval: bool = dataclasses.field(default=None)
-    product: bool = None
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.CHAT_LLM

abacusai/api_class/dataset_application_connector.py

@@ -0,0 +1,81 @@
+import dataclasses
+
+from . import enums
+from .abstract import ApiClass, _ApiClassFactory
+
+
+@dataclasses.dataclass
+class DatasetConfig(ApiClass):
+    application_connector_type: enums.ApplicationConnectorType = dataclasses.field(default=None, repr=False)
+
+    @classmethod
+    def _get_builder(cls):
+        return _DatasetConfigFactory
+
+
+@dataclasses.dataclass
+class ConfluenceDatasetConfig(DatasetConfig):
+    """
+    Dataset config for Confluence Application Connector
+    """
+    def __post_init__(self):
+        self.application_connector_type = enums.ApplicationConnectorType.CONFLUENCE
+
+
+@dataclasses.dataclass
+class GoogleAnalyticsDatasetConfig(DatasetConfig):
+    """
+    Dataset config for Google Analytics Application Connector
+    Args:
+        location (str): The view id of the report in the connector to fetch
+        start_timestamp (int, optional): Unix timestamp of the start of the period that will be queried
+        end_timestamp (int, optional): Unix timestamp of the end of the period that will be queried
+    """
+    location: str = dataclasses.field(default=None)
+    start_timestamp: int = dataclasses.field(default=None)
+    end_timestamp: int = dataclasses.field(default=None)
+
+    def __post_init__(self):
+        self.application_connector_type = enums.ApplicationConnectorType.GOOGLEANALYTICS
+
+
+@dataclasses.dataclass
+class SharepointDatasetConfig(DatasetConfig):
+    """
+    Dataset config for Sharepoint Application Connector
+    Args:
+        location (str): The regex location of the files to fetch
+        is_documentset (bool): Whether the dataset is a document set
+        csv_delimiter (str, optional): If the file format is CSV, use a specific csv delimiter
+        extract_bounding_boxes (bool, optional): Signifies whether to extract bounding boxes out of the documents. Only valid if is_documentset if True
+        merge_file_schemas (bool, optional): Signifies if the merge file schema policy is enabled. If is_documentset is True, this is also set to True by default
+    """
+    location: str = dataclasses.field(default=None)
+    is_documentset: bool = dataclasses.field(default=None)
+    csv_delimiter: str = dataclasses.field(default=None)
+    extract_bounding_boxes: bool = dataclasses.field(default=False)
+    merge_file_schemas: bool = dataclasses.field(default=False)
+
+    def __post_init__(self):
+        self.application_connector_type = enums.ApplicationConnectorType.SHAREPOINT
+
+
+@dataclasses.dataclass
+class ZendeskDatasetConfig(DatasetConfig):
+    """
+    Dataset config for Zendesk Application Connector
+    """
+    def __post_init__(self):
+        self.application_connector_type = enums.ApplicationConnectorType.ZENDESK
+
+
+@dataclasses.dataclass
+class _DatasetConfigFactory(_ApiClassFactory):
+    config_abstract_class = DatasetConfig
+    config_class_key = 'applicationConnectorType'
+    config_class_map = {
+        enums.ApplicationConnectorType.CONFLUENCE: ConfluenceDatasetConfig,
+        enums.ApplicationConnectorType.GOOGLEANALYTICS: GoogleAnalyticsDatasetConfig,
+        enums.ApplicationConnectorType.SHAREPOINT: SharepointDatasetConfig,
+        enums.ApplicationConnectorType.ZENDESK: ZendeskDatasetConfig,
+    }

abacusai/api_class/enums.py

@@ -155,6 +155,30 @@ class HolidayCalendars(ApiEnum):
     US = 'US'
 
 
+class FileFormat(ApiEnum):
+    AVRO = 'AVRO'
+    PARQUET = 'PARQUET'
+    TFRECORD = 'TFRECORD'
+    TSV = 'TSV'
+    CSV = 'CSV'
+    ORC = 'ORC'
+    JSON = 'JSON'
+    ODS = 'ODS'
+    XLS = 'XLS'
+    GZ = 'GZ'
+    ZIP = 'ZIP'
+    TAR = 'TAR'
+    DOCX = 'DOCX'
+    PDF = 'PDF'
+    RAR = 'RAR'
+    JPEG = 'JPG'
+    PNG = 'PNG'
+    TIF = 'TIFF'
+    NUMBERS = 'NUMBERS'
+    PPTX = 'PPTX'
+    PPT = 'PPT'
+
+
 class ExperimentationMode(ApiEnum):
     RAPID = 'rapid'
     THOROUGH = 'thorough'
@@ -296,6 +320,16 @@ class ConnectorType(ApiEnum):
     APPLICATION = 'APPLICATION'
 
 
+class ApplicationConnectorType(ApiEnum):
+    GOOGLEANALYTICS = 'GOOGLEANALYTICS'
+    GIT = 'GIT'
+    CONFLUENCE = 'CONFLUENCE'
+    ZENDESK = 'ZENDESK'
+    SLACK = 'SLACK'
+    SHAREPOINT = 'SHAREPOINT'
+    TEAMS = 'TEAMS'
+
+
 class PythonFunctionArgumentType(ApiEnum):
     FEATURE_GROUP = 'FEATURE_GROUP'
     INTEGER = 'INTEGER'

abacusai/api_class/model.py

@@ -741,3 +741,19 @@ class _TrainingConfigFactory(_ApiClassFactory):
         enums.ProblemType.CUSTOM_ALGORITHM: CustomAlgorithmTrainingConfig,
         enums.ProblemType.OPTIMIZATION: OptimizationTrainingConfig
     }
+
+
+@dataclasses.dataclass
+class DeployableAlgorithm(ApiClass):
+    """
+    Algorithm that can be deployed to a model.
+    Args:
+        algorithm (str): ID of the algorithm.
+        name (str): Name of the algorithm.
+        only_offline_deployable (bool): Whether the algorithm can only be deployed offline.
+        trained_model_types (List[dict]): List of trained model types.
+    """
+    algorithm: str = dataclasses.field(default=None)
+    name: str = dataclasses.field(default=None)
+    only_offline_deployable: bool = dataclasses.field(default=None)
+    trained_model_types: List[dict] = dataclasses.field(default=None)

abacusai/api_class/monitor_alert.py

@@ -23,46 +23,58 @@ class AccuracyBelowThresholdConditionConfig(AlertConditionConfig):
     """
     threshold: float = dataclasses.field(default=None)
 
+    def __post_init__(self):
+        self.alert_type = enums.MonitorAlertType.ACCURACY_BELOW_THRESHOLD
+
 
 @dataclasses.dataclass
 class FeatureDriftConditionConfig(AlertConditionConfig):
     """
     Feature Drift Condition Config for Monitor Alerts
     Args:
-        feature_drift_type (str): Feature drift type to apply the threshold on to determine whether a column has drifted significantly enough to be a violation.
+        feature_drift_type (FeatureDriftType): Feature drift type to apply the threshold on to determine whether a column has drifted significantly enough to be a violation.
         threshold (float): Threshold for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.
         minimum_violations (int): Number of columns that must exceed the specified threshold to trigger an alert.
     """
     feature_drift_type: enums.FeatureDriftType = dataclasses.field(default=None)
     threshold: float = dataclasses.field(default=None)
     minimum_violations: int = dataclasses.field(default=None)
 
+    def __post_init__(self):
+        self.alert_type = enums.MonitorAlertType.FEATURE_DRIFT
+
 
 @dataclasses.dataclass
 class DataIntegrityViolationConditionConfig(AlertConditionConfig):
     """
     Data Integrity Violation Condition Config for Monitor Alerts
     Args:
-        data_integrity_type (enums.DataIntegrityViolationType): This option selects the data integrity violations to monitor for this alert.
+        data_integrity_type (DataIntegrityViolationType): This option selects the data integrity violations to monitor for this alert.
         minimum_violations (int): Number of columns that must exceed the specified threshold to trigger an alert.
     """
     data_integrity_type: enums.DataIntegrityViolationType = dataclasses.field(default=None)
     minimum_violations: int = dataclasses.field(default=None)
 
+    def __post_init__(self):
+        self.alert_type = enums.MonitorAlertType.DATA_INTEGRITY_VIOLATIONS
+
 
 @dataclasses.dataclass
 class BiasViolationConditionConfig(AlertConditionConfig):
     """
     Bias Violation Condition Config for Monitor Alerts
     Args:
-        bias_type (enums.BiasType): This option selects the bias metric to monitor for this alert.
+        bias_type (BiasType): This option selects the bias metric to monitor for this alert.
         threshold (float): Threshold for when to consider a column to be in violation. The alert will only fire when the drift value is strictly greater than the threshold.
         minimum_violations (int): Number of columns that must exceed the specified threshold to trigger an alert.
     """
     bias_type: enums.BiasType = dataclasses.field(default=None)
     threshold: float = dataclasses.field(default=None)
     minimum_violations: int = dataclasses.field(default=None)
 
+    def __post_init__(self):
+        self.alert_type = enums.MonitorAlertType.BIAS_VIOLATIONS
+
 
 @dataclasses.dataclass
 class _AlertConditionConfigFactory(_ApiClassFactory):