Version 0.79.2

Author: Brandon Lefore

abacusai/__init__.py

@@ -4,4 +4,4 @@
 from .streaming_client import StreamingClient
 
 
-__version__ = "0.79.0"
+__version__ = "0.79.2"

abacusai/api_class/__init__.py

@@ -1,3 +1,4 @@
+from .ai_agents import *
 from .batch_prediction import *
 from .blob_input import *
 from .dataset import *

abacusai/api_class/ai_agents.py

@@ -0,0 +1,22 @@
+import dataclasses
+from typing import Union
+
+from . import enums
+from .abstract import ApiClass
+
+
+@dataclasses.dataclass
+class FieldDescriptor(ApiClass):
+    """
+    Configs for vector store indexing.
+
+    Args:
+        field (str): The field to be extracted. This will be used as the key in the response.
+        description (str): The description of this field. If not included, the response_field will be used.
+        example_extraction (Union[str, int, bool, float]): An example of this extracted field.
+        type (enums.FieldDescriptorType): The type of this field. If not provided, the default type is STRING.
+    """
+    field: str = dataclasses.field()
+    description: str = dataclasses.field(default=None)
+    example_extraction: Union[str, int, bool, float, list, dict] = dataclasses.field(default=None)
+    type: enums.FieldDescriptorType = dataclasses.field(default=enums.FieldDescriptorType.STRING)

abacusai/api_class/dataset.py

@@ -19,3 +19,4 @@ class DocumentProcessingConfig(ApiClass):
     remove_watermarks: bool = None
     use_full_ocr: bool = None
     layout_analysis: bool = False
+    enhanced_layout_detection: bool = False

abacusai/api_class/dataset_application_connector.py

@@ -39,6 +39,27 @@ def __post_init__(self):
         self.application_connector_type = enums.ApplicationConnectorType.GOOGLEANALYTICS
 
 
+@dataclasses.dataclass
+class GoogleDriveDatasetConfig(DatasetConfig):
+    """
+    Dataset config for Google Drive 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. Not applicable if is_documentset is True
+    """
+    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.GOOGLEDRIVE
+
+
 @dataclasses.dataclass
 class SharepointDatasetConfig(DatasetConfig):
     """
@@ -48,7 +69,7 @@ class SharepointDatasetConfig(DatasetConfig):
         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
+        merge_file_schemas (bool, optional): Signifies if the merge file schema policy is enabled. Not applicable if is_documentset is True
     """
     location: str = dataclasses.field(default=None)
     is_documentset: bool = dataclasses.field(default=None)
@@ -76,6 +97,7 @@ class _DatasetConfigFactory(_ApiClassFactory):
     config_class_map = {
         enums.ApplicationConnectorType.CONFLUENCE: ConfluenceDatasetConfig,
         enums.ApplicationConnectorType.GOOGLEANALYTICS: GoogleAnalyticsDatasetConfig,
+        enums.ApplicationConnectorType.GOOGLEDRIVE: GoogleDriveDatasetConfig,
         enums.ApplicationConnectorType.SHAREPOINT: SharepointDatasetConfig,
         enums.ApplicationConnectorType.ZENDESK: ZendeskDatasetConfig,
     }

abacusai/api_class/enums.py

@@ -323,6 +323,7 @@ class ConnectorType(ApiEnum):
 
 class ApplicationConnectorType(ApiEnum):
     GOOGLEANALYTICS = 'GOOGLEANALYTICS'
+    GOOGLEDRIVE = 'GOOGLEDRIVE'
     GIT = 'GIT'
     CONFLUENCE = 'CONFLUENCE'
     ZENDESK = 'ZENDESK'
@@ -422,3 +423,18 @@ class PythonFunctionType(ApiEnum):
     FEATURE_GROUP = 'FEATURE_GROUP'
     PLOTLY_FIG = 'PLOTLY_FIG'
     STEP_FUNCTION = 'STEP_FUNCTION'
+
+
+class EvalArtifactType(ApiEnum):
+    FORECASTING_ACCURACY = 'bar_chart'
+    FORECASTING_VOLUME = 'bar_chart_volume'
+    FORECASTING_HISTORY_LENGTH_ACCURACY = 'bar_chart_accuracy_by_history'
+
+
+class FieldDescriptorType(ApiEnum):
+    STRING = 'STRING'
+    INTEGER = 'INTEGER'
+    FLOAT = 'FLOAT'
+    BOOLEAN = 'BOOLEAN'
+    DATETIME = 'DATETIME'
+    DATE = 'DATE'

abacusai/api_class/model.py

@@ -57,11 +57,7 @@ class PersonalizationTrainingConfig(TrainingConfig):
         compute_session_metrics (bool): Evaluate models based on how well they are able to predict the next session of interactions.
         max_user_history_len_percentile (int): Filter out users with history length above this percentile.
         downsample_item_popularity_percentile (float): Downsample items more popular than this percentile.
-<<<<<<< HEAD
-        allow_duplicate_action_types (List[str]): event types which will not be deduplicated.
         use_user_id_feature (bool): Use user id as a feature in CTR models.
-=======
->>>>>>> e5f12c159c (add config options for session dedupe and recommendation exclusion)
     """
     # top-level params
     objective: enums.PersonalizationObjective = dataclasses.field(default=None)
@@ -382,6 +378,8 @@ class NamedEntityExtractionTrainingConfig(TrainingConfig):
         active_labels_column (str): Entities that have been marked in a particular text
         document_format (NLPDocumentFormat): Format of the input documents.
         include_longformer (bool): Whether to include the longformer model.
+        save_predicted_pdf (bool): Whether to save predicted PDF documents
+        enhanced_ocr (bool): Enhanced text extraction from predicted digital documents
     """
     objective: enums.NERObjective = dataclasses.field(default=None)
     sort_objective: enums.NERObjective = dataclasses.field(default=None)
@@ -396,6 +394,9 @@ class NamedEntityExtractionTrainingConfig(TrainingConfig):
     active_labels_column: str = dataclasses.field(default=None)
     document_format: enums.NLPDocumentFormat = dataclasses.field(default=None)
     include_longformer: bool = dataclasses.field(default=None)
+    # OCR
+    save_predicted_pdf: bool = True
+    enhanced_ocr: bool = False
 
     def __post_init__(self):
         self.problem_type = enums.ProblemType.NAMED_ENTITY_EXTRACTION

abacusai/api_endpoint.py

@@ -10,17 +10,19 @@ class ApiEndpoint(AbstractApiClass):
             apiEndpoint (str): The URI that can be used to make API calls
             predictEndpoint (str): The URI that can be used to make predict calls against Deployments
             proxyEndpoint (str): The URI that can be used to make proxy server calls
+            llmEndpoint (str): The URI that can be used to make llm api calls
     """
 
-    def __init__(self, client, apiEndpoint=None, predictEndpoint=None, proxyEndpoint=None):
+    def __init__(self, client, apiEndpoint=None, predictEndpoint=None, proxyEndpoint=None, llmEndpoint=None):
         super().__init__(client, None)
         self.api_endpoint = apiEndpoint
         self.predict_endpoint = predictEndpoint
         self.proxy_endpoint = proxyEndpoint
+        self.llm_endpoint = llmEndpoint
 
     def __repr__(self):
         repr_dict = {f'api_endpoint': repr(self.api_endpoint), f'predict_endpoint': repr(
-            self.predict_endpoint), f'proxy_endpoint': repr(self.proxy_endpoint)}
+            self.predict_endpoint), f'proxy_endpoint': repr(self.proxy_endpoint), f'llm_endpoint': repr(self.llm_endpoint)}
         class_name = "ApiEndpoint"
         repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
         ) if getattr(self, key, None) is not None])
@@ -33,6 +35,6 @@ def to_dict(self):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        resp = {'api_endpoint': self.api_endpoint, 'predict_endpoint':
-                self.predict_endpoint, 'proxy_endpoint': self.proxy_endpoint}
+        resp = {'api_endpoint': self.api_endpoint, 'predict_endpoint': self.predict_endpoint,
+                'proxy_endpoint': self.proxy_endpoint, 'llm_endpoint': self.llm_endpoint}
         return {key: value for key, value in resp.items() if value is not None}

abacusai/chat_session.py

@@ -16,11 +16,12 @@ class ChatSession(AbstractApiClass):
             createdAt (str): The timestamp at which the chat session was created
             status (str): The status of the chat sessions
             aiBuildingInProgress (bool): Whether the AI building is in progress or not
+            notification (str): A warn/info message about the chat session. For example, a suggestion to create a new session if the current one is too old
             chatHistory (ChatMessage): The chat history for the conversation
             nextAiBuildingTask (AiBuildingTask): The next AI building task for the chat session
     """
 
-    def __init__(self, client, answer=None, chatSessionId=None, projectId=None, name=None, createdAt=None, status=None, aiBuildingInProgress=None, chatHistory={}, nextAiBuildingTask={}):
+    def __init__(self, client, answer=None, chatSessionId=None, projectId=None, name=None, createdAt=None, status=None, aiBuildingInProgress=None, notification=None, chatHistory={}, nextAiBuildingTask={}):
         super().__init__(client, chatSessionId)
         self.answer = answer
         self.chat_session_id = chatSessionId
@@ -29,13 +30,14 @@ def __init__(self, client, answer=None, chatSessionId=None, projectId=None, name
         self.created_at = createdAt
         self.status = status
         self.ai_building_in_progress = aiBuildingInProgress
+        self.notification = notification
         self.chat_history = client._build_class(ChatMessage, chatHistory)
         self.next_ai_building_task = client._build_class(
             AiBuildingTask, nextAiBuildingTask)
 
     def __repr__(self):
         repr_dict = {f'answer': repr(self.answer), f'chat_session_id': repr(self.chat_session_id), f'project_id': repr(self.project_id), f'name': repr(self.name), f'created_at': repr(self.created_at), f'status': repr(
-            self.status), f'ai_building_in_progress': repr(self.ai_building_in_progress), f'chat_history': repr(self.chat_history), f'next_ai_building_task': repr(self.next_ai_building_task)}
+            self.status), f'ai_building_in_progress': repr(self.ai_building_in_progress), f'notification': repr(self.notification), f'chat_history': repr(self.chat_history), f'next_ai_building_task': repr(self.next_ai_building_task)}
         class_name = "ChatSession"
         repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
         ) if getattr(self, key, None) is not None])
@@ -48,8 +50,8 @@ def to_dict(self):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        resp = {'answer': self.answer, 'chat_session_id': self.chat_session_id, 'project_id': self.project_id, 'name': self.name, 'created_at': self.created_at, 'status': self.status,
-                'ai_building_in_progress': self.ai_building_in_progress, 'chat_history': self._get_attribute_as_dict(self.chat_history), 'next_ai_building_task': self._get_attribute_as_dict(self.next_ai_building_task)}
+        resp = {'answer': self.answer, 'chat_session_id': self.chat_session_id, 'project_id': self.project_id, 'name': self.name, 'created_at': self.created_at, 'status': self.status, 'ai_building_in_progress':
+                self.ai_building_in_progress, 'notification': self.notification, 'chat_history': self._get_attribute_as_dict(self.chat_history), 'next_ai_building_task': self._get_attribute_as_dict(self.next_ai_building_task)}
         return {key: value for key, value in resp.items() if value is not None}
 
     def get(self):