Version 1.4.48

Author: yogesh-abacusai

abacusai/__init__.py

@@ -253,6 +253,8 @@
 from .use_case_requirements import UseCaseRequirements
 from .user import User
 from .user_exception import UserException
+from .video_gen_model import VideoGenModel
+from .video_gen_model_options import VideoGenModelOptions
 from .video_gen_settings import VideoGenSettings
 from .video_search_result import VideoSearchResult
 from .voice_gen_details import VoiceGenDetails
@@ -265,4 +267,4 @@
 from .workflow_node_template import WorkflowNodeTemplate
 
 
-__version__ = "1.4.47"
+__version__ = "1.4.48"

abacusai/api_class/dataset_application_connector.py

@@ -30,15 +30,14 @@ class ConfluenceDatasetConfig(ApplicationConnectorDatasetConfig):
     Dataset config for Confluence Application Connector
     Args:
         location (str): The location of the pages to fetch
-        space_key (str): The space key of the space from which we fetch pages
         pull_attachments (bool): Whether to pull attachments for each page
         extract_bounding_boxes (bool): Whether to extract bounding boxes from the documents
-
+        location_type (str): The type of location to be fetched. Maps values in `location` to content type, example: 'spaceKey/folderTitle/*' -> 'folder'
     """
     location: str = dataclasses.field(default=None)
-    space_key: str = dataclasses.field(default=None)
     pull_attachments: bool = dataclasses.field(default=False)
     extract_bounding_boxes: bool = dataclasses.field(default=False)  # TODO: Deprecate in favour of document_processing_config
+    location_type: str = dataclasses.field(default=None)
 
     def __post_init__(self):
         self.application_connector_type = enums.ApplicationConnectorType.CONFLUENCE
@@ -106,9 +105,15 @@ class JiraDatasetConfig(ApplicationConnectorDatasetConfig):
 
     Args:
         jql (str): The JQL query for fetching issues
+        custom_fields (list): A list of custom fields to include in the dataset
+        include_comments (bool): Fetch comments for each issue
+        include_watchers (bool): Fetch watchers for each issue
 
     """
     jql: str = dataclasses.field(default=None)
+    custom_fields: list = dataclasses.field(default=None)
+    include_comments: bool = dataclasses.field(default=False)
+    include_watchers: bool = dataclasses.field(default=False)
 
     def __post_init__(self):
         self.application_connector_type = enums.ApplicationConnectorType.JIRA

abacusai/api_class/enums.py

@@ -507,6 +507,8 @@ class LLMName(ApiEnum):
     CLAUDE_V3_HAIKU = 'CLAUDE_V3_HAIKU'
     CLAUDE_V3_5_SONNET = 'CLAUDE_V3_5_SONNET'
     CLAUDE_V3_7_SONNET = 'CLAUDE_V3_7_SONNET'
+    CLAUDE_V4_SONNET = 'CLAUDE_V4_SONNET'
+    CLAUDE_V4_OPUS = 'CLAUDE_V4_OPUS'
     CLAUDE_V3_5_HAIKU = 'CLAUDE_V3_5_HAIKU'
     GEMINI_1_5_PRO = 'GEMINI_1_5_PRO'
     GEMINI_2_FLASH = 'GEMINI_2_FLASH'

abacusai/chatllm_task.py

@@ -8,36 +8,42 @@ class ChatllmTask(AbstractApiClass):
         Args:
             client (ApiClient): An authenticated API Client instance
             chatllmTaskId (str): The id of the chatllm task.
+            daemonTaskId (str): The id of the daemon task.
+            taskType (str): The type of task ('chatllm' or 'daemon').
             name (str): The name of the chatllm task.
             instructions (str): The instructions of the chatllm task.
             lifecycle (str): The lifecycle of the chatllm task.
             scheduleInfo (dict): The schedule info of the chatllm task.
             externalApplicationId (str): The external application id associated with the chatllm task.
             deploymentConversationId (str): The deployment conversation id associated with the chatllm task.
+            sourceDeploymentConversationId (str): The source deployment conversation id associated with the chatllm task.
             enableEmailAlerts (bool): Whether email alerts are enabled for the chatllm task.
             email (str): The email to send alerts to.
             numUnreadTaskInstances (int): The number of unread task instances for the chatllm task.
             computePointsUsed (int): The compute points used for the chatllm task.
     """
 
-    def __init__(self, client, chatllmTaskId=None, name=None, instructions=None, lifecycle=None, scheduleInfo=None, externalApplicationId=None, deploymentConversationId=None, enableEmailAlerts=None, email=None, numUnreadTaskInstances=None, computePointsUsed=None):
+    def __init__(self, client, chatllmTaskId=None, daemonTaskId=None, taskType=None, name=None, instructions=None, lifecycle=None, scheduleInfo=None, externalApplicationId=None, deploymentConversationId=None, sourceDeploymentConversationId=None, enableEmailAlerts=None, email=None, numUnreadTaskInstances=None, computePointsUsed=None):
         super().__init__(client, chatllmTaskId)
         self.chatllm_task_id = chatllmTaskId
+        self.daemon_task_id = daemonTaskId
+        self.task_type = taskType
         self.name = name
         self.instructions = instructions
         self.lifecycle = lifecycle
         self.schedule_info = scheduleInfo
         self.external_application_id = externalApplicationId
         self.deployment_conversation_id = deploymentConversationId
+        self.source_deployment_conversation_id = sourceDeploymentConversationId
         self.enable_email_alerts = enableEmailAlerts
         self.email = email
         self.num_unread_task_instances = numUnreadTaskInstances
         self.compute_points_used = computePointsUsed
         self.deprecated_keys = {}
 
     def __repr__(self):
-        repr_dict = {f'chatllm_task_id': repr(self.chatllm_task_id), f'name': repr(self.name), f'instructions': repr(self.instructions), f'lifecycle': repr(self.lifecycle), f'schedule_info': repr(self.schedule_info), f'external_application_id': repr(self.external_application_id), f'deployment_conversation_id': repr(
-            self.deployment_conversation_id), f'enable_email_alerts': repr(self.enable_email_alerts), f'email': repr(self.email), f'num_unread_task_instances': repr(self.num_unread_task_instances), f'compute_points_used': repr(self.compute_points_used)}
+        repr_dict = {f'chatllm_task_id': repr(self.chatllm_task_id), f'daemon_task_id': repr(self.daemon_task_id), f'task_type': repr(self.task_type), f'name': repr(self.name), f'instructions': repr(self.instructions), f'lifecycle': repr(self.lifecycle), f'schedule_info': repr(self.schedule_info), f'external_application_id': repr(self.external_application_id), f'deployment_conversation_id': repr(
+            self.deployment_conversation_id), f'source_deployment_conversation_id': repr(self.source_deployment_conversation_id), f'enable_email_alerts': repr(self.enable_email_alerts), f'email': repr(self.email), f'num_unread_task_instances': repr(self.num_unread_task_instances), f'compute_points_used': repr(self.compute_points_used)}
         class_name = "ChatllmTask"
         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])
@@ -50,6 +56,6 @@ def to_dict(self):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        resp = {'chatllm_task_id': self.chatllm_task_id, 'name': self.name, 'instructions': self.instructions, 'lifecycle': self.lifecycle, 'schedule_info': self.schedule_info, 'external_application_id': self.external_application_id,
-                'deployment_conversation_id': self.deployment_conversation_id, 'enable_email_alerts': self.enable_email_alerts, 'email': self.email, 'num_unread_task_instances': self.num_unread_task_instances, 'compute_points_used': self.compute_points_used}
+        resp = {'chatllm_task_id': self.chatllm_task_id, 'daemon_task_id': self.daemon_task_id, 'task_type': self.task_type, 'name': self.name, 'instructions': self.instructions, 'lifecycle': self.lifecycle, 'schedule_info': self.schedule_info, 'external_application_id': self.external_application_id,
+                'deployment_conversation_id': self.deployment_conversation_id, 'source_deployment_conversation_id': self.source_deployment_conversation_id, 'enable_email_alerts': self.enable_email_alerts, 'email': self.email, 'num_unread_task_instances': self.num_unread_task_instances, 'compute_points_used': self.compute_points_used}
         return {key: value for key, value in resp.items() if value is not None and key not in self.deprecated_keys}

abacusai/client.py

@@ -661,7 +661,7 @@ 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 = '1.4.47'
+    client_version = '1.4.48'
 
     def __init__(self, api_key: str = None, server: str = None, client_options: ClientOptions = None, skip_version_check: bool = False, include_tb: bool = False):
         self.api_key = api_key
@@ -855,8 +855,9 @@ def _proxy_request(self, name: str, method: str = 'POST', query_params: dict = N
         headers = {'APIKEY': self.api_key}
         deployment_id = os.getenv('ABACUS_EXEC_SERVICE_DEPLOYMENT_ID')
         if deployment_id:
-            query_params = {**(query_params or {}),
-                            'environmentDeploymentId': deployment_id}
+            if not (query_params or {}).get('deploymentId') or deployment_id == (query_params or {}).get('deploymentId'):
+                query_params = {**(query_params or {}),
+                                'environmentDeploymentId': deployment_id}
         caller = self._get_agent_caller()
         request_id = self._get_agent_app_request_id()
         if caller and request_id:
@@ -870,7 +871,7 @@ def _proxy_request(self, name: str, method: str = 'POST', query_params: dict = N
                 self, _request_context, 'deployment_id', str)
             if hashed_deployment_id:
                 query_params = {**(query_params or {}),
-                                'deploymentId': hashed_deployment_id}
+                                'billingDeploymentId': hashed_deployment_id}
             user_info = get_object_from_context(
                 self, _request_context, 'user_info', dict)
             if user_info:
@@ -7836,9 +7837,7 @@ def execute_agent(self, deployment_token: str, deployment_id: str, arguments: li
             deployment_id (str): A unique string identifier for the deployment created under the project.
             arguments (list): Positional arguments to the agent execute function.
             keyword_arguments (dict): A dictionary where each 'key' represents the paramter name and its corresponding 'value' represents the value of that parameter for the agent execute function."""
-        prediction_url = self._get_prediction_endpoint(
-            deployment_id, deployment_token) if deployment_token else None
-        return self._call_api('executeAgent', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, body={'arguments': arguments, 'keywordArguments': keyword_arguments}, server_override=prediction_url, timeout=1500)
+        return self._proxy_request('executeAgent', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, body={'arguments': arguments, 'keywordArguments': keyword_arguments}, is_sync=True)
 
     def get_matrix_agent_schema(self, deployment_token: str, deployment_id: str, query: str, doc_infos: list = None, deployment_conversation_id: str = None, external_session_id: str = None) -> Dict:
         """Executes a deployed AI agent function using the arguments as keyword arguments to the agent execute function.
@@ -7867,9 +7866,7 @@ def execute_conversation_agent(self, deployment_token: str, deployment_id: str,
             regenerate (bool): If True, will regenerate the response from the last query.
             doc_infos (list): An optional list of documents use for the conversation. A keyword 'doc_id' is expected to be present in each document for retrieving contents from docstore.
             agent_workflow_node_id (str): An optional agent workflow node id to trigger agent execution from an intermediate node."""
-        prediction_url = self._get_prediction_endpoint(
-            deployment_id, deployment_token) if deployment_token else None
-        return self._call_api('executeConversationAgent', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, body={'arguments': arguments, 'keywordArguments': keyword_arguments, 'deploymentConversationId': deployment_conversation_id, 'externalSessionId': external_session_id, 'regenerate': regenerate, 'docInfos': doc_infos, 'agentWorkflowNodeId': agent_workflow_node_id}, server_override=prediction_url)
+        return self._proxy_request('executeSyncConversationAgent', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, body={'arguments': arguments, 'keywordArguments': keyword_arguments, 'deploymentConversationId': deployment_conversation_id, 'externalSessionId': external_session_id, 'regenerate': regenerate, 'docInfos': doc_infos, 'agentWorkflowNodeId': agent_workflow_node_id}, is_sync=True)
 
     def lookup_matches(self, deployment_token: str, deployment_id: str, data: str = None, filters: dict = None, num: int = None, result_columns: list = None, max_words: int = None, num_retrieval_margin_words: int = None, max_words_per_chunk: int = None, score_multiplier_column: str = None, min_score: float = None, required_phrases: list = None, filter_clause: str = None, crowding_limits: dict = None, include_text_search: bool = False) -> List[DocumentRetrieverLookupResult]:
         """Lookup document retrievers and return the matching documents from the document retriever deployed with given query.
@@ -7913,7 +7910,7 @@ def get_completion(self, deployment_token: str, deployment_id: str, prompt: str)
             deployment_id, deployment_token) if deployment_token else None
         return self._call_api('getCompletion', 'POST', query_params={'deploymentToken': deployment_token, 'deploymentId': deployment_id}, body={'prompt': prompt}, server_override=prediction_url)
 
-    def execute_agent_with_binary_data(self, deployment_token: str, deployment_id: str, arguments: list = None, keyword_arguments: dict = None, deployment_conversation_id: str = None, external_session_id: str = None, blobs: None = None) -> Dict:
+    def execute_agent_with_binary_data(self, deployment_token: str, deployment_id: str, arguments: list = None, keyword_arguments: dict = None, deployment_conversation_id: str = None, external_session_id: str = None, blobs: None = None) -> AgentDataExecutionResult:
         """Executes a deployed AI agent function with binary data as inputs.
 
         Args:
@@ -7927,9 +7924,7 @@ def execute_agent_with_binary_data(self, deployment_token: str, deployment_id: s
 
         Returns:
             AgentDataExecutionResult: The result of the agent execution"""
-        prediction_url = self._get_prediction_endpoint(
-            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)
+        return self._proxy_request('executeAgentWithBinaryData', 'POST', query_params={}, data={'deploymentToken': deployment_token, 'deploymentId': deployment_id, 'arguments': arguments, 'keywordArguments': json.dumps(keyword_arguments.to_dict()) if hasattr(keyword_arguments, 'to_dict') else json.dumps(keyword_arguments), 'deploymentConversationId': deployment_conversation_id, 'externalSessionId': external_session_id}, files=blobs, parse_type=AgentDataExecutionResult, is_sync=True)
 
     def start_autonomous_agent(self, deployment_token: str, deployment_id: str, arguments: list = None, keyword_arguments: dict = None, save_conversations: bool = True) -> Dict:
         """Starts a deployed Autonomous agent associated with the given deployment_conversation_id using the arguments and keyword arguments as inputs for execute function of trigger node.