kailash 0.2.2__py3-none-any.whl → 0.3.1__py3-none-any.whl

kailash/nodes/data/retrieval.py

@@ -1,6 +1,6 @@
 """Document retrieval nodes for finding relevant content using various similarity methods."""
 
-from typing import Any, Dict, List
+from typing import Any
 
 from kailash.nodes.base import Node, NodeParameter, register_node
 
@@ -9,7 +9,7 @@ from kailash.nodes.base import Node, NodeParameter, register_node
 class RelevanceScorerNode(Node):
     """Scores chunk relevance using various similarity methods including embeddings similarity."""
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         return {
             "chunks": NodeParameter(
                 name="chunks",
@@ -45,7 +45,7 @@ class RelevanceScorerNode(Node):
             ),
         }
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         chunks = kwargs.get("chunks", [])
         query_embeddings = kwargs.get("query_embedding", [])
         chunk_embeddings = kwargs.get("chunk_embeddings", [])
@@ -98,8 +98,8 @@ class RelevanceScorerNode(Node):
         return {"relevant_chunks": top_chunks}
 
     def _cosine_similarity_scoring(
-        self, chunks: List[Dict], query_embeddings: List, chunk_embeddings: List
-    ) -> List[Dict]:
+        self, chunks: list[dict], query_embeddings: list, chunk_embeddings: list
+    ) -> list[dict]:
         """Score chunks using cosine similarity."""
         # Extract actual embedding vectors from the embedding objects
         # EmbeddingGeneratorNode returns embeddings in format: {"embedding": [...], "text": "...", "dimensions": X}
@@ -131,7 +131,7 @@ class RelevanceScorerNode(Node):
                 return 0.5
 
             try:
-                dot_product = sum(x * y for x, y in zip(a, b))
+                dot_product = sum(x * y for x, y in zip(a, b, strict=False))
                 norm_a = sum(x * x for x in a) ** 0.5
                 norm_b = sum(x * x for x in b) ** 0.5
                 return dot_product / (norm_a * norm_b) if norm_a * norm_b > 0 else 0
@@ -162,16 +162,16 @@ class RelevanceScorerNode(Node):
         return scored_chunks
 
     def _bm25_scoring(
-        self, chunks: List[Dict], query_embeddings: List, chunk_embeddings: List
-    ) -> List[Dict]:
+        self, chunks: list[dict], query_embeddings: list, chunk_embeddings: list
+    ) -> list[dict]:
         """Score chunks using BM25 algorithm (future implementation)."""
         # TODO: Implement BM25 scoring
         # For now, return chunks with default scores
         return [{**chunk, "relevance_score": 0.5} for chunk in chunks]
 
     def _tfidf_scoring(
-        self, chunks: List[Dict], query_embeddings: List, chunk_embeddings: List
-    ) -> List[Dict]:
+        self, chunks: list[dict], query_embeddings: list, chunk_embeddings: list
+    ) -> list[dict]:
         """Score chunks using TF-IDF similarity (future implementation)."""
         # TODO: Implement TF-IDF scoring
         # For now, return chunks with default scores

kailash/nodes/data/sharepoint_graph.py

@@ -23,7 +23,7 @@ Downstream consumers:
 
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any
 
 import requests
 
@@ -79,7 +79,7 @@ class SharePointGraphReader(Node):
             author="Kailash SDK",
         )
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Define input parameters for SharePoint Graph operations."""
         return {
             "tenant_id": NodeParameter(
@@ -149,7 +149,7 @@ class SharePointGraphReader(Node):
 
     def _authenticate(
         self, tenant_id: str, client_id: str, client_secret: str
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """Authenticate with Microsoft Graph API using MSAL.
 
         Returns dict with token and headers for stateless operation.
@@ -184,7 +184,7 @@ class SharePointGraphReader(Node):
             },
         }
 
-    def _get_site_data(self, site_url: str, headers: Dict[str, str]) -> Dict[str, Any]:
+    def _get_site_data(self, site_url: str, headers: dict[str, str]) -> dict[str, Any]:
         """Get SharePoint site data from Graph API."""
         # Convert SharePoint URL to Graph API site ID format
         site_id = site_url.replace("https://", "").replace(
@@ -201,8 +201,8 @@ class SharePointGraphReader(Node):
             )
 
     def _list_libraries(
-        self, site_id: str, headers: Dict[str, str]
-    ) -> List[Dict[str, Any]]:
+        self, site_id: str, headers: dict[str, str]
+    ) -> list[dict[str, Any]]:
         """List all document libraries in the site."""
         drives_url = f"https://graph.microsoft.com/v1.0/sites/{site_id}/drives"
         response = requests.get(drives_url, headers=headers)
@@ -215,8 +215,8 @@ class SharePointGraphReader(Node):
             )
 
     def _get_drive_id(
-        self, site_id: str, library_name: str, headers: Dict[str, str]
-    ) -> Optional[str]:
+        self, site_id: str, library_name: str, headers: dict[str, str]
+    ) -> str | None:
         """Get the drive ID for a specific library."""
         libraries = self._list_libraries(site_id, headers)
         for lib in libraries:
@@ -225,8 +225,8 @@ class SharePointGraphReader(Node):
         return None
 
     def _list_files(
-        self, site_id: str, library_name: str, folder_path: str, headers: Dict[str, str]
-    ) -> Dict[str, Any]:
+        self, site_id: str, library_name: str, folder_path: str, headers: dict[str, str]
+    ) -> dict[str, Any]:
         """List files in a specific library and folder."""
         drive_id = self._get_drive_id(site_id, library_name, headers)
         if not drive_id:
@@ -289,8 +289,8 @@ class SharePointGraphReader(Node):
         file_name: str,
         folder_path: str,
         local_path: str,
-        headers: Dict[str, str],
-    ) -> Dict[str, Any]:
+        headers: dict[str, str],
+    ) -> dict[str, Any]:
         """Download a file from SharePoint."""
         drive_id = self._get_drive_id(site_id, library_name, headers)
         if not drive_id:
@@ -344,8 +344,8 @@ class SharePointGraphReader(Node):
             )
 
     def _search_files(
-        self, site_id: str, library_name: str, query: str, headers: Dict[str, str]
-    ) -> Dict[str, Any]:
+        self, site_id: str, library_name: str, query: str, headers: dict[str, str]
+    ) -> dict[str, Any]:
         """Search for files in a library."""
         drive_id = self._get_drive_id(site_id, library_name, headers)
         if not drive_id:
@@ -383,7 +383,7 @@ class SharePointGraphReader(Node):
                 f"Search failed: {response.status_code} - {response.text}"
             )
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Execute SharePoint Graph operation.
 
         This method is stateless and returns JSON-serializable results
@@ -494,7 +494,7 @@ class SharePointGraphWriter(Node):
             author="Kailash SDK",
         )
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Define input parameters for SharePoint upload operations."""
         return {
             "tenant_id": NodeParameter(
@@ -549,7 +549,7 @@ class SharePointGraphWriter(Node):
             ),
         }
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Execute SharePoint upload operation."""
         # Validate required parameters
         tenant_id = kwargs.get("tenant_id")

kailash/nodes/data/sources.py

@@ -1,6 +1,6 @@
 """Data source nodes for providing input data to workflows."""
 
-from typing import Any, Dict
+from typing import Any
 
 from kailash.nodes.base import Node, NodeParameter, register_node
 
@@ -9,7 +9,7 @@ from kailash.nodes.base import Node, NodeParameter, register_node
 class DocumentSourceNode(Node):
     """Provides sample documents for hierarchical RAG processing."""
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         return {
             "sample_documents": NodeParameter(
                 name="sample_documents",
@@ -20,7 +20,7 @@ class DocumentSourceNode(Node):
             )
         }
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         # Sample documents for demonstration
         documents = [
             {
@@ -48,7 +48,7 @@ class DocumentSourceNode(Node):
 class QuerySourceNode(Node):
     """Provides sample queries for RAG processing."""
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         return {
             "query": NodeParameter(
                 name="query",
@@ -59,7 +59,7 @@ class QuerySourceNode(Node):
             )
         }
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         query = kwargs.get("query", "What are the main types of machine learning?")
         print(f"Debug QuerySource: providing query='{query}'")
         return {"query": query}

kailash/nodes/data/sql.py

@@ -16,7 +16,7 @@ import os
 import threading
 import time
 from datetime import datetime
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Optional
 
 import yaml
 from sqlalchemy import create_engine, text
@@ -38,7 +38,7 @@ class SQLDatabaseNode(Node):
             self.config_path = project_config_path
             self.config = self._load_project_config()
 
-        def _load_project_config(self) -> Dict[str, Any]:
+        def _load_project_config(self) -> dict[str, Any]:
             """Load project configuration from YAML file."""
             if not os.path.exists(self.config_path):
                 raise NodeExecutionError(
@@ -46,7 +46,7 @@ class SQLDatabaseNode(Node):
                 )
 
             try:
-                with open(self.config_path, "r") as f:
+                with open(self.config_path) as f:
                     config = yaml.safe_load(f)
                     return config or {}
             except yaml.YAMLError as e:
@@ -56,7 +56,7 @@ class SQLDatabaseNode(Node):
 
         def get_database_config(
             self, connection_name: str
-        ) -> Tuple[str, Dict[str, Any]]:
+        ) -> tuple[str, dict[str, Any]]:
             """Get database configuration by connection name.
 
             Args:
@@ -185,8 +185,8 @@ class SQLDatabaseNode(Node):
     """
 
     # Class-level shared resources for connection pooling
-    _shared_pools: Dict[Tuple[str, frozenset], Any] = {}
-    _pool_metrics: Dict[Tuple[str, frozenset], Dict[str, Any]] = {}
+    _shared_pools: dict[tuple[str, frozenset], Any] = {}
+    _pool_metrics: dict[tuple[str, frozenset], dict[str, Any]] = {}
     _pool_lock = threading.Lock()
     _config_manager: Optional["SQLDatabaseNode._DatabaseConfigManager"] = None
 
@@ -252,7 +252,7 @@ class SQLDatabaseNode(Node):
         # Call parent constructor
         super().__init__(**kwargs)
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Define input parameters for SQL execution.
 
         Configuration parameters (provided to constructor):
@@ -334,7 +334,7 @@ class SQLDatabaseNode(Node):
 
             return self._shared_pools[cache_key]
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Execute SQL query using shared connection pool.
 
         Args:
@@ -458,7 +458,7 @@ class SQLDatabaseNode(Node):
         }
 
     @classmethod
-    def get_pool_status(cls) -> Dict[str, Any]:
+    def get_pool_status(cls) -> dict[str, Any]:
         """Get status of all shared connection pools."""
         with cls._pool_lock:
             status = {}
@@ -736,7 +736,7 @@ class SQLDatabaseNode(Node):
 
         return sanitized
 
-    def _convert_to_named_parameters(self, query: str, parameters: List) -> tuple:
+    def _convert_to_named_parameters(self, query: str, parameters: list) -> tuple:
         """Convert positional parameters to named parameters for SQLAlchemy 2.0.
 
         Args:
@@ -790,8 +790,8 @@ class SQLDatabaseNode(Node):
         return modified_query, param_dict
 
     def _format_results(
-        self, rows: List, columns: List[str], result_format: str
-    ) -> List[Any]:
+        self, rows: list, columns: list[str], result_format: str
+    ) -> list[Any]:
         """Format query results according to specified format.
 
         Args:
@@ -820,4 +820,4 @@ class SQLDatabaseNode(Node):
             self.logger.warning(
                 f"Unknown result_format '{result_format}', defaulting to 'dict'"
             )
-            return [dict(zip(columns, row)) for row in rows]
+            return [dict(zip(columns, row, strict=False)) for row in rows]

kailash/nodes/data/streaming.py

@@ -44,7 +44,7 @@ Example:
 """
 
 import time
-from typing import Any, Dict, List
+from typing import Any
 
 from kailash.nodes.base import Node, NodeMetadata, NodeParameter, register_node
 from kailash.sdk_exceptions import NodeConfigurationError, NodeExecutionError
@@ -148,7 +148,7 @@ class KafkaConsumerNode(Node):
         self._consumer = None
         self._topic = None
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Define parameters for the Kafka consumer node."""
         return {
             "bootstrap_servers": NodeParameter(
@@ -206,7 +206,7 @@ class KafkaConsumerNode(Node):
             ),
         }
 
-    def configure(self, config: Dict[str, Any]) -> None:
+    def configure(self, config: dict[str, Any]) -> None:
         """Configure the Kafka consumer.
 
         Creates and configures the Kafka consumer with the specified
@@ -241,7 +241,7 @@ class KafkaConsumerNode(Node):
         self._consumer = f"kafka_consumer_{self.config['group_id']}"
         self._topic = self.config["topic"]
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Consume messages from Kafka.
 
         Implementation of the abstract run method from the base Node class.
@@ -254,7 +254,7 @@ class KafkaConsumerNode(Node):
         """
         return self.execute(kwargs)
 
-    def execute(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+    def execute(self, inputs: dict[str, Any]) -> dict[str, Any]:
         """Consume messages from Kafka.
 
         Polls for messages up to the specified limit or timeout.
@@ -286,7 +286,7 @@ class KafkaConsumerNode(Node):
         except Exception as e:
             raise NodeExecutionError(f"Failed to consume messages: {str(e)}")
 
-    def _consume_messages(self, max_messages: int, timeout_ms: int) -> List[Dict]:
+    def _consume_messages(self, max_messages: int, timeout_ms: int) -> list[dict]:
         """Consume messages from Kafka.
 
         This is a placeholder for actual message consumption logic.
@@ -420,7 +420,7 @@ class StreamPublisherNode(Node):
         self._publisher = None
         self._protocol = None
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Define parameters for the stream publisher node."""
         return {
             "protocol": NodeParameter(
@@ -465,7 +465,7 @@ class StreamPublisherNode(Node):
             ),
         }
 
-    def configure(self, config: Dict[str, Any]) -> None:
+    def configure(self, config: dict[str, Any]) -> None:
         """Configure the stream publisher.
 
         Creates the appropriate publisher based on the protocol.
@@ -499,7 +499,7 @@ class StreamPublisherNode(Node):
         # Placeholder for actual publisher creation
         self._publisher = f"{self._protocol}_publisher"
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Publish messages to the streaming platform.
 
         Implementation of the abstract run method from the base Node class.
@@ -512,7 +512,7 @@ class StreamPublisherNode(Node):
         """
         return self.execute(kwargs)
 
-    def execute(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+    def execute(self, inputs: dict[str, Any]) -> dict[str, Any]:
         """Publish messages to the streaming platform.
 
         Args:
@@ -541,7 +541,7 @@ class StreamPublisherNode(Node):
         except Exception as e:
             raise NodeExecutionError(f"Failed to publish messages: {str(e)}")
 
-    def _publish_messages(self, messages: List[Dict], headers: Dict) -> Dict[str, Any]:
+    def _publish_messages(self, messages: list[dict], headers: dict) -> dict[str, Any]:
         """Publish messages to the stream.
 
         This is a placeholder for actual publishing logic.
@@ -683,7 +683,7 @@ class WebSocketNode(Node):
         self._connected = False
         self._message_queue = []
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Get the parameters for this node.
 
         Returns:
@@ -750,7 +750,7 @@ class WebSocketNode(Node):
             ),
         }
 
-    def configure(self, config: Dict[str, Any]) -> None:
+    def configure(self, config: dict[str, Any]) -> None:
         """Configure the WebSocket connection.
 
         Validates the URL and prepares connection parameters.
@@ -770,7 +770,7 @@ class WebSocketNode(Node):
         if not url.startswith(("ws://", "wss://")):
             raise NodeConfigurationError("URL must start with ws:// or wss://")
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Run the WebSocket node.
 
         This method fulfills the abstract run method requirement from the base Node class.
@@ -786,7 +786,7 @@ class WebSocketNode(Node):
         """
         return self.execute(kwargs)
 
-    def execute(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+    def execute(self, inputs: dict[str, Any]) -> dict[str, Any]:
         """Execute WebSocket operations.
 
         Performs the requested action (connect, send, receive, disconnect).
@@ -816,7 +816,7 @@ class WebSocketNode(Node):
         except Exception as e:
             raise NodeExecutionError(f"WebSocket operation failed: {str(e)}")
 
-    def _connect(self) -> Dict[str, Any]:
+    def _connect(self) -> dict[str, Any]:
         """Connect to the WebSocket server.
 
         Returns:
@@ -832,7 +832,7 @@ class WebSocketNode(Node):
             "metadata": {"timestamp": time.time()},
         }
 
-    def _send_message(self, message: Any) -> Dict[str, Any]:
+    def _send_message(self, message: Any) -> dict[str, Any]:
         """Send a message through the WebSocket.
 
         Args:
@@ -851,7 +851,7 @@ class WebSocketNode(Node):
             "metadata": {"timestamp": time.time()},
         }
 
-    def _receive_messages(self, timeout: float) -> Dict[str, Any]:
+    def _receive_messages(self, timeout: float) -> dict[str, Any]:
         """Receive messages from the WebSocket.
 
         Args:
@@ -877,7 +877,7 @@ class WebSocketNode(Node):
             "metadata": {"count": len(messages), "timeout": timeout},
         }
 
-    def _disconnect(self) -> Dict[str, Any]:
+    def _disconnect(self) -> dict[str, Any]:
         """Disconnect from the WebSocket server.
 
         Returns:
@@ -994,7 +994,7 @@ class EventStreamNode(Node):
         self._connected = False
         self._last_event_id = None
 
-    def get_parameters(self) -> Dict[str, NodeParameter]:
+    def get_parameters(self) -> dict[str, NodeParameter]:
         """Get the parameters for this node.
 
         Returns:
@@ -1048,7 +1048,7 @@ class EventStreamNode(Node):
             ),
         }
 
-    def run(self, **kwargs) -> Dict[str, Any]:
+    def run(self, **kwargs) -> dict[str, Any]:
         """Run the EventStream node.
 
         This method fulfills the abstract run method requirement from the base Node class.
@@ -1064,7 +1064,7 @@ class EventStreamNode(Node):
         """
         return self.execute(kwargs)
 
-    def execute(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+    def execute(self, inputs: dict[str, Any]) -> dict[str, Any]:
         """Execute EventStream operations.
 
         Args:
@@ -1090,7 +1090,7 @@ class EventStreamNode(Node):
         except Exception as e:
             raise NodeExecutionError(f"EventStream operation failed: {str(e)}")
 
-    def _start_stream(self) -> Dict[str, Any]:
+    def _start_stream(self) -> dict[str, Any]:
         """Start the event stream connection.
 
         Returns:
@@ -1106,7 +1106,7 @@ class EventStreamNode(Node):
             "metadata": {"timestamp": time.time()},
         }
 
-    def _stop_stream(self) -> Dict[str, Any]:
+    def _stop_stream(self) -> dict[str, Any]:
         """Stop the event stream connection.
 
         Returns:
@@ -1124,7 +1124,7 @@ class EventStreamNode(Node):
             },
         }
 
-    def _receive_events(self, max_events: int) -> Dict[str, Any]:
+    def _receive_events(self, max_events: int) -> dict[str, Any]:
         """Receive events from the stream.
 
         Args: