kailash 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

kailash/nodes/base.py

@@ -214,24 +214,23 @@ class Node(ABC):
         - During workflow creation: Used for connection validation
         - During export: Included in workflow manifests
 
-        Example::
-
-            def get_parameters(self):
-                return {
-                    'input_file': NodeParameter(
-                        name='input_file',
-                        type=str,
-                        required=True,
-                        description='Path to input CSV file'
-                    ),
-                    'delimiter': NodeParameter(
-                        name='delimiter',
-                        type=str,
-                        required=False,
-                        default=',',
-                        description='CSV delimiter character'
-                    )
-                }
+        Example:
+            >>> def get_parameters(self):
+            ...     return {
+            ...         'input_file': NodeParameter(
+            ...             name='input_file',
+            ...             type=str,
+            ...             required=True,
+            ...             description='Path to input CSV file'
+            ...         ),
+            ...         'delimiter': NodeParameter(
+            ...             name='delimiter',
+            ...             type=str,
+            ...             required=False,
+            ...             default=',',
+            ...             description='CSV delimiter character'
+            ...         )
+            ...     }
 
         Returns:
             Dictionary mapping parameter names to their definitions
@@ -265,29 +264,28 @@ class Node(ABC):
         3. Workflow connection validation
         4. Export manifest generation
 
-        Example::
-
-            def get_output_schema(self):
-                return {
-                    'dataframe': NodeParameter(
-                        name='dataframe',
-                        type=dict,
-                        required=True,
-                        description='Processed data as dictionary'
-                    ),
-                    'row_count': NodeParameter(
-                        name='row_count',
-                        type=int,
-                        required=True,
-                        description='Number of rows processed'
-                    ),
-                    'processing_time': NodeParameter(
-                        name='processing_time',
-                        type=float,
-                        required=False,
-                        description='Time taken to process in seconds'
-                    )
-                }
+        Example:
+            >>> def get_output_schema(self):
+            ...     return {
+            ...         'dataframe': NodeParameter(
+            ...             name='dataframe',
+            ...             type=dict,
+            ...             required=True,
+            ...             description='Processed data as dictionary'
+            ...         ),
+            ...         'row_count': NodeParameter(
+            ...             name='row_count',
+            ...             type=int,
+            ...             required=True,
+            ...             description='Number of rows processed'
+            ...         ),
+            ...         'processing_time': NodeParameter(
+            ...             name='processing_time',
+            ...             type=float,
+            ...             required=False,
+            ...             description='Time taken to process in seconds'
+            ...         )
+            ...     }
 
         Returns:
             Dictionary mapping output names to their parameter definitions
@@ -325,15 +323,14 @@ class Node(ABC):
         - Error wrapping and logging
         - Execution timing and metrics
 
-        Example::
-
-            def run(self, input_file, delimiter=','):
-                df = pd.read_csv(input_file, delimiter=delimiter)
-                return {
-                    'dataframe': df.to_dict(),
-                    'row_count': len(df),
-                    'columns': list(df.columns)
-                }
+        Example:
+            >>> def run(self, input_file, delimiter=','):
+            ...     df = pd.read_csv(input_file, delimiter=delimiter)
+            ...     return {
+            ...         'dataframe': df.to_dict(),
+            ...         'row_count': len(df),
+            ...         'columns': list(df.columns)
+            ...     }
 
         Args:
             **kwargs: Validated input parameters matching get_parameters()
@@ -1010,11 +1007,11 @@ class NodeRegistry:
             - Logs the clearing action
             - Existing node instances remain valid
 
-        Warning::
-
-        - Subsequent get() calls will fail
-        - Workflows may not deserialize
-        - Should re-register needed nodes
+        Warning:
+            >>> # Warning: This affects all future operations
+            >>> # - Subsequent get() calls will fail
+            >>> # - Workflows may not deserialize
+            >>> # - Should re-register needed nodes
         """
         cls._nodes.clear()
         logging.info("Cleared all registered nodes")
@@ -1057,15 +1054,14 @@ def register_node(alias: Optional[str] = None):
         - Returns the unmodified class
         - Handles registration errors
 
-    Example::
-
-        @register_node(alias='CSV')
-        class CSVReaderNode(Node):
-            def get_parameters(self):
-                return {'file': NodeParameter(...)}
-
-            def run(self, file):
-                return pd.read_csv(file)
+    Example:
+        >>> @register_node(alias='CSV')
+        ... class CSVReaderNode(Node):
+        ...     def get_parameters(self):
+        ...         return {'file': NodeParameter(...)}
+        ...
+        ...     def run(self, file):
+        ...         return pd.read_csv(file)
     """
 
     def decorator(node_class: Type[Node]):

kailash/nodes/code/python.py

@@ -144,6 +144,7 @@ class CodeExecutor:
             "filter",
             "float",
             "int",
+            "isinstance",  # Common type checking
             "len",
             "list",
             "map",
@@ -546,48 +547,47 @@ class PythonCodeNode(Node):
     - State management for class-based nodes
     - AST-based security validation
 
-    Example::
-
-        # Function-based node
-        def custom_filter(data: pd.DataFrame, threshold: float) -> pd.DataFrame:
-            return data[data['value'] > threshold]
-
-        node = PythonCodeNode.from_function(
-            func=custom_filter,
-            name="threshold_filter"
-        )
-
-        # Class-based stateful node
-        class MovingAverage:
-            def __init__(self, window_size: int = 3):
-                self.window_size = window_size
-                self.values = []
-
-            def process(self, value: float) -> float:
-                self.values.append(value)
-                if len(self.values) > self.window_size:
-                    self.values.pop(0)
-                return sum(self.values) / len(self.values)
-
-        node = PythonCodeNode.from_class(
-            cls=MovingAverage,
-            name="moving_avg"
-        )
-
-        # Code string node
-        code = '''
-        result = []
-        for item in data:
-            if item > threshold:
-                result.append(item * 2)
-        '''
-
-        node = PythonCodeNode(
-            name="custom_processor",
-            code=code,
-            input_types={'data': list, 'threshold': float},
-            output_type=list
-        )
+    Example:
+        >>> # Function-based node
+        >>> def custom_filter(data: pd.DataFrame, threshold: float) -> pd.DataFrame:
+        ...     return data[data['value'] > threshold]
+
+        >>> node = PythonCodeNode.from_function(
+        ...     func=custom_filter,
+        ...     name="threshold_filter"
+        ... )
+
+        >>> # Class-based stateful node
+        >>> class MovingAverage:
+        ...     def __init__(self, window_size: int = 3):
+        ...         self.window_size = window_size
+        ...         self.values = []
+        ...
+        ...     def process(self, value: float) -> float:
+        ...         self.values.append(value)
+        ...         if len(self.values) > self.window_size:
+        ...             self.values.pop(0)
+        ...         return sum(self.values) / len(self.values)
+
+        >>> node = PythonCodeNode.from_class(
+        ...     cls=MovingAverage,
+        ...     name="moving_avg"
+        ... )
+
+        >>> # Code string node
+        >>> code = '''
+        ... result = []
+        ... for item in data:
+        ...     if item > threshold:
+        ...         result.append(item * 2)
+        ... '''
+
+        >>> node = PythonCodeNode(
+        ...     name="custom_processor",
+        ...     code=code,
+        ...     input_types={'data': list, 'threshold': float},
+        ...     output_type=list
+        ... )
     """
 
     def __init__(
@@ -727,6 +727,25 @@ class PythonCodeNode(Node):
 
         return parameters
 
+    def validate_inputs(self, **kwargs) -> Dict[str, Any]:
+        """Validate runtime inputs.
+
+        For code-based nodes, we accept any inputs since the code
+        can use whatever variables it needs.
+
+        Args:
+            **kwargs: Runtime inputs
+
+        Returns:
+            All inputs as-is for code nodes, validated inputs for function/class nodes
+        """
+        # If using code string, pass through all inputs
+        if self.code:
+            return kwargs
+
+        # Otherwise use standard validation for function/class nodes
+        return super().validate_inputs(**kwargs)
+
     def get_output_schema(self) -> Dict[str, "NodeParameter"]:
         """Define output parameters for this node.
 

kailash/nodes/data/__init__.py

@@ -57,9 +57,9 @@ All nodes provide detailed error messages for:
 Example Workflows:
     # Traditional ETL
     workflow = Workflow()
-    workflow.add_node('read', CSVReader(file_path='input.csv'))
+    workflow.add_node('read', CSVReaderNode(file_path='input.csv'))
     workflow.add_node('transform', DataTransform())
-    workflow.add_node('write', JSONWriter(file_path='output.json'))
+    workflow.add_node('write', JSONWriterNode(file_path='output.json'))
     workflow.connect('read', 'transform')
     workflow.connect('transform', 'write')
 
@@ -80,7 +80,7 @@ Example Workflows:
     workflow.connect('process', 'publish')
 """
 
-from kailash.nodes.data.readers import CSVReader, JSONReader, TextReader
+from kailash.nodes.data.readers import CSVReaderNode, JSONReaderNode, TextReaderNode
 from kailash.nodes.data.retrieval import RelevanceScorerNode
 from kailash.nodes.data.sharepoint_graph import (
     SharePointGraphReader,
@@ -99,18 +99,18 @@ from kailash.nodes.data.vector_db import (
     TextSplitterNode,
     VectorDatabaseNode,
 )
-from kailash.nodes.data.writers import CSVWriter, JSONWriter, TextWriter
+from kailash.nodes.data.writers import CSVWriterNode, JSONWriterNode, TextWriterNode
 
 __all__ = [
     # Readers
-    "CSVReader",
-    "JSONReader",
-    "TextReader",
+    "CSVReaderNode",
+    "JSONReaderNode",
+    "TextReaderNode",
     "SharePointGraphReader",
     # Writers
-    "CSVWriter",
-    "JSONWriter",
-    "TextWriter",
+    "CSVWriterNode",
+    "JSONWriterNode",
+    "TextWriterNode",
     "SharePointGraphWriter",
     # Sources
     "DocumentSourceNode",

kailash/nodes/data/readers.py

@@ -12,9 +12,9 @@ Design Philosophy:
 5. Type-safe parameter validation
 
 Node Categories:
-- CSVReader: Tabular data from CSV files
-- JSONReader: Structured data from JSON files
-- TextReader: Raw text from any text file
+- CSVReaderNode: Tabular data from CSV files
+- JSONReaderNode: Structured data from JSON files
+- TextReaderNode: Raw text from any text file
 
 Upstream Components:
 - FileSystem: Provides files to read
@@ -36,7 +36,7 @@ from kailash.nodes.base import Node, NodeParameter, register_node
 
 
 @register_node()
-class CSVReader(Node):
+class CSVReaderNode(Node):
     """Reads data from a CSV file.
 
     This node provides robust CSV file reading capabilities with support for
@@ -78,19 +78,18 @@ class CSVReader(Node):
     - UnicodeDecodeError: Encoding mismatch
     - csv.Error: Malformed CSV data
 
-    Example::
-
-        # Read customer data with headers
-        reader = CSVReader(
-            file_path='customers.csv',
-            headers=True,
-            delimiter=','
-        )
-        result = reader.execute()
-        # result['data'] = [
-        #     {'id': '1', 'name': 'John', 'age': '30'},
-        #     {'id': '2', 'name': 'Jane', 'age': '25'}
-        # ]
+    Example:
+        >>> # Read customer data with headers
+        >>> reader = CSVReaderNode(
+        ...     file_path='customers.csv',
+        ...     headers=True,
+        ...     delimiter=','
+        ... )
+        >>> result = reader.execute()
+        >>> # result['data'] = [
+        >>> #     {'id': '1', 'name': 'John', 'age': '30'},
+        >>> #     {'id': '2', 'name': 'Jane', 'age': '25'}
+        >>> # ]
     """
 
     def get_parameters(self) -> Dict[str, NodeParameter]:
@@ -235,7 +234,7 @@ class CSVReader(Node):
 
 
 @register_node()
-class JSONReader(Node):
+class JSONReaderNode(Node):
     """Reads data from a JSON file.
 
     This node handles JSON file reading with support for complex nested
@@ -280,7 +279,7 @@ class JSONReader(Node):
 
     Example:
         # Read API response data
-        reader = JSONReader(file_path='api_response.json')
+        reader = JSONReaderNode(file_path='api_response.json')
         result = reader.execute()
         # result['data'] = {
         #     'status': 'success',
@@ -359,7 +358,7 @@ class JSONReader(Node):
 
 
 @register_node()
-class TextReader(Node):
+class TextReaderNode(Node):
     """Reads text from a file.
 
     This node provides simple text file reading with encoding support.
@@ -403,15 +402,14 @@ class TextReader(Node):
     - UnicodeDecodeError: Wrong encoding
     - MemoryError: File too large
 
-    Example::
-
-        # Read a log file
-        reader = TextReader(
-            file_path='application.log',
-            encoding='utf-8'
-        )
-        result = reader.execute()
-        # result['text'] = "2024-01-01 INFO: Application started\\n..."
+    Example:
+        >>> # Read a log file
+        >>> reader = TextReaderNode(
+        ...     file_path='application.log',
+        ...     encoding='utf-8'
+        ... )
+        >>> result = reader.execute()
+        >>> # result['text'] = "2024-01-01 INFO: Application started\\n..."
     """
 
     def get_parameters(self) -> Dict[str, NodeParameter]:

kailash/nodes/data/retrieval.py

@@ -102,7 +102,7 @@ class RelevanceScorerNode(Node):
     ) -> List[Dict]:
         """Score chunks using cosine similarity."""
         # Extract actual embedding vectors from the embedding objects
-        # EmbeddingGenerator returns embeddings in format: {"embedding": [...], "text": "...", "dimensions": X}
+        # EmbeddingGeneratorNode returns embeddings in format: {"embedding": [...], "text": "...", "dimensions": X}
 
         # Handle query embedding - should be the first (and only) embedding in the list
         query_embedding_obj = query_embeddings[0] if query_embeddings else {}

kailash/nodes/data/sharepoint_graph.py

@@ -56,18 +56,17 @@ class SharePointGraphReader(Node):
     3. Search for files by name
     4. Navigate folder structures
 
-    Example::
-
-        reader = SharePointGraphReader()
-        result = reader.execute(
-            tenant_id="your-tenant-id",
-            client_id="your-client-id",
-            client_secret="your-secret",
-            site_url="https://company.sharepoint.com/sites/project",
-            operation="list_files",
-            library_name="Documents",
-            folder_path="Reports/2024"
-        )
+    Example:
+        >>> reader = SharePointGraphReader()
+        >>> result = reader.execute(
+        ...     tenant_id="your-tenant-id",
+        ...     client_id="your-client-id",
+        ...     client_secret="your-secret",
+        ...     site_url="https://company.sharepoint.com/sites/project",
+        ...     operation="list_files",
+        ...     library_name="Documents",
+        ...     folder_path="Reports/2024"
+        ... )
     """
 
     def get_metadata(self) -> NodeMetadata:
@@ -471,19 +470,18 @@ class SharePointGraphWriter(Node):
     This node handles file uploads to SharePoint document libraries,
     supporting folder structures and metadata.
 
-    Example::
-
-        writer = SharePointGraphWriter()
-        result = writer.execute(
-            tenant_id="your-tenant-id",
-            client_id="your-client-id",
-            client_secret="your-secret",
-            site_url="https://company.sharepoint.com/sites/project",
-            local_path="report.pdf",
-            library_name="Documents",
-            folder_path="Reports/2024",
-            sharepoint_name="Q4_Report_2024.pdf"
-        )
+    Example:
+        >>> writer = SharePointGraphWriter()
+        >>> result = writer.execute(
+        ...     tenant_id="your-tenant-id",
+        ...     client_id="your-client-id",
+        ...     client_secret="your-secret",
+        ...     site_url="https://company.sharepoint.com/sites/project",
+        ...     local_path="report.pdf",
+        ...     library_name="Documents",
+        ...     folder_path="Reports/2024",
+        ...     sharepoint_name="Q4_Report_2024.pdf"
+        ... )
     """
 
     def get_metadata(self) -> NodeMetadata:

kailash/nodes/data/sql.py

@@ -63,20 +63,19 @@ class SQLDatabaseNode(Node):
     - TimeoutError: Query execution timeout
     - PermissionError: Access denied
 
-    Example::
-
-        # Query customer data
-        sql_node = SQLDatabaseNode(
-            connection_string='postgresql://user:pass@host/db',
-            query='SELECT * FROM customers WHERE active = ?',
-            parameters=[True],
-            result_format='dict'
-        )
-        result = sql_node.execute()
-        # result['data'] = [
-        #     {'id': 1, 'name': 'John', 'active': True},
-        #     {'id': 2, 'name': 'Jane', 'active': True}
-        # ]
+    Example:
+        >>> # Query customer data
+        >>> sql_node = SQLDatabaseNode(
+        ...     connection_string='postgresql://user:pass@host/db',
+        ...     query='SELECT * FROM customers WHERE active = ?',
+        ...     parameters=[True],
+        ...     result_format='dict'
+        ... )
+        >>> result = sql_node.execute()
+        >>> # result['data'] = [
+        >>> #     {'id': 1, 'name': 'John', 'active': True},
+        >>> #     {'id': 2, 'name': 'Jane', 'active': True}
+        >>> # ]
     """
 
     def get_parameters(self) -> Dict[str, NodeParameter]:
@@ -259,18 +258,17 @@ class SQLQueryBuilderNode(Node):
     3. Multi-table joins
     4. Aggregation queries
 
-    Example::
-
-        builder = SQLQueryBuilderNode(
-            table='customers',
-            select=['name', 'email'],
-            where={'active': True, 'country': 'USA'},
-            order_by=['name'],
-            limit=100
-        )
-        result = builder.execute()
-        # result['query'] = 'SELECT name, email FROM customers WHERE active = ? AND country = ? ORDER BY name LIMIT 100'
-        # result['parameters'] = [True, 'USA']
+    Example:
+        >>> builder = SQLQueryBuilderNode(
+        ...     table='customers',
+        ...     select=['name', 'email'],
+        ...     where={'active': True, 'country': 'USA'},
+        ...     order_by=['name'],
+        ...     limit=100
+        ... )
+        >>> result = builder.execute()
+        >>> # result['query'] = 'SELECT name, email FROM customers WHERE active = ? AND country = ? ORDER BY name LIMIT 100'
+        >>> # result['parameters'] = [True, 'USA']
     """
 
     def get_parameters(self) -> Dict[str, NodeParameter]: