kailash 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

kailash/nodes/transform/formatters.py

@@ -0,0 +1,96 @@
+"""Text formatting nodes for transforming and preparing text data."""
+
+from typing import Any, Dict
+
+from kailash.nodes.base import Node, NodeParameter, register_node
+
+
+@register_node()
+class ChunkTextExtractorNode(Node):
+    """Extracts text content from chunks for embedding generation."""
+
+    def get_parameters(self) -> Dict[str, NodeParameter]:
+        return {
+            "chunks": NodeParameter(
+                name="chunks",
+                type=list,
+                required=False,
+                description="List of chunks to extract text from",
+            )
+        }
+
+    def run(self, **kwargs) -> Dict[str, Any]:
+        chunks = kwargs.get("chunks", [])
+        # Extract just the content text from chunks
+        texts = [chunk["content"] for chunk in chunks]
+        return {"input_texts": texts}
+
+
+@register_node()
+class QueryTextWrapperNode(Node):
+    """Wraps query string in list for embedding generation."""
+
+    def get_parameters(self) -> Dict[str, NodeParameter]:
+        return {
+            "query": NodeParameter(
+                name="query",
+                type=str,
+                required=False,
+                description="Query string to wrap",
+            )
+        }
+
+    def run(self, **kwargs) -> Dict[str, Any]:
+        query = kwargs.get("query", "")
+        print(f"Debug QueryTextWrapper: received query='{query}'")
+        # Use input_texts for batch embedding (single item list)
+        result = {"input_texts": [query]}
+        print(f"Debug QueryTextWrapper: returning {result}")
+        return result
+
+
+@register_node()
+class ContextFormatterNode(Node):
+    """Formats relevant chunks into context for LLM."""
+
+    def get_parameters(self) -> Dict[str, NodeParameter]:
+        return {
+            "relevant_chunks": NodeParameter(
+                name="relevant_chunks",
+                type=list,
+                required=False,
+                description="List of relevant chunks with scores",
+            ),
+            "query": NodeParameter(
+                name="query",
+                type=str,
+                required=False,
+                description="Original query string",
+            ),
+        }
+
+    def run(self, **kwargs) -> Dict[str, Any]:
+        relevant_chunks = kwargs.get("relevant_chunks", [])
+        query = kwargs.get("query", "")
+        # Format context from relevant chunks
+        context_parts = []
+        for chunk in relevant_chunks:
+            context_parts.append(
+                f"From '{chunk['document_title']}' (Score: {chunk['relevance_score']:.3f}):\n"
+                f"{chunk['content']}\n"
+            )
+
+        context = "\n".join(context_parts)
+
+        # Create prompt for LLM
+        prompt = f"""Based on the following context, please answer the question: "{query}"
+
+Context:
+{context}
+
+Please provide a comprehensive answer based on the information provided above."""
+
+        # Create messages list for LLMAgent
+        messages = [{"role": "user", "content": prompt}]
+
+        return {"formatted_prompt": prompt, "messages": messages, "context": context}

kailash/runtime/docker.py

@@ -174,7 +174,7 @@ def main():
     logger.info(f"Loaded configuration for {node_data['class']} node")
 
     # Load runtime inputs if available
-    input_path = Path("/data/input/inputs.json")
+    input_path = Path("/examples/data/input/inputs.json")
     runtime_inputs = {}
     if input_path.exists():
         logger.info(f"Loading inputs from {input_path}")
@@ -206,7 +206,7 @@ def main():
     except Exception as e:
         logger.error(f"Node execution failed: {e}")
         # Save error information
-        with open("/data/output/error.json", 'w') as f:
+        with open("/examples/data/output/error.json", 'w') as f:
             json.dump({
                 "error": str(e),
                 "type": e.__class__.__name__
@@ -216,7 +216,7 @@ def main():
     # Save results
     logger.info("Saving execution results")
     try:
-        result_path = Path("/data/output/result.json")
+        result_path = Path("/examples/data/output/result.json")
         with open(result_path, 'w') as f:
             # Handle non-serializable objects with basic conversion
             try:
@@ -266,7 +266,7 @@ COPY node.json /app/node.json
 COPY entrypoint.py /app/entrypoint.py
 
 # Create data directories
-RUN mkdir -p /data/input /data/output
+RUN mkdir -p /examples/data/input /examples/data/output
 
 # Set entrypoint
 ENTRYPOINT ["/app/entrypoint.py"]
@@ -391,9 +391,9 @@ ENTRYPOINT ["/app/entrypoint.py"]
         cmd.extend(
             [
                 "-v",
-                f"{self.input_dir.absolute()}:/data/input",
+                f"{self.input_dir.absolute()}:/examples/data/input",
                 "-v",
-                f"{self.output_dir.absolute()}:/data/output",
+                f"{self.output_dir.absolute()}:/examples/data/output",
             ]
         )
 

kailash/sdk_exceptions.py

@@ -278,16 +278,7 @@ class TemplateError(KailashException):
 
 
 # Code execution exceptions
-class SafetyViolationError(NodeException):
-    """Raised when code execution violates safety rules.
-
-    This typically occurs when:
-    - Potentially dangerous operations are attempted
-    - Resource limits are exceeded
-    - Security policies are violated
-    """
-
-    pass
+# (SafetyViolationError already defined above - removing duplicate)
 
 
 class CodeExecutionError(NodeException):
@@ -302,6 +293,29 @@ class CodeExecutionError(NodeException):
     pass
 
 
+# Resource exceptions
+class KailashNotFoundException(KailashException):
+    """Raised when a requested resource cannot be found.
+
+    This typically occurs when:
+    - A template ID doesn't exist in the registry
+    - A node type is not registered
+    - A file or resource is missing
+    """
+
+    pass
+
+
+# Workflow-specific exceptions
+class KailashWorkflowException(WorkflowException):
+    """Raised for general workflow-related errors.
+
+    This is an alias for WorkflowException for consistency.
+    """
+
+    pass
+
+
 # Legacy exception name compatibility for tests and backwards compatibility
 KailashRuntimeError = RuntimeExecutionError
 KailashValidationError = NodeValidationError

kailash/tracking/metrics_collector.py

@@ -88,7 +88,8 @@ class MetricsCollector:
     metrics during node execution, with support for both process-level and
     system-level monitoring.
 
-    Usage:
+    Usage::
+
         collector = MetricsCollector()
         with collector.collect() as metrics:
             # Execute node code here

kailash/utils/templates.py

@@ -327,7 +327,7 @@ A Kailash workflow project.
 
 - `workflows/`: Workflow definitions
 - `nodes/`: Custom node implementations
-- `data/`: Input data files
+- `examples/data/`: Input data files
 - `outputs/`: Output files
 
 ## Usage
@@ -363,7 +363,7 @@ workflow = Workflow(
 )
 
 # Add nodes
-workflow.add_node("reader", CSVReader(), file_path="data/input.csv")
+workflow.add_node("reader", CSVReader(), file_path="examples/examples/data/input.csv")
 workflow.add_node("filter", Filter(), field="value", operator=">", value=100)
 workflow.add_node("sort", Sort(), field="value", reverse=True)
 workflow.add_node("aggregate", Aggregator(), group_by="category", operation="sum")
@@ -482,8 +482,8 @@ workflow = Workflow(
 )
 
 # Data ingestion
-workflow.add_node("csv_reader", CSVReader(), file_path="data/sales_data.csv")
-workflow.add_node("json_reader", JSONReader(), file_path="data/product_data.json")
+workflow.add_node("csv_reader", CSVReader(), file_path="examples/examples/data/sales_data.csv")
+workflow.add_node("json_reader", JSONReader(), file_path="examples/examples/data/product_data.json")
 
 # Transform data
 workflow.add_node("filter_sales", Filter(), field="amount", operator=">", value=1000)
@@ -553,7 +553,7 @@ workflow = Workflow(
 )
 
 # Data ingestion
-workflow.add_node("read_data", CSVReader(), file_path="data/text_data.csv")
+workflow.add_node("read_data", CSVReader(), file_path="examples/examples/data/text_data.csv")
 
 # Preprocessing
 workflow.add_node("extract_text", Map(), field="content")
@@ -616,7 +616,7 @@ workflow = Workflow(
 )
 
 # Read configuration
-workflow.add_node("read_config", JSONReader(), file_path="data/api_config.json")
+workflow.add_node("read_config", JSONReader(), file_path="examples/examples/data/api_config.json")
 
 # Process with AI agent
 workflow.add_node("chat_agent", ChatAgent(),