data-processing.json•3.65 kB
{
"id": "example-data-processing",
"name": "Data Processing Pipeline",
"description": "ETL workflow for processing, validating, and transforming data with conditional branching",
"goal": "Process raw data into clean, validated, and transformed output",
"version": "1.0.0",
"tags": ["data", "etl", "processing"],
"inputs": {
"input_file": {
"type": "string",
"description": "Path to input data file",
"required": true
},
"output_format": {
"type": "string",
"description": "Desired output format (json, csv, parquet)",
"required": true
},
"quality_threshold": {
"type": "number",
"description": "Minimum data quality score (0-1)",
"required": false,
"default": 0.8
}
},
"required_tools": ["read_file", "write_file"],
"steps": [
{
"id": 1,
"action": "tool_call",
"tool_name": "read_file",
"description": "Load raw data from input file",
"parameters": {
"path": "{{input_file}}"
},
"save_result_as": "raw_data",
"error_handling": "stop"
},
{
"id": 2,
"action": "validate",
"description": "Validate data format and structure",
"input_from": ["raw_data"],
"criteria": "Check for required fields, data types, and format consistency",
"save_result_as": "validation_result",
"error_handling": "stop"
},
{
"id": 3,
"action": "analyze",
"description": "Analyze data quality and completeness",
"input_from": ["raw_data", "validation_result"],
"save_result_as": "quality_analysis",
"error_handling": "continue"
},
{
"id": 4,
"action": "branch",
"description": "Branch based on data quality score",
"conditions": [
{
"if": "quality_analysis.score >= quality_threshold",
"goto_step": 5
},
{
"if": "quality_analysis.score < quality_threshold",
"goto_step": 8
}
],
"error_handling": "stop"
},
{
"id": 5,
"action": "transform",
"description": "Clean and normalize high-quality data",
"input_from": ["raw_data"],
"transformation": "Remove duplicates, handle missing values, normalize formats",
"save_result_as": "cleaned_data",
"error_handling": "stop"
},
{
"id": 6,
"action": "transform",
"description": "Convert data to desired output format",
"input_from": ["cleaned_data", "output_format"],
"transformation": "Convert to specified format with proper encoding",
"save_result_as": "formatted_data",
"error_handling": "stop"
},
{
"id": 7,
"action": "tool_call",
"tool_name": "write_file",
"description": "Save processed data to output file",
"parameters": {
"path": "processed_{{output_format}}_data",
"content": "{{formatted_data}}"
},
"save_result_as": "output_result",
"error_handling": "stop"
},
{
"id": 8,
"action": "notify",
"description": "Alert about low quality data",
"input_from": ["quality_analysis"],
"save_result_as": "quality_alert",
"error_handling": "continue"
},
{
"id": 9,
"action": "compose",
"description": "Create data quality report",
"input_from": ["quality_analysis", "validation_result"],
"save_result_as": "quality_report",
"error_handling": "stop"
}
],
"metadata": {
"created_at": "2025-06-11T02:00:00Z",
"updated_at": "2025-06-11T02:00:00Z",
"times_run": 0
},
"is_deleted": false
}