MeghaOS Docs

Parameters

Name	Type	Required	Description
`input_path`	string	yes	Absolute path to the messy CSV or Excel file.
`output_path`	string	yes	Absolute path where the cleaned file will be saved. Must match input extension.
`sheet_name`	string	—	For Excel files only: specific sheet to clean. Default is the first sheet.
`handle_missing`	drop \| mean \| median \| mode \| zero	—	Strategy for missing values. Default is 'mean' for numeric, 'empty' for text.
`remove_duplicates`	boolean	—	Whether to drop exact duplicate rows. Default is true.
`normalize_text`	boolean	—	Whether to trim whitespace and standardize casing on text columns. Default is true.
`standardize_columns`	boolean	—	Whether to convert column names to snake_case. Default is true.

How to use it

You normally trigger this by describing what you want in chat — the agent selects CLEAN_DATA automatically. For example:

Try saying

“use analyst tools to clean …”

In a workflow

As a step in a multi-step workflow DAG:

{
  "id": "s1",
  "agent": "analyst_tools",
  "action": "CLEAN_DATA",
  "args": {
    "input_path": "/Users/me/Documents/file.txt",
    "output_path": "/Users/me/Documents/file.txt"
  },
  "depends_on": [],
  "outputs": []
}

Direct call

For scripting, call it directly via POST /execute_tool. Every tool returns { success, message, data }.

curl -X POST http://127.0.0.1:8000/execute_tool \
  -H "Content-Type: application/json" \
  -d '{"tool_name":"CLEAN_DATA","args":{"input_path":"/Users/me/Documents/file.txt","output_path":"/Users/me/Documents/file.txt"}}'

Part of the analyst_tools plugin. Browse the full Plugin & Tool Catalog or the relevant feature guide.