ChatGPT - Create Data Dictionary

Overview

This template takes in a CSV file and creates a data dictionary. Example

input: "id,name,age\n1,Alice,30\n2,Bob,25" output: Data dictionary for the CSV (id,name,age) — 2 rows

1) id - Data type: Integer - Description: Unique identifier for each person (primary key) - Sample values: 1, 2 - Constraints: Not null, unique, positive integer - Suggested DB type: INTEGER PRIMARY KEY

2) name - Data type: String / Text - Description: Person's name - Sample values: "Alice", "Bob" - Constraints: Not null (if every record must have a name). Recommended max length if using VARCHAR, e.g. VARCHAR(255) - Suggested DB type: VARCHAR(255) or TEXT

3) age - Data type: Integer - Description: Person's age in years - Sample values: 30, 25 - Constraints: Not null (if every record must have age). Logical bounds: non-negative (e.g., 0–120) - Suggested DB type: SMALLINT or INTEGER, optionally with CHECK (age >= 0 AND age <= 120)

Optional SQL (example) CREATE TABLE people ( id INTEGER PRIMARY KEY, name VARCHAR(255) NOT NULL, age SMALLINT NOT NULL CHECK (age BETWEEN 0 AND 120)

Variables

Name	Reference	Type	Required	Default	Options	Description
CSV File	CHATGPT_FILE	Alphanumeric	✅	-	-	The data that you would like a data dictionary created from in CSV form.
Destination File Name	CHATGPT_DESTINATION_FILE_NAME	Alphanumeric	✅	-	-	The file where the data dictionary will be stored.
Destination Folder Name	CHATGPT_DESTINATION_FOLDER_NAME	Alphanumeric	➖	-	-
Model	CHATGPT_MODEL	Select	➖	gpt-5	GPT-5: gpt-5 GPT-5-Mini: gpt-5-mini GPT-5-Nano: gpt-5-nano GPT-4.1: gpt-4.1	Model To Use

YAML

Below is the YAML template

YAML


source:
  template: ChatGPT - Create Data Dictionary
  inputs:
    CHATGPT_FILE:
    CHATGPT_DESTINATION_FILE_NAME:
    CHATGPT_DESTINATION_FOLDER_NAME:
    CHATGPT_MODEL: gpt-5
  type: TEMPLATE
guardrails:
  retry_count: 0
  retry_wait: 0h0m0s
  runtime_cutoff: 1h0m0s
  exclude_exit_code_ranges:
    - 200