> For the complete documentation index, see [llms.txt](https://ai2sql.gitbook.io/ai2sql/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai2sql.gitbook.io/ai2sql/10.-dataset-questions-generation.md).

# 10. Dataset Questions Generation

Introduction

The Dataset Questions Generation Tool is an innovative solution that utilizes the power of AI2sql,  to generate insightful questions based on a given dataset name. The purpose of the tool is to assist users in exploring potential angles of analysis for their datasets, thereby enabling a deeper understanding of the data.

#### Getting Started

**How to Input Dataset Names**

The tool requires the dataset name as input. This can be provided via a text interface, where the user types in the dataset name and then waits for the model to generate questions about the dataset.

**Expected Output**

Upon receiving the dataset name, the tool generates five relevant questions about the dataset. The output is purely textual and aims to stimulate the user's thought process in exploring the data.

#### Understanding Dataset Names

A dataset name is a label or identifier assigned to a specific collection of data. Just as a filename is used to identify a file on a computer, a dataset name is used to uniquely identify and reference a specific dataset within a data storage system.

#### How the Tool Works

The tool operates by feeding the dataset name to the AI2sql, which then uses its language understanding capabilities to generate questions about the dataset. However, it's important to note that the tool does not have access to the actual data or its schema and, as such, generates questions based purely on the name of the dataset.

#### User Guide

Using the Dataset Questions Generation Tool is a straightforward process:

1. Start the tool, and you'll be greeted with a text input field.
2. Enter the name of your dataset into the text input field.
3. After submitting the dataset name, wait a moment as the AI2sql generates questions.
4. The tool will then display five questions relevant to your dataset.

#### Input

You start the tool and in the text input field, you enter `Ecommerce_Sales_Data` and submit it.

#### Output

The tool then generates five questions:

1. What is the distribution of sales across different product categories in the `Ecommerce_Sales_Data` dataset?
2. Can we identify any seasonal trends in sales data from the `Ecommerce_Sales_Data` dataset?
3. What are the customer demographics for the top-selling products in the `Ecommerce_Sales_Data` dataset?
4. Are there any correlations between order value and the time of day in the `Ecommerce_Sales_Data` dataset?
5. What is the repeat purchase behavior like for customers according to the `Ecommerce_Sales_Data` dataset?

These questions could help guide your analysis of the dataset by suggesting various aspects to investigate. Remember, the tool generates these questions based on the dataset name, not its actual contents, so they may not all apply perfectly to the data in the dataset. These are intended to serve as starting points for your data exploration.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai2sql.gitbook.io/ai2sql/10.-dataset-questions-generation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.