Quick Start | Notion

AI Learning Guide

What can Aralia OpenRAG do?

Aralia OpenRAG is a sample experience that combines AI semantic understanding, LLM RAG technology, and the Aralia Open Ecosystem to show how you can retrieve precise, source-attributable data and analytical results from the Data Ecosystem—just by chatting.

It relies on Aralia’s AI SDK to handle semantic understanding, information retrieval, and data parsing.

Try the integrated experience below:

Open “Open RAG Demo Site”：https://openrag.dev.araliadata.io/

https://openrag.dev.araliadata.io/

Paste the following into the input box and submit:

Is there a relationship between the average GDP growth at purchasers' prices from 2021 to 2024 and the Gini coefficient of each state in Malaysia in 2024?

The Aralia OpenRAG Demo service will automatically trigger five tool nodes (Find datasets → Plan → Decide query parameters → Execute query → Generate insights) and return:

A list of data sources (from multiple Data Planets, such as SDG, UN)
An insight that aligns years and geographic units before comparing

Behind the scenes, the AI understands the user’s question, searches for relevant insights inside Aralia’s Ecosystem, and responds to the user’s request.

Want to test more? Try these prompts:

Malaysia | GDP Growth × Gini (2019/2021–2024)
- What is the average GDP growth rate of each state in Malaysia in 2019?
- Is there a relationship between the average GDP growth at purchasers’ prices from 2021 to 2024 and the Gini coefficient of each state in Malaysia in 2024?
Traffic Safety | DUI and Accidents
- Which city/county has the highest number of DUI fatalities in a specific breath test range (e.g., 0.16–0.25 mg/L)? Sort by city/county.
- For the six special municipalities, what are the numbers of deaths and injuries for a given breath test range?
- Which road type accounts for the majority of DUI fatalities?
- What is the average age for breath alcohol > 0.80 mg/L (or blood alcohol > 0.16%)?

Tips: Ask a “complete question”

AI will not follow up to ask you for missing context. Defining the question clearly helps it find the correct insight.
If you’re unsure about indicators, use common, explicit statistical names (e.g., Gini coefficient) to avoid ambiguous abbreviations.
Specify the definition of “average” and comparison time points upfront.

How to “say it all at once”

Indicators: e.g., average GDP growth at purchasers’ prices (Average? YoY? Nominal/real?)
Time: specific years or ranges (e.g., 2021–2024; 2024)
Geographic level: Country/State/County/Region + scope (e.g., Malaysia by state)
Comparison/Relationship: correlation, ranking, difference, grouped comparison, etc.

🧩 Prompt Template

Is there a relationship between <Metric A> in <Time Range A> and <Metric B> in <Time/Year B> across <Geography Level/Scope>?

Example (ready to use):

Is there a relationship between the average GDP growth at purchasers' prices from 2021 to 2024 and the Gini coefficient of each state in Malaysia in 2024?

🧯 Common Misunderstandings (learn faster)

“Will AI guess the year/region for me?” → No. Include them in the prompt.
“Will AI fetch data from the open web?” → No. It only queries the Aralia Data Ecosystem and interprets the results.
“Do I need to code?” → No. Colab is prepared for you. Advanced users can check the Default AI-Powered SDK Workflow.

🙅‍♂️ Counter-Examples (unanswerable)

“Is there a relationship between GDP and Gini in Malaysia?” (Missing time and geographic level)
“Compare inequality.” (Missing indicator definition and year)

To understand how the AI achieves these results, continue to the sections below for the key concepts.

← Previous Chapter: AI Agent Tutorial

Next Chapter: System Overview & Core Concepts →