Enrich your datasets with business context: Migrating from legacy Topics to semantic datasets in Amazon Quick

2026-07-07 · Source: Artificial Intelligence · Field: Technology & Digital — Data Science & Analytics, Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Intermediate, long

Summary

Amazon Quick introduces Dataset Enrichment, a new feature that embeds business context directly into datasets, replacing the legacy Topics approach. This enhancement moves column descriptions, synonyms, calculated fields, custom instructions, and business rules from separate legacy Topic objects into the dataset's metadata. The change establishes a single source of truth, ensuring automatic inheritance of semantic context by downstream assets like dashboards and AI-powered chat features, simplifying governance, and improving AI-readiness for natural language querying. While legacy Topics were separate assets requiring synchronization, the new architecture elevates "Topic" to a multi-dataset semantic and reasoning layer. A Python script automates the migration for datasets already utilizing the new data prep experience, requiring AWS CLI v2 (2.34.50+), Python 3.6+, and Amazon Quick Enterprise with Q.

Key takeaway

For Data Engineers or AI Architects managing Amazon Quick datasets, migrating from legacy Topics to Dataset Enrichment is crucial for establishing a unified semantic layer. You should automate this transition using the provided Python script for datasets already in the new data prep experience. This consolidates business context directly into your datasets, simplifying governance, ensuring data consistency, and significantly improving AI-powered natural language querying capabilities. Validate thoroughly with a question set before retiring legacy Topics.

Key insights

Amazon Quick's Dataset Enrichment unifies business context within datasets, streamlining governance and enhancing AI-driven analytics.

Principles

• Business context belongs with data.
• One asset simplifies governance.
• Semantic layers enable AI-readiness.

Method

A Python script extracts legacy Topic metadata (descriptions, synonyms, calculated fields, entities, filters, instructions) and applies it to a new data prep dataset's `SemanticModelConfiguration` via Quick Sight API.

In practice

• Use `enrich_dataset.py` for migration.
• Validate with 10-20 natural language questions.
• Test ambiguous queries and synonyms.

Topics

• Amazon Quick
• Dataset Enrichment
• Semantic Layer
• Data Governance
• AI-driven Analytics
• Python Automation
• AWS CLI

Best for: Data Engineer, MLOps Engineer, AI Architect

Related on AIssential

• Context intelligence for your data and AI agents at scale — AWS innovations provide scalable, governed context intelligence for AI agents by unifying scattered data into knowledge graphs.
• Semantic Layers in the Age of AI are 100% Needed — Semantic layers translate natural language queries into data operations, ensuring consistent data interpretation for AI and users.
• Introducing Dataset Q&A: Expanding natural language querying for structured datasets in Amazon Quick — Amazon Quick's Dataset Q&A enables direct natural language querying of full datasets, enhancing BI agility and transparency.
• Talk to all your data, wherever it lives — Databricks Lakehouse Federation unifies disparate enterprise data for AI-driven natural language querying without migration.
• Is context the new compute? How the AI race is moving to the data layer — AI competitive advantage now stems from proprietary organizational context and robust data infrastructure, not just model compute.
• datasette-enrichments-llm 0.2a1 — Passing the triggering actor to LLM enrichment methods enhances contextual control and personalization.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.