Open data published by national, regional, and local governments covering demographics, economics, health, transport, environment, and more.
13sources
Government and public sector data is the official record: statistics, budgets, health indicators, company registers, transport figures, and the day to day business of national, regional, and local government. For a RAG (Retrieval-Augmented Generation) system, it is some of the most trustworthy material you can retrieve, because it comes straight from the body responsible for it rather than a secondhand summary. If you are building anything that answers questions about a country’s economy, population, public services, or laws, this is where the authoritative numbers live.
Choosing within it is really about scope and structure. National statistics offices and broad open data portals publish well documented datasets under permissive terms, while specialist bodies go deep on one area such as health, policing, or company filings. The trade-off is rarely quality, since official data is usually reliable, but coverage and granularity: a national portal gives you breadth, a dedicated agency gives you the fine detail. Decide how local and how current you need to be before you pick.
Two things catch people out. First, format: a lot of government data still arrives as spreadsheets, PDFs, or bespoke XML, so you will often need to extract and reshape it into clean text before it is useful for retrieval. Second, licensing: most of this is genuinely open, frequently under the Open Government Licence (a permissive licence that allows reuse with attribution), but always check, because some datasets carry extra conditions or personal data restrictions.
The sources below range from broad national portals to focused agencies covering statistics, health, policing, and company records.
The UK's official register of companies. Search every registered company, its directors, filing history, and accounts, or pull the data in bulk. A reliable source for UK corporate facts in a RAG system.
The European Data Portal, a single point of access to open data from 36 European countries and the EU institutions. Over 1.6 million datasets span every policy area, giving RAG systems broad, multilingual coverage of official European data.
The US federal government's open data portal, gathering more than 300,000 datasets from federal agencies. Coverage spans agriculture, climate, education, energy, finance, health, and public safety, making it a broad source of official US data for RAG systems.
The UK Government's central catalogue of open public sector data, run by the Government Digital Service. More than 47,000 datasets cover health, housing, transport, demographics, and the environment, giving RAG systems a trusted base of UK facts, figures, and official records.
Crime and policing data published on behalf of police forces in England and Wales, Northern Ireland, and the British Transport Police, gathered in one central place. Covers street-level crime, outcomes, and stop-and-search records.
A large public health data collection for England, including mental health indicators and the Public Health Outcomes Framework. Useful for viewing trends over time and comparing differences between areas.
The official word-for-word record of proceedings in the UK Parliament, both the Commons and the Lords. Full text searchable and available as XML and linked data going back centuries, it is a rich source of political and legislative debate for RAG systems.
A free and open data-sharing site for data and analysis from the Greater London Authority, providing more than 700 datasets at regional and local levels across the capital.
The national provider of information and data on health and social care in England, covering general practices, hospital-level mortality, mental health, population health, and NHS outcomes. Published under the Open Government Licence.
A service from the Office for National Statistics holding detailed data on the national and local labour market, covering official census and labour market statistics. Offers an API for programmatic access.
The UK's official statistics body. It publishes Census data, economic indicators, population estimates, labour market figures, and more, making it the authoritative source for UK statistics in a RAG system.
A portfolio of free geospatial datasets covering Great Britain from the national mapping agency, available for commercial and personal reuse under the Open Government Licence. Provides mapping, boundary, and location data through the OS Data Hub in formats including GeoPackage, GML, Shapefile, and CSV.
The official US federal rulemaking portal, exposing a public API to dockets, proposed and final rules, supporting materials and millions of public comments across federal agencies. Free to access with a registered API key.