London Datastore
The London Datastore is the Greater London Authority's open data site, a free store of more than 700 datasets about the capital. Coverage runs across demographics and population projections, transport, housing and rents, the economy and jobs, crime, health, and the environment, at both London-wide and borough or ward level, sitting alongside the GLA's own published analysis and briefings.
Datasets download directly as CSV, Excel, and JSON, and many entries link out to the original source or an API where one exists. The blend of tabular data and written analysis shapes how you ingest it: the reports and commentary are ready to chunk and embed as prose, while the spreadsheets are best turned into short natural-language statements, one per row or figure, before embedding, so your retriever has readable text to match against rather than bare numbers.
This is the natural foundation for any London-focused RAG application: a local assistant that answers questions about a borough, a planning or housing research tool, a civic chatbot, or an analysis helper that needs authoritative regional statistics. Because it is one curated source rather than a scatter of separate council websites, you get consistent formatting and clear provenance across topics.
A couple of things are worth watching. Datasets are refreshed on their own schedules, so some series are bang up to date while others are historical snapshots; check the date on anything time-sensitive. The licence, by contrast, is refreshingly clear: nearly everything is published under the Open Government Licence v3.0, which permits commercial and personal reuse as long as you include the required attribution statement. A small number of linked third-party datasets may carry their own terms, so glance at the licence field on each one.
Set against its neighbours, data.gov.uk is the national catalogue to reach for when you need coverage beyond the capital, the Office for National Statistics supplies the underlying UK-wide figures, and other city portals follow the same open-data pattern. The London Datastore is the one to start with whenever your questions are specifically about London.
Related sources
Companies House
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.
data.europa.eu
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.
data.gov
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.
data.gov.uk
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.