data.police.uk
data.police.uk is the central point for open crime and policing data across England and Wales, Northern Ireland, and the British Transport Police. It publishes street-level crime, outcome, and stop-and-search records month by month, each row carrying a category, an approximate location, and a date, along with detailed force-level figures and information about individual police forces and their neighbourhood teams. Locations are deliberately snapped to anonymous map points rather than exact addresses to protect privacy, which is worth knowing before you draw fine-grained geographic conclusions.
You can get the data two ways. The bulk download hands you monthly CSV archives covering all forces, which is the right choice for building a corpus or doing historical analysis over several years. The REST API returns JSON and is better for targeted lookups: crimes within a point or area for a given month, stop and search by force, and reference data like the list of forces and their senior officers. The API has no key requirement, but it is rate-limited and paginates large areas, so batch your requests and cache results when ingesting at scale.
For a RAG (Retrieval-Augmented Generation) system, this suits assistants about UK crime, community safety, and local policing, or any tool answering "what happened near here" questions. Because so much of the payload is tabular and categorical, the effective pattern is to summarise it into natural-language passages (for example, monthly trends per neighbourhood or per crime type) and embed those, keeping the underlying rows linked for detail.
Licensing is refreshingly simple: it is published under the Open Government Licence v3.0, so you can reuse it commercially and personally with attribution, no share-alike condition, and no differing terms on the underlying content. Cite data.police.uk and the relevant forces as the source and you are covered. For wider UK public data, it sits naturally alongside data.gov.uk and the ONS.
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.