Datahub.io
Datahub.io organises data as data packages, a simple standard that pairs the raw files with a small descriptor file explaining the columns, types, and sources. That consistency means you can load many different datasets the same way instead of writing bespoke parsing for each one.
The site features curated core datasets covering common reference data such as currency codes, stock market indices, geographic lists, and population figures. You can download packages directly, browse them on the web, or pull them programmatically, mostly as CSV and JSON.
Licences vary by dataset, so check each package before you rely on it. For RAG, Datahub is handy for the small, clean lookup datasets that fill gaps in a knowledge base, the kind of reference data you want tidy and predictable rather than large.
Related sources
AWS Data Exchange
A marketplace for finding, subscribing to, and using third-party data inside the AWS cloud. It carries both free open datasets and paid commercial data products, so you can pull licensed data straight into your AWS workflows without setting up separate transfers.
AWS Open Data Registry
A registry of high-value datasets hosted on AWS and made publicly available, covering genomics, geospatial data, climate, satellite imagery, and more. Over 300 PB of data in total, free to access: you pay only for the compute you use to process it.
Google Dataset Search
A search engine for datasets that indexes millions of them from thousands of repositories worldwide. It does not host data itself: it points you to wherever each dataset lives, which makes it a fast first stop when you are hunting for a source on a specific topic.
Hugging Face Datasets
The largest open hub for machine learning datasets, with well over 100,000 datasets you can search, stream, and version. Many RAG-ready corpora live here, and its Python library lets you pull data straight into a pipeline in a few lines.