OpenAlex
OpenAlex maps the research world as connected entities: works (papers, books, datasets), the authors who wrote them, the venues that published them, the institutions behind them, and the topics they cover. Every entity carries an ID and links to related entities, so you can walk from a paper to its authors, their institutions, and the works it cites.
It was built by the nonprofit OurResearch to replace Microsoft Academic Graph after Microsoft retired it in 2021. The metadata is released under CC0, which places it in the public domain with no restrictions on reuse.
You can query it through a free API with no key required, or download the full data snapshot from Amazon S3 for bulk work. For RAG, the metadata and citation structure are handy for ranking, filtering, and enriching a corpus, though the works themselves are abstracts and metadata rather than full text.
Related sources
arXiv
An open-access preprint server for physics, mathematics, computer science, quantitative biology, statistics, and more, holding over 2.5 million papers. You can pull the full archive in bulk from Amazon S3, or harvest the metadata through OAI-PMH, a standard protocol for sharing records between repositories.
CORE
An aggregator of open-access research papers that harvests from thousands of repositories and journals worldwide. It holds over 300 million metadata records and more than 40 million full-text articles, all reachable through one search API.
Crossref
A nonprofit DOI registration agency that publishes metadata for over 150 million scholarly works, including journal articles, books, and conference proceedings. A DOI is the permanent identifier assigned to each work, and Crossref shares its metadata through a free API.
PubMed / PubMed Central (PMC)
The US National Library of Medicine's database of biomedical and life sciences literature. PubMed indexes over 36 million citations and abstracts, and PubMed Central (PMC) adds free full-text access to a growing subset. You can download the data in bulk over FTP.