DrugBank
DrugBank brings together what is known about individual drugs, from their chemical structure and mechanism of action to dosing, interactions, and the proteins they target in the body. Each entry cross-references related drugs, targets, and pathways, so it reads more like a connected knowledge base than a flat list.
This structure suits RAG systems that answer questions about medicines, interactions, or drug targets, whether for research, education, or clinical decision support. You can browse the data online and, with an account, export it for use in your own pipelines.
Licensing depends on how you use it. Academic and non-commercial use falls under CC BY-NC 4.0, while commercial use requires a separate paid licence, so check which applies to your project before you build on it.
Related sources
ClinicalTrials.gov
A US National Institutes of Health database of privately and publicly funded clinical studies. It holds structured records on more than 450,000 studies, including protocols, conditions, interventions, outcomes, and results, all in the public domain.
MIMIC-III / MIMIC-IV
Freely accessible critical care databases with de-identified health data from more than 40,000 intensive care patients at Beth Israel Deaconess Medical Center. They include vital signs, lab results, medications, and clinical notes. Access needs credentialing and a data-use agreement.
PhysioNet
A repository of freely available medical research data, including physiological signals such as ECG and EEG, clinical databases, and related software. It hosts MIMIC and many other biomedical datasets, so it is a central hub for clinical RAG source material.
UniProt
A resource for protein sequence and functional information, with more than 250 million protein sequences and rich annotations. It is a core reference for bioinformatics, so it grounds life sciences RAG systems in reliable protein facts.