WordNet
WordNet organises English around meaning. Words that share a sense are gathered into a synset (a set of synonyms), and the synsets are joined by relationships such as "is a kind of", "is a part of", and "is the opposite of". Because a word can have several senses, WordNet keeps them separate, which helps tell apart, say, a river bank from a savings bank.
It has been a staple of language technology for decades and ships in many toolkits, so you can load it locally and look words up without an API. The data is small and fast to work with, and versions exist for other languages through related projects.
For RAG and search, WordNet is useful for expanding queries with synonyms, working out which sense of a word is meant, and measuring how closely two words relate. It is a dependable building block wherever you need a structured view of English vocabulary.
Related sources
ConceptNet
A multilingual common-sense knowledge graph that links words and phrases with labelled connections, such as "a cat is a pet" or "rain causes wet". It captures the everyday relationships between ideas that plain text rarely spells out.
Google Knowledge Graph API
An API into Google's Knowledge Graph, the store of billions of facts about entities that powers the info panels you see beside search results. You send a name or query and get back matching entities with descriptions, types, and links. Free to use within rate limits.
NELL (Never-Ending Language Learner)
A machine learning system from Carnegie Mellon that has been reading the web since 2010 and building a knowledge base as it goes. It extracts beliefs, entities, and the relationships between them from text, and keeps refining them over time.