Keyword Search
Keyword search finds content by matching the literal words in a query against the words in documents, the traditional approach now complemented by meaning-based vector search.
Keyword search matches words to words. It's the traditional method — find documents containing the query's terms, rank by relevance functions like BM25 — and it powered search for decades before vector search added matching by meaning.
It hasn't gone away. Keyword search excels at exact, literal needs — names, codes, quotes — where semantic methods can drift, which is why engines increasingly run both in a hybrid blend. For AEO this means you optimize for two audiences at once: include the precise terms people actually type or say, and express ideas clearly enough to match by meaning. Clear, extractable content that uses real vocabulary covers both.
Example. Someone searching the exact phrase "Schedule C deductions" is served well by keyword search finding that literal term — so having the precise phrase on a page that also explains the concept clearly wins on both the literal and the semantic match.
Relevant pillar
Related terms
- Vector SearchVector search is a retrieval method that finds passages by meaning rather than keywords, comparing the numeric embedding of a query against the embeddings of indexed content to surface the closest matches.
- BM25BM25 is a classic ranking function that scores how well a document matches a query based on term frequency and rarity, and it remains a strong, widely-used retrieval baseline.
- Hybrid SearchHybrid search combines keyword-based and meaning-based retrieval so a system can match both exact terms and semantic intent, and is the common approach in modern AI search.