Skip to content

3.20 When the person's words are not the data's — ai.terms

MATCH (s:DiseaseSearch {query: $q})-[r:MATCHES]->(h:DiseaseHit)
RETURN h.id AS id, h.name AS name, null AS suggestedBy
UNION
CALL ai.terms($q, 'disease names, synonyms and abbreviations', {ai: {confidence: 0.6, maxTerms: 5}})
YIELD term
MATCH (s2:DiseaseSearch {query: term})-[:MATCHES]->(h2:DiseaseHit)
RETURN h2.id AS id, h2.name AS name, term AS suggestedBy

Means: “Find the disease someone typed as HSV 2 vaccine.” The search index has no “HSV-2”; a model knows it is herpes simplex virus 2, which the vocabulary files under genital herpes.

  • The model suggests, the data decides. ai.terms yields words — a term, its kind, how sure the model is — never a disease. Each term is looked up like a typed one; a suggestion the index does not know finds nothing and is simply not a row. Counts are over what the lookup found.
  • Say where a row came from. suggestedBy carries the term that reached it, so an app can show “suggested by a model: HSV-2 → genital herpes” — and the result’s AI_TERMS note names the role, the input and every term, so nothing a model said passes as the data’s own words.
  • The same question, the same terms. Answers are kept per input and steering; {ai: {fresh: true}} asks again. A model that cannot be reached gives no suggestions and a TERMS_UNAVAILABLE warning; the index’s own rows still answer.

Habits: put the deterministic search first and the suggestions beside it; set a confidence floor so long-shot terms are never looked up; hand the call a null input when the search was already strong, and it asks nothing. See §7.10 of the spec.