Part ofAI in product and site
AI search and vector search
Vector search, or semantic search, compares the meaning of a query against the meaning of your content instead of matching character strings. Each document becomes a vector, the query is converted the same way, and the results are those closest in meaning. That lets a visitor find the right page even when they use entirely different words than you do.
Why vector search alone falls short
Vector search is weak on exact matches: part numbers, product names and model codes. The practical answer is hybrid search, where classic keyword search and vector search run in parallel and the results are blended. That gives both understanding of the question and precision on the code the customer pasted in.
How content is chunked
A document is not indexed whole but in passages, because a vector spanning twenty pages becomes so general it matches nothing. The split has to follow the structure of the content, keeping the heading with each part, or the passage loses its context and the result is unintelligible when displayed.
Knowing whether it got better
Search is evaluated against a list of real queries with known correct answers, taken from your own search logs. Without that list it is impossible to tell whether a change helped or merely felt better, and search projects without evaluation reliably collapse into opinion.
Common questions about this service
Do we have to replace our current search?
Rarely straight away. Vector search is usually placed alongside the existing search and the results blended, so exact matches on part numbers keep working as before. It also means the change can be rolled back if the evaluation does not show an improvement.
What does keeping the index current cost?
Less than most people expect. The cost is in creating vectors, and that only has to happen for content that actually changed. For a site with a few thousand pages the ongoing cost is a handful of euros a month, while the search itself runs against the index without model calls.
More in the same area
AI search and vector search
Search that understands what the visitor meant, not just which words they typed.
RAG assistants
Assistants that answer only from your documents, with the source cited.
Product content at scale
Product copy and metadata generated from your structured data, not from nothing.
