Stacklane is now Vantion LabsLearn more

Semantic search development

We build semantic search that understands what people mean, combining embeddings with keyword matching and your business rules. Customers find the right product and employees find the right document, even when their wording does not match yours.

What it is and when it fits

Semantic search turns text, and sometimes images, into embeddings so that queries match on meaning. On its own that misses exact terms like part numbers and brand names, so we build hybrid search: vector and keyword retrieval combined, reranked and adjusted with filters, stock, margin or recency. We tune it on your real search logs and measure relevance with labelled query sets.

This is a strong fit for large catalogues with inconsistent product data, multilingual content, or knowledge bases where people search in their own words. If your users mostly search by exact code or your collection is small and well tagged, tuning your current keyword search may be enough. We check your search logs before recommending either.

What we build

Semantic search, keyword search or hybrid search.

Semantic search matches on meaning: the query and your content are turned into embeddings and compared, so a search for a waterproof jacket also finds a product described as a rain coat. Keyword search matches the exact words. Hybrid search combines both, and it is what most product catalogues and knowledge bases need.

Search typeMatches onStrong atWeak at
Keyword searchThe exact words in the queryPart numbers, brand names and exact phrasesSynonyms and different wording
Semantic searchMeaning, through embeddingsNatural questions and varied wordingExact codes and rare terms
Hybrid searchBoth, combined and rerankedCollections that get both kinds of queryNeeds tuning on real search logs

Our guide to embeddings and semantic search covers choosing a model, pgvector or a vector database, and how to measure relevance.

How it works

  1. 01

    Study the search logs

    We look at what people search for, where they get zero or poor results and which queries matter most commercially.

  2. 02

    Build a relevance baseline

    We label a query set, measure your current search against it and set targets for the new ranking.

  3. 03

    Build and tune

    We choose embedding models, build the hybrid pipeline and tune ranking against the query set and your business rules.

  4. 04

    Release and measure

    New search runs alongside the old one on part of the traffic, and we compare conversion and engagement before switching fully.

Related work

Further reading

Common questions

Talk through one process with the founder