What is vector search?
Vector search is a retrieval technique that turns queries and documents into numeric vectors, called embeddings, and returns the documents whose vectors sit closest to the query's. It finds by similarity of meaning, not by shared words, and that is why it tends to fail on exact codes, such as a SKU, or on a newly created product name.
Key takeaways
- Vector search compares numbers, not words: each text becomes a vector and the one closest to the query's wins.
- With millions of vectors you do not compare one by one: you use approximate nearest neighbor indexes, which trade a little exactness for a lot of speed.
- It finds "something for the cold" even when the page says "coat", but Google Cloud warns it does not work well with product numbers, SKUs or newly created names.
- Hybrid search combines vectors and keywords, and it is the usual answer to that limit.
- The vector comes from your text: what the page does not say, vector search cannot find.
A customer types "something to take steady photos at night" into a camera store's search box and gets tripods, even though no product page says "night" or "steady". Vector search may be behind it: instead of comparing words, it compares numbers that represent what each text means. It has nothing to do with vector graphics or searching for SVG images. It matters to a store twice over: it may be behind the search on your own site, and it is one of the pieces an assistant uses to find the pages it then cites.
How it works
The job has three steps. First, a model turns each text in the catalog into a vector, a list of numbers: Google describes it as a type of vector that represents data in a way that captures its semantic meaning.[1]Google Cloud, Vertex AI documentation (updated October 6, 2026). Vector Search overview Those vectors are embeddings, and their entry explains how the distance between two is measured. Second, the vectors are stored in an index. Third, when a query arrives, it is turned into a vector with the same model and the closest vectors are looked up. OpenAI lists search as the first use of its embeddings: results are ranked by how related they are to the query text.[2]OpenAI, API documentation. Vector embeddings
The second step is what sets vector search apart from a simple comparison. With millions of products, comparing the query against every vector, one by one, is slow. So systems look for approximate nearest neighbors: they accept not guaranteeing the exact closest one in exchange for answering fast. One well-known method is HNSW, published by Yu. A. Malkov and D. A. Yashunin in 2016, which organizes the vectors into several layers of proximity graphs and makes the cost of a search grow logarithmically with the size of the collection.[3]arXiv (Malkov and Yashunin; first version 2016, revised 2018). Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs Google's Vector Search service uses another algorithm, ScaNN, developed by Google Research, and cites among its uses ecommerce recommendations and RAG (retrieval-augmented generation), with eBay and Mercari as examples.[1]Google Cloud, Vertex AI documentation (updated October 6, 2026). Vector Search overview
There is a practical limit before you start: the text has to fit in the model. OpenAI's embeddings models accept at most 8,192 tokens per input,[2]OpenAI, API documentation. Vector embeddings so a long document is split into chunks and each chunk gets its own vector.
Where it fails, and hybrid search
Vector search finds by similarity of meaning, and that has a flip side. Google Cloud's documentation says it with store examples: arbitrary product numbers or SKUs, the names of products that were just added and internal code names do not work with semantic search, because they were not in the data the embeddings model was trained on.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search A code like "TV-200-BK" means nothing to the model: it is a string of characters.
The usual fix is to mix two kinds of vector. Google distinguishes dense embeddings, which represent the meaning of the text, from sparse ones, which represent its syntax and work like a keyword search.[1]Google Cloud, Vertex AI documentation (updated October 6, 2026). Vector Search overview Hybrid search uses both and merges the two result lists with a method called Reciprocal Rank Fusion: each result earns points according to its position in each list, so whatever ranks high in both comes first. A parameter decides how much each side weighs, from dense vectors only to keywords only.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
In a store
A fictional example: the internal search of a camera store, with three queries. The last column applies what Google Cloud's documentation says about each method.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
| Query | Keywords only | Vector search only | Hybrid search |
|---|---|---|---|
| "something to take steady photos at night" | Few results: the pages do not use those words | Tripods and stabilizers, by similarity of meaning | Tripods and stabilizers |
| "TV-200-BK", the code the manufacturer gives | The page that contains that code | Risk of missing it: the code means nothing to the model | The exact page, thanks to the keyword side |
| The name of a range the brand launched this month | Finds it if the page spells it out | Risk of confusing it with something similar | Finds it |
Platforms already offer it. Since June 24, 2024, Shopify stores on the Shopify and Advanced plans can turn on semantic search in the Search & Discovery app, which understands that someone searching for "something to wear in summer" wants a pair of shorts;[5]Shopify Changelog (June 24, 2024). Semantic search is now available on more plans the announcement does not detail the technique it uses inside. Clione, for example, computes a vector for each product and lets you search the catalog by meaning while filtering at the same time by status, brand and availability.
The lesson for the catalog is twofold. The vector can only represent what your text says, so the description has to name the use, the material and the situation in plain words. And codes, the SKU, the MPN or the GTIN, have to sit in fields the keyword side can match as they are.
What people often get wrong
That vector search replaces keyword search, and that turning it on improves every query. Google Cloud explains that each method fails where the other succeeds, that a SKU or a newly created name does not work with semantic search and that this is why hybrid search exists, better than either one alone.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
How to check it
- Search your store for a need, not a product, using words your product pages do not use. If nothing useful comes up, your search is not comparing by meaning.
- Search for an exact SKU and a manufacturer code. If the product page does not appear, the search is not combining the keyword side or that code is not indexed.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
- Search for the name of a product you added this week. It is the other case Google flags as weak for vectors.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
- Check that the description is text and not an image, and that a very long text gets chunked: the embeddings model has a maximum number of tokens per input.[2]OpenAI, API documentation. Vector embeddings
- Review the searches with no results in your internal search's report, if it has one: those are the queries neither words nor vectors solved.
Related concept: semantic search
Semantic search is the goal, finding by meaning; vector search is one of the techniques for getting there. Google presents its Vector Search as an engine for semantic similarity searches,[1]Google Cloud, Vertex AI documentation (updated October 6, 2026). Vector Search overview but its own documentation shows the best result comes from mixing vectors with the same old words.[4]Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search
To go further, the embeddings entry explains what vectors are and how their distance is measured, and the reading path orders the rest of the terms.
Synonyms
- English
- vector search, vector similarity search
- Español
- búsqueda por vectores
Sources
- [1] Google Cloud, Vertex AI documentation (updated October 6, 2026). Vector Search overview. Accessed . ↑ ↑ ↑ ↑
- [2] OpenAI, API documentation. Vector embeddings. Accessed . ↑ ↑ ↑
- [3] arXiv (Malkov and Yashunin; first version 2016, revised 2018). Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. Accessed . ↑
- [4] Google Cloud, Vertex AI documentation (updated October 6, 2026). About hybrid search. Accessed . ↑ ↑ ↑ ↑ ↑ ↑ ↑
- [5] Shopify Changelog (June 24, 2024). Semantic search is now available on more plans. Accessed . ↑
Change history
- First English version.
This definition is published under CC BY 4.0. Reuse this definition freely, crediting Clione with a link to this page.
Related terms
Embeddings
What embeddings are, how they measure similarity between texts with vectors, what OpenAI and Gemini use and what they do and do not say about your products.
Semantic search
What semantic search is, how Google reads a query by its meaning and not its words, and what changes on the product pages of an online store.
RAG
What RAG is in AI, the paper it comes from, how Google and ChatGPT use it to answer with sources, and what part of your product page ends up in the answer.
Token
What a token is in artificial intelligence, how many characters it takes, how OpenAI, Gemini and Claude count them and what they cost on your product pages.
Context window
What an LLM's context window is, how many tokens fit in Claude or Gemini, why more context is not better and how much of your product page gets read.
SKU
What a product SKU is, how it differs from a GTIN and an MPN, how to create one per variant on Shopify or BigCommerce, and where Google asks for it.
Make your catalog easy for bots to read
Clione fills every product page with what bots read best: the JSON-LD graph with its structured data, the meta description and the FAQs. You review and press Push; then we check your live store so it all stays published.