Jump to content

Vector-based searching and embeddings

From UBC Wiki
Algorithms vs. artificial intelligence vs. machine learning vs. deep learning (Author: Johannes Vrana, CC BY-ND 4.0)

Compiled by

Updated

See also

Introduction

Vector-based searching (also known as semantic search or embedding-based search) is an information retrieval method that finds and ranks results based on the semantic meaning of content rather than exact keyword matches. It represents documents and queries as numerical vectors and retrieves results by measuring similarity between those vectors.

Traditional keyword-based searching relies on lexical matching, meaning results are returned only when query terms explicitly appear in records. Vector-based searching instead encodes meaning using machine learning models, allowing systems to retrieve relevant content even when different words, synonyms, or paraphrases are used. In vector-based systems, items with similar meanings are located close together in "a high dimensional vector space", enabling searches based on conceptual similarity rather than literal text overlap.

How vector-based searching works

Vector-based searching typically involves four stages:

1) Embedding

Content such as documents, sentences, images, or audio is converted into numerical representations called vector embeddings using a machine learning model. Queries are embedded using the same model.

2) Indexing

Embeddings are stored in a specialized index or vector database. To enable fast retrieval at scale, systems commonly use Approximate Nearest Neighbor (ANN) algorithms.

3) Querying

When a user submits a query, it is transformed into a vector embedding.

4) Similarity matching

The system calculates similarity between the query vector and stored vectors using distance metrics such as:

Results are ranked by closeness in the vector space.

Comparison with keyword search

Feature Keyword Search Vector-Based Search
Matching method Exact word "lexical" matching Semantic similarity
Synonym handling Limited Strong
Sensitivity to phrasing High Low
Context awareness Minimal High
Multilingual capability Limited Often supported

Models used

Vector-based searching typically relies on encoder models, which generate embeddings rather than text. Common examples include:

These models differ from large language models (LLMs), which are designed primarily for text generation rather than semantic encoding.

Applications

Vector-based searching is widely used in the following search and information retrieval systems:

  • Web search engines;
  • Academic and biomedical databases;
  • Retrieval augmented generation (RAG) systems;
  • Recommendation systems;
  • Chatbots and question-answering systems;
  • Image and multimodal search

Hybrid search

Many modern search systems implement hybrid search techniques, combining vector-based search with traditional keyword or Boolean searching approaches. This ensemble approach balances semantic recall with lexical precision and filtering.

Advantages

  • Improved recall for semantically related content;
  • Robust handling of synonyms and paraphrases;
  • Better support for natural-language queries;
  • Cross-lingual and multimodal capabilities.

Limitations

  • Higher computational costs;
  • Reduced transparency compared to keyword matching, "opaque" and black box effects;
  • Potential semantic false positives;
  • Dependence on model quality and training data.

See also

One-sentence definition

Vector-based searching retrieves information by comparing the semantic similarity of vector embeddings rather than matching exact words.

References

Note: I have read widely on this topic, and will be populating this section with an extensive bibliography to support the entry. This is a complex topic so thank you for your patience while I write this entry for librarians and information professionals. Some content was informed by the Wikipedia entry: https://en.wikipedia.org/wiki/Vector_database and https://learn.microsoft.com/en-us/azure/cosmos-db/vector-database and What is Vector search"? https://learn.microsoft.com/en-us/training/modules/improve-search-results-vector-search/2-vector-search

Disclaimer

  • Note: Please use your critical reading skills while reading entries. No warranties, implied or actual, are granted for any health or medical search or AI information obtained while using these pages. Check with your librarian for more contextual, accurate information.
Retrieved from "https://wiki.ubc.ca/index.php?title=Vector-based_searching_and_embeddings&oldid=885117"