Skip to content

Vector Search

Definition

Vector search is a method of finding information based on semantic meaning rather than exact keyword matches. It works by converting text into numerical representations (vectors/embeddings) and finding the most similar vectors in a database. Also called semantic search or similarity search.

How it works

Traditional keyword search requires exact word matches, searching for "pricing" will not find a document about "cost" or "fees." Vector search understands that these words are semantically related. It converts both the query and all documents into high-dimensional vectors using embedding models, then finds the documents whose vectors are closest to the query vector.

Vector databases like pgvector, Pinecone, and Weaviate store these embeddings and perform fast similarity searches. The quality of vector search depends on the embedding model used, better models create more accurate semantic representations.

Why it matters

Vector search is essential for AI chatbots because customers phrase questions in unpredictable ways. A customer asking "how do I change my subscription" should match a knowledge base article titled "Manage your plan" even though no words overlap. Vector search bridges this vocabulary gap, making AI chatbots significantly more helpful than keyword-based search.

How Chatsy uses it

Chatsy uses pgvector for vector search as part of its hybrid search system. When a customer asks a question, the query is embedded into a vector and compared against all knowledge base content embeddings to find semantically relevant passages. This is combined with BM25 full-text search for maximum recall.

Chatsy

What else should I know about Vector Search?

Embedding models convert text into high-dimensional numerical vectors where similar meanings cluster together

Key takeaways

Test this in your own agent

Add your help content, ask the questions on this page, and check every answer before you publish.

Start free

Chatsy

Example scenarios

  1. 01

    Synonym matching in support queries

    A customer searches for "refund policy" but the help article is titled "Returns and money-back guarantee." Vector search finds the article because both phrases share semantic meaning, where keyword search would return zero results.

  2. 02

    Multilingual query resolution

    A Spanish-speaking customer types "como cancelar mi cuenta" and the vector search matches it to an English knowledge base article about account cancellation, because multilingual embedding models map both phrases to a similar region in vector space.

  3. 03

    Handling typos and shorthand

    A customer types "cant login 2fa broken", informal, abbreviated text. Vector search still matches it to a well-written article titled "Troubleshooting two-factor authentication issues" because the semantic intent is the same.

Key takeaways

  • Vector search matches by meaning rather than exact keywords, bridging the vocabulary gap between customers and documentation
  • Embedding models convert text into high-dimensional numerical vectors where similar meanings cluster together
  • Vector databases (pgvector, Pinecone, Weaviate) are purpose-built for fast similarity search at scale
  • Search quality depends directly on the embedding model, better models produce more accurate semantic representations
  • Vector search is most effective when combined with keyword search in a hybrid approach for maximum recall

When it does not apply

  • You have fewer than 1,000 documents. Keyword search is fine.
  • Your queries are exact-match (product SKUs, IDs). Use traditional indexing.
  • Your content updates several times per day and re-embedding cost outweighs the recall gain.

Frequently asked questions

Keyword search matches exact words. Vector search matches meaning. Searching for "cancel my account" with keyword search only finds documents containing those exact words. Vector search also finds documents about "close account," "delete profile," or "end subscription" because they have similar meaning.

A vector database is specialized storage for embedding vectors that supports fast similarity search. Examples include pgvector (PostgreSQL extension), Pinecone, Weaviate, and Qdrant. Chatsy uses pgvector to keep everything in PostgreSQL.

Vector search with optimized indexes (HNSW or IVFFlat) returns results in 5-50 milliseconds for databases with millions of vectors. This is comparable to keyword search and fast enough for real-time chatbot responses.

Short queries produce less precise vectors because there is less semantic context to encode. For single-word queries like "pricing," keyword search often outperforms vector search, which is why hybrid search combining both methods is recommended.

Vector search is a way of finding "things that mean roughly the same thing" instead of "things that contain the exact same words." It turns each piece of text into a list of numbers (a vector) so the computer can measure how close two ideas are mathematically, even when the words are different.

Elasticsearch is a search engine traditionally built around inverted-index keyword search (BM25). Vector search uses embeddings and similarity scoring instead. Modern Elasticsearch and OpenSearch now support vector search natively, so the practical question is usually keyword vs hybrid vs pure vector, not Elasticsearch vs vector.

A vector lookup is a single similarity query against a vector database: you give it a query embedding and it returns the top-K most similar stored embeddings. In a chatbot pipeline, each customer message triggers one or more vector lookups to find the most relevant knowledge base passages before the LLM generates a response.

Related terms

Browse the glossary

Further reading

Browse the glossary

See these concepts in action

Try Chatsy free and experience how these concepts come together in an AI-powered support platform.

Start freeSee Chatsy features