Glossary

Semantic Search

Semantic search is a search technique that finds information based on the meaning and intent behind a query rather than matching exact keywords. It uses natural language understanding and vector embeddings to identify content that is conceptually relevant, even when the query and the content share no common words.

How it works

Traditional keyword search operates on a simple principle: match the words in the query to words in the document. "Cancel subscription" only finds documents containing those exact words. Semantic search understands that "cancel subscription," "end my plan," "stop my membership," and "I want out" all mean the same thing.

Semantic search works by: 1. **Encoding**: Converting both queries and documents into vector embeddings using neural network models 2. **Indexing**: Storing document embeddings in a vector database for fast retrieval 3. **Querying**: Converting the search query into an embedding and finding the closest document vectors 4. **Ranking**: Ordering results by semantic similarity (cosine distance) to the query

The quality of semantic search depends heavily on the embedding model used. Modern models like OpenAI text-embedding-3 and Cohere embed-v4 achieve near-human accuracy on semantic similarity tasks, making them reliable for production customer support applications.

Why it matters

Customers never phrase questions the same way documentation is written. A help article titled "Managing Your Subscription" needs to be found when a customer asks "how do I change my plan." Semantic search bridges this vocabulary gap, making AI chatbots dramatically more helpful than keyword-based search. It is the key technology that makes RAG systems work effectively.

How Chatsy uses semantic search

Chatsy uses semantic search as one half 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 stored in pgvector. The most semantically relevant passages are retrieved and combined with BM25 keyword results for maximum accuracy.

Real-world examples

Vocabulary gap bridging

A customer asks "how do I get my money back?" The knowledge base article is titled "Refund Policy and Return Process." No words overlap between the query and the title. Semantic search still matches them with high confidence because the meaning is the same — the customer gets their answer instantly.

Intent-aware search results

Two customers search for "security." Customer A asks "is my data secure?" (seeking privacy/compliance information). Customer B asks "how do I set up security for my team?" (seeking access control instructions). Semantic search understands the different intents and returns different articles for each query.

Cross-language search

A French customer asks "Comment changer mon mot de passe?" Multilingual embedding models map this query near the English article "How to Reset Your Password" in vector space. The customer gets the right article without needing a French translation of the knowledge base.

Key takeaways

Semantic search matches content by meaning, not keywords — bridging the vocabulary gap between customers and documentation
It uses vector embeddings to represent text as numerical vectors where similar meanings cluster together
Semantic search is the key technology that makes RAG retrieval effective for AI chatbots
Modern embedding models achieve near-human accuracy on semantic similarity, making them production-ready
Best results come from combining semantic search with keyword search (hybrid search) for maximum recall

Frequently asked questions

How is semantic search different from keyword search?

Keyword search matches exact words — "cancel" only finds documents containing "cancel." Semantic search matches meaning — "cancel" also finds "terminate," "end," "discontinue," and "stop." Semantic search understands synonyms, paraphrases, and conceptual similarity without requiring exact word matches.

Is semantic search the same as vector search?

They are closely related but not identical. Semantic search is the goal (finding content by meaning). Vector search is the technical mechanism (comparing vector embeddings). Semantic search typically uses vector search as its implementation, but can also incorporate other signals like knowledge graphs or entity recognition.

Does semantic search work well with short queries?

Short queries (1-2 words) produce less precise semantic embeddings because there is less context to encode. For queries like just "pricing," keyword search can outperform semantic search. This is why hybrid search (combining both methods) is recommended — keyword search handles short, specific queries while semantic search handles longer, natural language questions.

How accurate is semantic search for customer support?

With modern embedding models, semantic search achieves 85-95% relevance accuracy on well-structured knowledge base content. Accuracy improves with: higher quality embedding models, well-written focused articles, appropriate chunk sizes (300-500 words), and hybrid search combining semantic and keyword approaches.

Related terms

Vector Search

Vector search is a method of finding information based on semantic meaning rather than exact keyword matches. It works b...

Embedding

An embedding is a dense numerical vector (array of numbers) that represents the semantic meaning of a piece of text. Emb...

Hybrid Search

Hybrid search is a retrieval method that combines semantic search (vector/embedding-based) with lexical search (keyword/...

Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation (RAG) is an AI architecture that enhances large language model responses by first retriev...