What is Semantic Search?

Retrieval that represents a query and candidates in an embedding space and ranks candidates using a vector-similarity function.

What people say

“Search by meaning instead of exact words.”

Why does Semantic Search matter?

It can retrieve paraphrases and conceptually related text, but exact identifiers and rare strings may still need lexical search.

Lessons that name Semantic Search in a title or section

Capstone 02 — RAG over Codebase (Cross-Repo Semantic Search)
Every serious engineering org in 2026 runs an internal code search that understands meaning, not just strings. Sourcegraph Amp, Cursor's codebase answers, Augment's enterprise graph, Aider's…
Phase 19: Capstone Projects
Embeddings & Vector Representations
Text is discrete. Math is continuous. Every time you ask an LLM to find "similar" documents, compare meanings, or search beyond keywords, you're relying on a bridge between these two worlds.
Phase 11: LLM Engineering

EmbeddingA learned mapping from discrete items (words, images, users) to dense vectors in continuous space, where similar items end up close together
Hybrid RetrievalRetrieval that combines signals from different methods, commonly lexical matching and dense-vector similarity, before merging or reranking…
Vector DatabaseA storage and indexing system that supports nearest-neighbor queries over vector representations, often with metadata filtering,…
RerankerA second-stage model or scoring function that reorders a small candidate set using a richer comparison between the query and each candidate.
Cosine SimilarityThe normalized dot product of two vectors. It compares their direction rather than their magnitude and ranges from -1 to 1 for real-valued…
Dense RetrievalFirst-stage retrieval that embeds queries and candidates into vector representations and ranks candidates by a similarity function.
Precision & RecallPrecision asks how many flagged items were correct; recall asks how many relevant items were found.
Shared Embedding SpaceA common vector space in which representations from different modalities can be compared with the same similarity function.