Definition
Vector embedding
A vector embedding is a numerical representation of text (or an image, or audio) as a list of floating-point numbers, produced by a model so that semantically similar inputs land close together in high-dimensional space. Embeddings are what let software compare meaning rather than spelling — the foundation of semantic search, retrieval-augmented generation, and recommendation.
Key takeaways
- A vector embedding represents content as a list of numbers so semantically similar inputs land close together.
- It lets software compare meaning rather than spelling — the foundation of semantic search, RAG, and recommendation.
- Content is embedded once and stored in a vector index so similarity lookups stay fast.
- Planoda embeds issues and documents into HNSW-indexed vectors in PostgreSQL, scoped per tenant.
Computers compare numbers, not meaning. An embedding model bridges the gap by mapping a piece of content to a fixed-length vector whose geometry encodes meaning: two phrases about the same idea — 'sign-in fails' and 'authentication error' — map to nearby vectors even with no shared words, while unrelated phrases map far apart. Distance in this space becomes a usable proxy for semantic similarity.
Once content is embedded, a whole family of capabilities follows. Search becomes nearest-neighbor lookup; retrieval for an AI answer becomes fetching the closest vectors to the question; clustering, deduplication, and recommendation all reduce to operations on the same geometry. The embedding is computed once per item and stored in a vector index so these lookups stay fast.
Planoda embeds issues and documents into vectors stored with HNSW indexes in PostgreSQL, so its search and AI features retrieve by meaning — fast, and scoped strictly to a single tenant's data.
Related terms
- EmbeddingAn embedding is a numeric vector that represents a piece of content — text, image, or other data — as a point in high-dimensional space, positioned so that similar items land near each other. Produced by a model trained to capture meaning, embeddings let software compare content by semantic similarity rather than by matching exact words.
- Semantic SearchSemantic search finds results by meaning rather than exact keywords, using vector embeddings that place similar concepts near each other in mathematical space. A query for 'login broken' can surface an issue titled 'users can't authenticate' even with no shared words. It powers more relevant search and is the retrieval layer behind many AI features.
- HNSW indexAn HNSW (Hierarchical Navigable Small World) index is a data structure for approximate nearest-neighbor search over vector embeddings. It organizes vectors into a layered graph that can be traversed greedily, so a query finds its closest matches in roughly logarithmic time instead of comparing against every vector — the workhorse that makes semantic search and RAG fast at scale.
- Vector DatabaseA vector database stores data as high-dimensional embeddings and retrieves items by similarity rather than exact match. Given a query vector, it returns the nearest stored vectors — the records most similar in meaning. Specialized indexes make this fast across millions of items, making vector databases the retrieval backbone of semantic search and AI applications.
- Retrieval-Augmented Generation (RAG)Retrieval-augmented generation (RAG) grounds a language model's answers in your own data by retrieving the most relevant documents at query time and feeding them into the model's context before it responds. Instead of relying solely on what the model memorized in training, RAG lets it answer from current, authoritative, private sources — sharply reducing hallucination.