Skip to main content

Glossary · ai

Embedding

Definition

An embedding represents text/images/audio as a numerical vector (1024-3072 dim). Closer meanings produce closer vectors — 'dog' and 'cat' are close, 'dog' and 'car' are far. It's the mathematical foundation of RAG, semantic search, and recommendations.

Published: 2026-05-05Updated: 2026-05-05

Detailed explanation

Embeddings are 'meaning coordinates'. Each word/sentence/doc is a point in space; semantically similar items are close. 'Weather is nice in Istanbul' and 'Istanbul is sunny today' yield cosine similarity 0.85+; 'Istanbul is nice' and 'Python code' return 0.3.

2026 models: OpenAI text-embedding-3-large (3072 dim, most common), Cohere embed-v3 (1024 dim, multilingual), Voyage AI voyage-3-large (1024 dim, leader in code + multilingual), BGE-M3 (open source, self-host).

Turkish quality: Cohere multilingual + Voyage are better in Turkish. OpenAI is acceptable but weak on Turkish-specific details. Cost: OpenAI $0.13/1M tokens; 100K docs × 500 tokens = 50M tokens = $6.5 one-off.

Use cases

RAG retrieval (search inside a vector DB)

Semantic search (beyond keywords)

Clustering (group similar product/content)

Anomaly detection (outlier vectors)

Recommendation (user-product similarity)

Pros

  • +Turns meaning into numbers (works in algorithms)
  • +Multi-modal (text + image + audio same space)
  • +Cross-language (with multilingual models)
  • +Compact (1KB-12KB per chunk)

Cons

  • Re-embedding when model updates (high cost)
  • Storage cost (vector DB)
  • Quality bound to model (bad embedding = bad retrieval)

Related terms

Vector DBRAGCosine SimilarityLLM

Related services

Planning a project around Embedding?

In a 30-minute discovery call we share a written architecture + cost + team recommendation tailored to your project.

Start a discovery call