Back to Glossary
Artificial Intelligence
AI Embedding
An embedding is a vector representation of data (text, images) that captures semantic meaning.
Definition
An embedding is a numerical vector representation of data — text, images, audio, or video — that captures semantic relationships. Embeddings are generated by AI models (e.g., OpenAI text-embedding-3, BGE, Cohere embed) and are used for: (1) Semantic search — finding similar content by vector distance, (2) Clustering — grouping similar items, (3) Classification — using embeddings as features, (4) RAG — retrieving relevant context for LLMs. Embedding models typically output 256-1536 dimensional vectors. Harch Corp provides fast embedding inference on GPU cloud.
Related Keywords
embeddingai embeddingtext embeddingvector embeddingsemantic embedding
Related Terms
Vector Database
A vector database stores and queries high-dimensional vectors for AI similarity search.
RAG (Retrieval-Augmented Generation)
RAG combines a retrieval system with an LLM to ground responses in external knowledge.
AI Inference
AI inference is the process of using a trained model to make predictions on new data.