Embeddings convert complex data into dense vectors (arrays of numbers) that capture semantic meaning. Similar items have similar embeddings in vector space. Text embeddings are generated by models like text-embedding-ada-002 or nomic-embed-text. Used for similarity search, clustering, classification, and RAG systems. Typically 768-1536 dimensions.
⚙️ AI Infrastructure advanced
Embedding
Numerical vector representation of text, images, or other data for machine learning.
13
views
</> Related Terms
Vector Database
Specialized database for storing and searching high-dimensional vector embeddings.
RAG (Retrieval-Augmented Generation)
AI technique combining vector search with LLMs to provide contextual answers from custom knowledge bases.
pgvector
PostgreSQL extension that adds vector similarity search capabilities for AI and machine learning applications.
Embedding Server
A specialized server that converts text into vector representations (embeddings) for semantic search and RAG applications.