Vector
ELI5 — The Vibe Check
In AI, a vector is just a list of numbers. But it's a list of numbers that means something — like 0.23, -0.91, 0.44, ... might represent the concept 'angry cat.' The closer two vectors are in space, the more similar their meanings. Vectors are how computers handle meaning mathematically.
Real Talk
In machine learning, a vector is a one-dimensional array of floating-point numbers representing a point in high-dimensional space. Embeddings are vectors, model weights are tensors of vectors, and activations throughout a neural network are vector operations. Similarity between vectors is measured via cosine similarity or dot product.
When You'll Hear This
"Each sentence becomes a 768-dimensional vector." / "Find the nearest vector in the database."
Related Terms
Cosine Similarity
Cosine similarity measures how similar two things are by comparing the angles of their vectors.
Embedding
An embedding is turning words, sentences, or entire documents into lists of numbers (vectors) that capture their meaning.
RAG (Retrieval Augmented Generation)
RAG is how you give an AI access to your private documents without retraining it.
Vector Database
A vector database is a special database built to store and search embeddings.