embeddings model

The model used to convert text/images into vectors before storing or querying. Must use the same model for both indexing and querying to ensure comparable vectors.

Syntax

vector-databases

vectors = model.encode(texts)  # always use same model for index + query

Example

vector-databases

# Popular embedding models:

# OpenAI (1536 dims, high quality):
from openai import OpenAI
client = OpenAI()
response = client.embeddings.create(model="text-embedding-3-small", input=texts)
vectors = [r.embedding for r in response.data]

# Local (384 dims, free, fast):
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("all-MiniLM-L6-v2")
vectors = model.encode(texts)

# CRITICAL: same model for index + query!