0PricingLogin▼
AI Agents · Lesson

Generating Embeddings with text-embedding-3

Use OpenAI text-embedding-3-small/large to convert strings into 1536- or 3072-dim vectors.

OpenAI Embedding Models

OpenAI offers two production embedding models:

  • text-embedding-3-small — 1536 dim, cheap, fast
  • text-embedding-3-large — 3072 dim, better quality, slower

Use small for most cases; large only when quality matters more than cost.

Your First Embedding

One line of SDK code:

from openai import OpenAI
client = OpenAI()

resp = client.embeddings.create(
    model='text-embedding-3-small',
    input='Hello, world!'
)
vector = resp.data[0].embedding
print(len(vector))      # 1536

All lessons in this course

  1. What Embeddings Are (Vector Representations)
  2. Generating Embeddings with text-embedding-3
  3. Cosine Similarity for Retrieval
  4. Embedding Models Compared (OpenAI vs Cohere vs OSS)
← Back to AI Agents