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.

Generating Embeddings with text-embedding-3 is a free AI Agents lesson on CoddyKit — lesson 2 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the AI Agents learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.

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

Batch Embedding

The API supports lists — much faster than calling one at a time:

texts = ['cat', 'dog', 'pizza', 'sushi']
resp = client.embeddings.create(
    model='text-embedding-3-small',
    input=texts
)
vectors = [d.embedding for d in resp.data]
# vectors[0] is for 'cat', vectors[1] for 'dog', etc.

Token Limits

Each input has a max token limit (8192 for text-embedding-3). Long documents must be chunked first.

Reducing Dimensions

You can ask for fewer dimensions (Matryoshka embeddings) — useful for storage:

resp = client.embeddings.create(
    model='text-embedding-3-large',
    input='Hello',
    dimensions=512    # default would be 3072
)

Cost

As of writing:

text-embedding-3-small: $0.02 / 1M tokens
text-embedding-3-large: $0.13 / 1M tokens

Embedding 1M words ~ $0.025 with the small model — essentially free.

Embedding Once, Reusing Forever

Embeddings do not change as you re-embed — you can compute them once and store them. Caching is essential for any production system.

Normalising Vectors

OpenAI embeddings are already L2-normalised (length = 1). This means cosine similarity = dot product, saving compute:

import numpy as np
a = np.array(vec_a)
b = np.array(vec_b)
sim = np.dot(a, b)     # since |a| = |b| = 1

Async Embedding

For high throughput, use the async client:

from openai import AsyncOpenAI
import asyncio

client = AsyncOpenAI()

async def embed_batch(texts):
    resp = await client.embeddings.create(
        model='text-embedding-3-small',
        input=texts
    )
    return [d.embedding for d in resp.data]

vectors = asyncio.run(embed_batch(['a', 'b', 'c']))

Retry on Failure

Embedding calls fail like any HTTP call. Wrap in retry-with-backoff:

from tenacity import retry, wait_exponential, stop_after_attempt

@retry(wait=wait_exponential(multiplier=1, max=10), stop=stop_after_attempt(5))
def safe_embed(text):
    return client.embeddings.create(model='text-embedding-3-small', input=text)

Storing Embeddings

Three common storage options:

SQLite with the sqlite-vec extension
Postgres with the pgvector extension
Dedicated vector DB (Pinecone, Qdrant, Weaviate)

Cost Awareness

Roughly how much does it cost to embed 1 million words with text-embedding-3-small?

Recap

Pick text-embedding-3-small, batch your calls, store the vectors, and you have the foundation of semantic search.

Frequently asked questions

Is the “Generating Embeddings with text-embedding-3” lesson free?

Yes — the full text of “Generating Embeddings with text-embedding-3” is free to read here on the web, and the AI Agents course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the AI Agents course, upgrade to CoddyKit PRO.

What will I learn in “Generating Embeddings with text-embedding-3”?

Use OpenAI text-embedding-3-small/large to convert strings into 1536- or 3072-dim vectors. You practise AI Agents with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.

Do I need any experience to start AI Agents?

No prior experience is required. AI Agents on CoddyKit is structured for beginners through advanced learners; this is — lesson 2 of 4, so you can start here or from the beginning and move at your own pace.

How long does the “Generating Embeddings with text-embedding-3” lesson take?

Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.

Can I write and run code in this AI Agents lesson?

Yes. Every AI Agents lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.

All lessons in this course

What Embeddings Are (Vector Representations)
Generating Embeddings with text-embedding-3
Cosine Similarity for Retrieval
Embedding Models Compared (OpenAI vs Cohere vs OSS)

← Back to AI Agents