How to beginner · 4 min read

How to use OpenAI embeddings API

Q: How to use OpenAI embeddings API

Use the OpenAI embeddings API by calling client.embeddings.create with your input text and a model like text-embedding-3-small. The API returns a vector embedding as a list of floats representing the semantic meaning of the input.

Quick answer

Use the OpenAI embeddings API by calling client.embeddings.create with your input text and a model like text-embedding-3-small. The API returns a vector embedding as a list of floats representing the semantic meaning of the input.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official OpenAI Python SDK and set your API key as an environment variable for secure authentication.

bash

pip install openai>=1.0

Step by step

This example shows how to generate an embedding vector for a sample text using the text-embedding-3-small model.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="OpenAI embeddings API example"
)

embedding_vector = response.data[0].embedding
print(f"Embedding vector length: {len(embedding_vector)}")
print(f"First 5 values: {embedding_vector[:5]}")

output

Embedding vector length: 1536
First 5 values: [0.0123, -0.0345, 0.0567, -0.0789, 0.0234]

Common variations

Use different embedding models like text-embedding-3-large for higher quality vectors.
Batch multiple inputs by passing a list of strings to input.
Use async calls with asyncio for concurrent embedding generation.

python

import asyncio
import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

async def get_embeddings():
    response = await client.embeddings.acreate(
        model="text-embedding-3-small",
        input=["First text", "Second text"]
    )
    for i, embedding in enumerate(response.data):
        print(f"Embedding {i} length: {len(embedding.embedding)}")

asyncio.run(get_embeddings())

output

Embedding 0 length: 1536
Embedding 1 length: 1536

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
For rate limit errors, implement exponential backoff retries.
Ensure your input text is not empty or too long; the API has input size limits.

✅

Key Takeaways

Use client.embeddings.create with a suitable model to get vector embeddings.
Embedding vectors are lists of floats representing semantic meaning for downstream tasks.
Batch inputs and async calls improve efficiency for multiple embeddings.
Always secure your API key via environment variables to avoid leaks.
Handle API errors like authentication and rate limits gracefully.

Verified 2026-04 · text-embedding-3-small, text-embedding-3-large

Verify ↗