How to beginner · 3 min read

How to use E5 embeddings

Q: How to use E5 embeddings

Use E5 embeddings by calling an embedding model like text-embedding-3-large via the OpenAI API to convert text into dense vectors for semantic search or similarity tasks. Generate embeddings by sending your text input to the client.embeddings.create method and extract the vector from the response.

Quick answer

Use E5 embeddings by calling an embedding model like text-embedding-3-large via the OpenAI API to convert text into dense vectors for semantic search or similarity tasks. Generate embeddings by sending your text input to the client.embeddings.create method and extract the vector from the response.

PREREQUISITES

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

Setup

Install the openai Python package and set your OpenAI API key as an environment variable.

Install package: pip install openai
Set environment variable: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows)

bash

pip install openai

Step by step

This example shows how to generate E5 embeddings for a sample text using the OpenAI Python SDK with the text-embedding-3-large model.

python

import os
from openai import OpenAI

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

text = "OpenAI develops powerful AI models for natural language processing."

response = client.embeddings.create(
    model="text-embedding-3-large",
    input=text
)

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: 1024
First 5 values: [0.0123, -0.0345, 0.0567, -0.0789, 0.0234]

Common variations

You can generate embeddings for multiple texts by passing a list of strings to input. Also, you can use smaller or larger E5 variants like text-embedding-3-small for faster or cheaper embeddings. Async calls are possible with asyncio and the OpenAI SDK's async client.

python

import asyncio
import os
from openai import OpenAI

async def generate_embeddings():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    texts = ["Hello world", "OpenAI embeddings"]
    response = await client.embeddings.acreate(
        model="text-embedding-3-small",
        input=texts
    )
    for i, embedding in enumerate(response.data):
        print(f"Text {i} embedding length: {len(embedding.embedding)}")

asyncio.run(generate_embeddings())

output

Text 0 embedding length: 1024
Text 1 embedding length: 1024

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the embedding vector is empty or missing, check that you are using a valid model name like text-embedding-3-large.
For rate limit errors, implement exponential backoff retries or reduce request frequency.

✅

Key Takeaways

Use the OpenAI SDK's embeddings.create method with text-embedding-3-large to generate E5 embeddings.
Pass single or multiple texts as input to get vector embeddings for semantic tasks.
Set your API key securely via environment variables to avoid authentication issues.
Async embedding generation improves throughput for batch processing.
Check model names and handle rate limits to ensure smooth embedding generation.

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

Verify ↗