Embeddings

Generate high-quality vector embeddings for text using the Gravix Layer API. This endpoint is compatible with OpenAI's embedding API and supports seamless integration in Python and JavaScript.

---

Quickstart

Get started by calling the embeddings endpoint with your API key and model of choice.

Endpoint

POST /v1/inference/embeddings

Request Headers

Content-Type: "application/json"
Authorization: Bearer GRAVIXLAYER_API_KEY

---

Example Usage

cURL

curl https://api.gravixlayer.com/v1/inference/embeddings \
  -H "Authorization: Bearer $GRAVIXLAYER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Why is the sky blue?",
    "model": "meta-llama/llama-3.1-8b-instruct"
  }'

Python - OpenAI

import os
import json
from openai import OpenAI

client = OpenAI(
    base_url="https://api.gravixlayer.com/v1/inference",
    api_key=os.environ.get("GRAVIXLAYER_API_KEY"),
)

embedding = client.embeddings.create(
    model="meta-llama/llama-3.1-8b-instruct",
    input="Why is the sky blue?",
)

print(json.dumps(embedding.model_dump(), indent=2))

Python - Gravix SDK

import os
from gravixlayer import GravixLayer

# Make sure to export your API key in the environment
# export GRAVIXLAYER_API_KEY=your_api_key_here
client = GravixLayer()
embedding = client.embeddings.create(
  model="meta-llama/llama-3.1-8b-instruct",
  input="Why is the sky blue?",
)
import json
print(json.dumps(embedding.model_dump(), indent=2))

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.GRAVIXLAYER_API_KEY,
    baseURL: "https://api.gravixlayer.com/v1/inference"
});

async function main() {
    const embedding = await openai.embeddings.create({
        model: "meta-llama/llama-3.1-8b-instruct",
        input: "Why is the sky blue?",
        encoding_format: "float",
    });

    console.log(JSON.stringify(embedding, null, 2));
}

main();

---

Response

The API returns a JSON response with the following structure:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        -0.0028842222,
        "... (1536 floats total for text-embedding-ada-002)"
      ],
      "index": 0
    }
  ],
  "model": "meta-llama/llama-3.1-8b-instruct",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}

---