POST /v1/embeddings

Generate vector embeddings for text inputs.

• Method: POST
• Path: /v1/embeddings
• Auth: Bearer token in Authorization header
• Content-Type: application/json

Request parameters

• model (string, required): Embedding model ID.
• input (required): One of:
  • single string
  • array of strings
  • array of integers (token IDs)
  • array of arrays of integers (batched token IDs)
• dimensions (integer, optional): Target dimensionality if the model supports it.
• encoding_format (enum, optional, default "float"): "float" or "base64".

Example Request

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

resp = client.embeddings.create(
    model="text-embedding-3-small",
    input=[
        "The food was delicious!",
        "Service could be faster."
    ],
    # dimensions=512,  # if supported
    # encoding_format="base64",
)
print(resp)

Node.js

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: "YOUR_API_KEY" });

const resp = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: ["The food was delicious!", "Service could be faster."],
  // dimensions: 512, // if supported
  // encoding_format: "base64",
});
console.log(resp);

cURL

curl https://api.naga.ac/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["The food was delicious!", "Service could be faster."]
  }'

Authentication

Provide your key as a Bearer token:

Authorization: Bearer YOUR_API_KEY

Response

Returns embedding vectors per input. The structure is compatible with OpenAI's embeddings API. When encoding_format="float", vectors are float arrays; with "base64", vectors are base64-encoded.

Response Fields

• object (string): Always "list"
• data (array): Array of embedding objects
  • object (string): Always "embedding"
  • embedding (array): The embedding vector (float array or base64 string)
  • index (integer): Index of this embedding in the input array
• model (string): The model used for embeddings
• usage (object): Token usage information
  • prompt_tokens (integer): Number of tokens in the input
  • total_tokens (integer): Total tokens processed