Generate Text Embeddings

curl --request POST \
  --url https://api.nugen.in/api/v3/inference/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "The quick brown fox jumped over the lazy dog",
  "model": "nugen-flash-embed",
  "dimensions": 123
}
'

import requests

url = "https://api.nugen.in/api/v3/inference/embeddings"

payload = {
    "input": "The quick brown fox jumped over the lazy dog",
    "model": "nugen-flash-embed",
    "dimensions": 123
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: 'The quick brown fox jumped over the lazy dog',
    model: 'nugen-flash-embed',
    dimensions: 123
  })
};

fetch('https://api.nugen.in/api/v3/inference/embeddings', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.nugen.in/api/v3/inference/embeddings",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => 'The quick brown fox jumped over the lazy dog',
    'model' => 'nugen-flash-embed',
    'dimensions' => 123
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.nugen.in/api/v3/inference/embeddings"

	payload := strings.NewReader("{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.nugen.in/api/v3/inference/embeddings")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.nugen.in/api/v3/inference/embeddings")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}"

response = http.request(request)
puts response.read_body

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Inference

Generate Text Embeddings

Generate dense vector embeddings for input text.

This endpoint creates numerical vector representations (embeddings) of text using specified embedding models. Embeddings are useful for semantic search, clustering, similarity comparisons, and RAG applications.

Request Body:

model: Embedding model ID (required) - Name of the model to use for generating embeddings
input: Text or list of texts to embed (required) - Single string or array of strings. Cannot be empty and must not exceed max input tokens for the model
dimensions (optional): Number of dimensions for output embeddings (only applicable for Resizable Matryoshka Embedding models)

Returns:

id: Unique identifier for the response
object: Object type (always embedding)
data: List of embedding objects, each containing:
- object: Object type (always embedding)
- embedding: Vector of floats representing the text (length depends on the model)
- index: Position in the input array
model: Model ID used for generation
created: Unix timestamp (seconds) when response was generated
usage: Token usage statistics containing:
- total_tokens: Total number of tokens used by the request

Example Request (Single Text):

POST /api/v3/inference/embeddings
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model": "text-embedding-xyz",
  "input": "The quick brown fox jumps over the lazy dog"
}

Example Request (Multiple Texts):

POST /api/v3/inference/embeddings
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model": "aligned-model-01kmqm4nrn9fw6r",
  "input": [
    "First document for semantic search",
    "Second document for clustering",
    "Third document for similarity comparison"
  ]
}

Example Request (With Dimensions):

POST /api/v3/inference/embeddings
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model": "aligned-model-01kmqm4nrn9fw6r",
  "input": "Sample text to embed",
  "dimensions": 512
}

Example Response:

{
  "id": "embed-abc123xyz",
  "object": "embedding",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.00658765, -0.008665467, -0.007653789, 0.0023, -0.0091, 0.0125],
      "index": 0
    }
  ],
  "model": "text-embedding-ada-002",
  "created": 1705329600.0,
  "usage": {
    "total_tokens": 10
  }
}

Notes:

Input must not exceed the maximum input tokens supported by the model
Input cannot be an empty string
For batch processing, pass multiple texts as an array to the input field
The embedding vector length varies by model - check model documentation for specifics
Use dimensions parameter only with Matryoshka embedding models that support resizing

POST

api

inference

embeddings

Generate Text Embeddings

curl --request POST \
  --url https://api.nugen.in/api/v3/inference/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "The quick brown fox jumped over the lazy dog",
  "model": "nugen-flash-embed",
  "dimensions": 123
}
'

import requests

url = "https://api.nugen.in/api/v3/inference/embeddings"

payload = {
    "input": "The quick brown fox jumped over the lazy dog",
    "model": "nugen-flash-embed",
    "dimensions": 123
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: 'The quick brown fox jumped over the lazy dog',
    model: 'nugen-flash-embed',
    dimensions: 123
  })
};

fetch('https://api.nugen.in/api/v3/inference/embeddings', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.nugen.in/api/v3/inference/embeddings",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => 'The quick brown fox jumped over the lazy dog',
    'model' => 'nugen-flash-embed',
    'dimensions' => 123
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.nugen.in/api/v3/inference/embeddings"

	payload := strings.NewReader("{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.nugen.in/api/v3/inference/embeddings")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.nugen.in/api/v3/inference/embeddings")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"The quick brown fox jumped over the lazy dog\",\n  \"model\": \"nugen-flash-embed\",\n  \"dimensions\": 123\n}"

response = http.request(request)
puts response.read_body

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

input

required

Input text to embed, encoded as a string or a list of strings. To embed multiple inputs in a single request, pass a list of strings. The input must not exceed the max input tokens for the model, cannot be an empty string.

Example:

"The quick brown fox jumped over the lazy dog"

model

string

required

The name of the model used to generate the embedding.

Example:

"nugen-flash-embed"

dimensions

integer | null

(Applicable for only Resizable Matryoshka Embedding models) The number of dimensions the resulting output embeddings should have.

Response

Vector embeddings and usage statistics

Delete Evaluation Generate Completions