Skip to main content
POST
/
v1
/
indexes
/
create
Create Index
curl --request POST \
  --url https://api.example.com/v1/indexes/create
import requests

url = "https://api.example.com/v1/indexes/create"

response = requests.post(url)

print(response.text)
const options = {method: 'POST'};

fetch('https://api.example.com/v1/indexes/create', 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.example.com/v1/indexes/create",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

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

curl_close($curl);

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

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

func main() {

	url := "https://api.example.com/v1/indexes/create"

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

	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.example.com/v1/indexes/create")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/indexes/create")

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

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body
Create a new encrypted index with the specified configuration.

​
Request Body

{
  "index_name": "my_index",
  "index_key": "64_character_hex_string_representing_32_bytes",
  "index_config": {
    "type": "ivfpq",
    "dimension": 384,
    "pq_dim": 64,
    "pq_bits": 8
  },
  "metric": "euclidean",
  "embedding_model": "all-MiniLM-L6-v2"
}

​
Index Types

Suitable for applications requiring high recall with moderate memory usage: 
{
  "type": "ivfflat",
  "dimension": 384
}
Speed: Fast | Recall: Highest | Index Size: Biggest

​
IVFSQ

Scalar Quantization compresses each dimension independently, balancing speed and index size: 
{
  "type": "ivfsq",
  "dimension": 384,
  "sq_bits": 16
}
Speed: Fast | Recall: High | Index Size: Small

​
IVFPQ

Product Quantization compresses embeddings, balancing memory use and recall: 
{
  "type": "ivfpq",
  "dimension": 384,
  "pq_dim": 64,
  "pq_bits": 8
}
Speed: Fast | Recall: High | Index Size: Medium

​
IVF (Deprecated)

The ivf type is deprecated. Use ivfflat instead, which provides equivalent functionality.

​
Distance Metrics

  • "euclidean": Euclidean distance
  • "cosine": Cosine similarity
  • "squared_euclidean": Squared Euclidean distance

​
Response

{
  "status": "success",
  "message": "Index 'my_index' created successfully"
}

​
Exceptions

  • 401: Authentication failed (invalid API key)
  • 409: Index name already exists
  • 422: Invalid request parameters
  • 500: Internal server error

​
Example Usage

curl -X POST "http://localhost:8000/v1/indexes/create" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "index_config": {
         "type": "ivfflat",
         "dimension": 384
       }
     }'

​
With Auto-Embedding

# With explicit index config
curl -X POST "http://localhost:8000/v1/indexes/create" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "semantic_search_index",
       "index_key": "your_64_character_hex_key_here",
       "index_config": {
         "type": "ivfflat"
       },
       "embedding_model": "all-MiniLM-L6-v2"
     }'

# Minimal configuration - index_config defaults to IVFFlat
curl -X POST "http://localhost:8000/v1/indexes/create" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "auto_index",
       "index_key": "your_64_character_hex_key_here",
       "embedding_model": "all-MiniLM-L6-v2"
     }'
When embedding_model is specified:
  • The dimension parameter in index_config is optional
  • The entire index_config object is optional (defaults to IVFFlat with auto-detected dimension)
  • The index will automatically generate embeddings for text content during upsert operations