Skip to main content
POST
/
v1beta
/
models
/
{model}
:embedContent
embedContent
curl --request POST \
  --url https://openp.ai/v1beta/models/{model}:embedContent
import requests

url = "https://openp.ai/v1beta/models/{model}:embedContent"

response = requests.post(url)

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

fetch('https://openp.ai/v1beta/models/{model}:embedContent', 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://openp.ai/v1beta/models/{model}:embedContent",
  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://openp.ai/v1beta/models/{model}:embedContent"

	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://openp.ai/v1beta/models/{model}:embedContent")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://openp.ai/v1beta/models/{model}:embedContent")

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
Get Gemini embedding vectors. You can also batch via :batchEmbedContents.

​
Request

curl "https://openp.ai/v1beta/models/text-embedding-004:embedContent" \
  -H "x-goog-api-key: $OPENPAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": {"parts": [{"text": "hello world"}]}
  }'

​
Fields

FieldTypeRequiredDescription
content.partsarray✅Array of text segments
taskTypestringRETRIEVAL_QUERY / RETRIEVAL_DOCUMENT / SEMANTIC_SIMILARITY / CLASSIFICATION / CLUSTERING
titlestringCan be attached when taskType=RETRIEVAL_DOCUMENT
outputDimensionalityintegerTruncate dimensions (gemini-embedding-001 only)

​
Response

{
  "embedding": {
    "values": [0.012, -0.034, ..., 0.001]
  }
}

​
Batch embedding

curl "https://openp.ai/v1beta/models/text-embedding-004:batchEmbedContents" \
  -H "x-goog-api-key: $OPENPAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "requests": [
      {"model": "models/text-embedding-004", "content": {"parts": [{"text": "a"}]}},
      {"model": "models/text-embedding-004", "content": {"parts": [{"text": "b"}]}}
    ]
  }'
Returns: 
{
  "embeddings": [
    {"values": [...]},
    {"values": [...]}
  ]
}