Generate Image Embedding

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/embeddings/image \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=multimodalembedding@001 \
  --form file='@example-file'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/embeddings/image"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "model": "multimodalembedding@001" }
headers = {"Authorization": "<api-key>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('model', 'multimodalembedding@001');
form.append('file', '<string>');

const options = {method: 'POST', headers: {Authorization: '<api-key>'}};

options.body = form;

fetch('https://mavi-backend.memories.ai/serve/api/v2/embeddings/image', 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://mavi-backend.memories.ai/serve/api/v2/embeddings/image",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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://mavi-backend.memories.ai/serve/api/v2/embeddings/image"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/embeddings/image")
  .header("Authorization", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/embeddings/image")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "code": 200,
  "msg": "success",
  "data": {
    "embedding": [
      0.0234375,
      -0.015625,
      0.0078125,
      0.0390625,
      -0.0234375,
      "... (continues for vector length)"
    ]
  },
  "success": true,
  "failed": false
}

POST

embeddings

image

Generate Image Embedding

curl --request POST \
  --url https://mavi-backend.memories.ai/serve/api/v2/embeddings/image \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=multimodalembedding@001 \
  --form file='@example-file'

import requests

url = "https://mavi-backend.memories.ai/serve/api/v2/embeddings/image"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "model": "multimodalembedding@001" }
headers = {"Authorization": "<api-key>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('model', 'multimodalembedding@001');
form.append('file', '<string>');

const options = {method: 'POST', headers: {Authorization: '<api-key>'}};

options.body = form;

fetch('https://mavi-backend.memories.ai/serve/api/v2/embeddings/image', 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://mavi-backend.memories.ai/serve/api/v2/embeddings/image",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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://mavi-backend.memories.ai/serve/api/v2/embeddings/image"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/embeddings/image")
  .header("Authorization", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mavi-backend.memories.ai/serve/api/v2/embeddings/image")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nmultimodalembedding@001\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "code": 200,
  "msg": "success",
  "data": {
    "embedding": [
      0.0234375,
      -0.015625,
      0.0078125,
      0.0390625,
      -0.0234375,
      "... (continues for vector length)"
    ]
  },
  "success": true,
  "failed": false
}

Product: Visual Intelligence — Embeddings Use case: Generate vector embeddings for image, video, or text inputs for semantic search and similarity tasks Host: https://mavi-backend.memories.ai/serve/api/v2 Auth: Authorization: sk-mavi-... (no Bearer prefix)

This endpoint generates vector embeddings for images. You can either upload an image file directly or reference an existing asset by its ID.

Pricing:

$0.0001 per image

Code Examples

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";

const formData = new FormData();
formData.append('file', imageFile);
formData.append('model', 'multimodalembedding@001');

const response = await fetch(`${BASE_URL}/embeddings/image`, {
  method: 'POST',
  headers: {
    'Authorization': API_KEY
  },
  body: formData
});

const data = await response.json();
console.log(data);

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";

const response = await fetch(`${BASE_URL}/embeddings/image`, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': API_KEY
  },
  body: JSON.stringify({
    asset_id: 'imc_657766047105290240_15',
    model: 'multimodalembedding@001'
  })
});

const data = await response.json();
console.log(data);

import axios from 'axios';

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";

const formData = new FormData();
formData.append('file', imageFile);
formData.append('model', 'multimodalembedding@001');

const response = await axios.post(`${BASE_URL}/embeddings/image`, formData, {
  headers: {
    'Authorization': API_KEY
  }
});

console.log(response.data);

import axios from 'axios';

const BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2";
const API_KEY = "sk-mavi-...";

const response = await axios.post(`${BASE_URL}/embeddings/image`, {
  asset_id: 'imc_657766047105290240_15',
  model: 'multimodalembedding@001'
}, {
  headers: {
    'Authorization': API_KEY
  }
});

console.log(response.data);

import requests

BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2"
API_KEY = "sk-mavi-..."
HEADERS = {
    "Authorization": f"{API_KEY}"
}

def image_embedding_from_file(file_path, model="multimodalembedding@001"):
    url = f"{BASE_URL}/embeddings/image"
    data = {"model": model}
    files = {"file": open(file_path, "rb")}
    response = requests.post(url, headers=HEADERS, data=data, files=files)
    return response.json()

# Usage example
result = image_embedding_from_file("path/to/image.png", model="multimodalembedding@001")
print(result)

import requests

BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2"
API_KEY = "sk-mavi-..."
HEADERS = {
    "Authorization": f"{API_KEY}"
}

def image_embedding_from_asset(asset_id, model="multimodalembedding@001"):
    url = f"{BASE_URL}/embeddings/image"
    data = {"asset_id": asset_id, "model": model}
    response = requests.post(url, headers=HEADERS, json=data)
    return response.json()

# Usage example
result = image_embedding_from_asset("imc_657766047105290240_15", model="multimodalembedding@001")
print(result)

Request Parameters

This endpoint supports two methods of providing images: Method 1: File Upload (multipart/form-data)

Field	Type	Required	Description
file	file	Yes	Image file to upload (JPEG, PNG, GIF, WebP, etc.)
model	string	Yes	Embedding model name

Method 2: Asset ID (application/json)

Field	Type	Required	Description
asset_id	string	Yes	Existing image asset ID from a previous upload
model	string	Yes	Embedding model name

Supported Models:

multimodalembedding@001 - Google’s multimodal embedding model
mobileclip - Efficient mobile-optimized CLIP model

Response

Returns the embedding vector synchronously.

{
  "code": 200,
  "msg": "success",
  "data": {
    "embedding": [
      0.0234375,
      -0.015625,
      0.0078125,
      0.0390625,
      -0.0234375,
      "... (continues for vector length)"
    ]
  },
  "success": true,
  "failed": false
}

Response Parameters

Parameter	Type	Description
code	string	Response code indicating the result status (200 indicates success)
msg	string	Response message describing the operation result
data	object	Response data object containing the embedding
data.embedding	array[number]	Vector embedding array (dimensionality depends on the model)
success	boolean	Indicates whether the operation was successful
failed	boolean	Indicates whether the operation failed

Notes

Image embeddings are returned synchronously in the response
Embedding dimensions vary by model (typically 512-1024 dimensions)
Supported image formats: JPEG, PNG, GIF, WebP, BMP, TIFF
Maximum file size may vary by deployment
Use the file upload method for one-time embedding generation
Use the asset ID method when you’ve already uploaded the image via the /upload endpoint
Embeddings can be used for image similarity search, classification, and clustering

Authorizations

Authorization

string

header

required

Body

model

enum<string>

required

Embedding model name

Available options:

multimodalembedding@001,

mobileclip

Example:

"multimodalembedding@001"

file

Image file to upload

Response

200 - application/json

Embedding generated successfully

code

string

Response code indicating the result status

Example:

200

msg

string

Response message describing the operation result

Example:

"success"

data

object

Response data object containing the embedding

Show child attributes

success

boolean

Indicates whether the operation was successful

Example:

true

failed

boolean

Indicates whether the operation failed

Example:

false

Get Started

Asset Management

Social Media Scraping

Audio File Transcription

Live Audio Transcription

Video Model APIs

Video Task APIs

Live Video Content Moderation

Live Video Understanding

Image Model APIs

Embeddings

Human ReID & Caption

Reference

Generate Image Embedding

Code Examples

Request Parameters

Response

Response Parameters

Notes

Authorizations

Body

Response

​Code Examples

​Request Parameters

​Response

​Response Parameters

​Notes

Authorizations

Body

Response

Code Examples

Request Parameters

Response

Response Parameters

Notes