Query model Embedding

v1
post
/1/ai/{product_id}/openai/v1/embeddings

Path parameters

product_id
requiredinteger

AI TOOLS API product identifier - Use the following endpoint to retrieve your product identifier.

Examples:78849

Body Parameters

application/json
encoding_formatstring
Possible values:float

The encoding format of the returned embeddings. Defaults to float.

Examples:float
inputrequiredarray

Input text to embed, encoded as a string or array of tokens.

modestring
Possible values:indexquery

Specify the mode of the embedding request.

Examples:query
modelrequiredstring
Possible values:bge_multilingual_gemma2mini_lm_l12_v2

Model name to use

Examples:bge_multilingual_gemma2
task_descriptionstring

Optional set your custom task information in query mode

Examples:example

Response Body

application/json
objectstring

The object type, which is always "list".

Examples:list
dataarrayofEmbedding object

An embedding object

modelstring

ID of the model used for the request

Examples:bge_multilingual_gemma2
usagerequiredEmbedding Response

Usage statistics for embedding request

Example request

                <?php
use GuzzleHttp\Client;

$client = new Client();
$headers = [
	'Authorization' => 'Bearer YOUR-TOKEN-HERE',
	'Content-Type' => 'application/json'
];

$body = '{
    "input": [],
    "model": "bge_multilingual_gemma2"
}';

$request = new Request('POST', 'https://api.infomaniak.com/1/ai/{product_id}/openai/v1/embeddings', $headers, $body);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();

Example response

application/json
                
                    
{
"object":"list",
"data":[
{
"index":0,
"object":"embedding",
"embedding":[
3.71
]
}
],
"model":"bge_multilingual_gemma2",
"usage":{
"prompt_tokens":60883,
"total_tokens":21912
}
}