Text Embedding LLM API Endpoint Documentation

API Endpoint Access URL

https://llm.pixlab.io/embedding

Description

The TEXT-EMBED API endpoint transforms textual data into numerical vectors, effectively capturing the semantic meaning and context of a stream of words (tokens). It supports multiple major languages and provides efficient embedding services for text data. This is beneficial for natural language processing tasks such as RAG, text classification, sentiment analysis, and text indexing.

HTTP Methods

JSON POST

HTTP Parameters

Required

Fields	Type	Description
`input`	string	The input text to generate an embedding vector for. A maximum 8192 tokens is allowed for each input sentence.
`key`	String	Your PixLab API Key ↗. You can also embed your key in the `WWW-Authenticate:` HTTP header and omit this parameter if you want to.

Optional

Fields	Type	Description
`dimension`	integer	The output embedding vector dimension. The value must be either 512 or 1024. Defaults to `1024`.

POST Request Body

This section outlines the requirements for POST requests, which are used instead of GET requests in specific scenarios.

Allowed Content-Types:

application/json

JSON is the default format for POST requests. If you are uploading a file via a JSON POST request, please ensure the file is base64 encoded within the JSON payload.

HTTP Response

application/json

The default response format is the PixLab simple LLM response format which is unified across our vLM API endpoints, and is suitable for most applications that includes the bare minimum information including the embedding vector, tokens count, etc.

PixLab Simple vLM Response Format


{
  "status": 200,
  "embedding": [2.8765, 1.9870, 4.9076, 7.9177, ...],
  "total_tokens": 512
}

Fields	Type	Description
`status`	Integer	HTTP 200 indicates success. Any other code indicates failure.
`embedding`	List	An array (or list) of floating points stream containing the complete output text embedding vector.
`model`	String	Underlying LLM model ID/Name.
`total_tokens`	Integer	Total number of ingested/output tokens.
`error`	String	Error description when `status` != 200.

Code Samples


import requests
import json

# Generate text embedding vector for a given sentence or piece of text.
# Refer to: https://pixlab.io/endpoints/text-embed for the official documentation.

key = 'PIXLAB_API_KEY' # Get your API key from https://console.pixlab.io/

# Make the API call; Switch to POST if you want to upload your image directly.
req = requests.get('https://llm.pixlab.io/embedding',params={
  'input': "What is the meaning of life?",
  'key': key,
  'dimension': 1024, # Desired output vector dimension
})
reply = req.json()
if reply['status'] != 200:
	print (reply['error'])
else:
  embedding = reply['embedding']
  print(f"Text embedding vector: {embedding}")


// Generate text embedding vector for a given sentence or piece of text.
// Refer to: https://pixlab.io/endpoints/text-embed for the official documentation.

const key = 'PIXLAB_API_KEY'; // Get your API key from https://console.pixlab.io/

// Make the API call; Switch to POST if you want to upload your image directly.
fetch('https://llm.pixlab.io/embedding?input=What is the meaning of life?&key=' + key + '&dimension=1024')
  .then(response => response.json())
  .then(reply => {
    if (reply['status'] !== 200) {
      console.log(reply['error']);
    } else {
      const embedding = reply['embedding'];
      console.log(`Text embedding vector: ${embedding}`);
    }
  })
  .catch(error => {
    console.error('Error:', error);
  });

<?php
# Generate text embedding vector for a given sentence or piece of text.
# Refer to: https://pixlab.io/endpoints/text-embed for the official documentation.

$key = 'PIXLAB_API_KEY'; // Get your API key from https://console.pixlab.io/

# Make the API call; Switch to POST if you want to upload your image directly.
$ch = curl_init('https://llm.pixlab.io/embedding?input=What is the meaning of life?&key=' . $key . '&dimension=1024');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);

$reply = json_decode($response, true);

if ($reply['status'] != 200) {
    echo $reply['error'];
} else {
    $embedding = $reply['embedding'];
    echo "Text embedding vector: " . json_encode($embedding);
}

Similar API Endpoints

tagimg, nsfw, docscan, llm-parse, chat, llm-tools, answer, describe, image-embed, llm-tool-call, query, coder

Text Embedding API Endpoint