Create vector embeddings

Opensolr API Endpoint: embed

Overview

The embed endpoint allows you to generate vector embeddings for any arbitrary text payload (up to 50,000 characters) and use them wherever you need — in KNN searches, your own storage, or any downstream pipeline. This is ideal for embedding dynamic or ad-hoc content, without having to pre-index data in Solr first.

Endpoint URL

https://api.opensolr.com/solr_manager/api/embed

Supports only POST requests.

Authentication & Core Parameters

Embedding Parameters

Query vs Document Embedding\n\nThe embedding model (intfloat/multilingual-e5-large-instruct) is instruction-tuned — it produces better vectors when it knows whether the input is a search query or a document.\n\n- is_query=1: Prepends an instruction prefix that tells the model "this is a search query — optimize for retrieval." Use this when embedding user search strings before sending them to Solr KNN.\n- is_query=0 (default): No prefix. Use this when embedding documents/passages at index time.\n\nThis asymmetry improves recall by 5–15% on queries where the wording differs significantly from the indexed documents. It also enables cross-language matching (e.g., a Romanian query matching English documents).\n\n---\n\n## Special Notes

• payload can be any UTF-8 text (e.g., a document, user input, generated content, etc).
• If payload is missing or less than 2 characters, the API returns a 404 error with a JSON error response.
• You must specify a valid index_name to indicate you are an Opensolr Member (only used for authentication purposes).
• The response is returned as JSON.

Example Solr Schema Requirement

To store embeddings, your Solr schema must define an appropriate vector field, for example:

<field name="embeddings" type="vector" indexed="true" stored="false" multiValued="false"/>
<fieldType name="vector" class="solr.DenseVectorField" vectorDimension="1024" required="false" similarityFunction="cosine"/>

Adjust the name, type, and vectorDimension as needed to fit your use-case and model. ⚠️ IMPORTANT: This API uses the embedding model: intfloat/multilingual-e5-large-instruct which produces a 1024D vector representation of your text.

Example Usage

cURL

curl -X POST https://api.opensolr.com/solr_manager/api/embed \
  -d "email=your@email.com" \
  -d "api_key=YOUR_API_KEY" \
  -d "index_name=your_index" \
  -d "payload=Your text to embed here. This can be any UTF-8 content up to 50000 characters." \\n  -d "is_query=0"

PHP

<?php
$url = 'https://api.opensolr.com/solr_manager/api/embed';

$params = [
    'email'      => 'your@email.com',
    'api_key'    => 'YOUR_API_KEY',
    'index_name' => 'your_index',
    'payload'    => 'Your text to embed here. This can be any UTF-8 content up to 50000 characters.',
    'is_query'   => '0',  // Set to '1' for search queries
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($params));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/x-www-form-urlencoded']);

$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
curl_close($ch);

$data = json_decode($response, true);

if ($http_code === 200 && isset($data['embedding'])) {
    echo "Embedding generated — " . count($data['embedding']) . " dimensions
";
    // $data['embedding'] is a 1024-element float array ready for KNN search
} else {
    echo "Error: " . ($data['ERROR'] ?? $response) . "
";
}

Python

import requests

url = "https://api.opensolr.com/solr_manager/api/embed"

params = {
    "email": "your@email.com",
    "api_key": "YOUR_API_KEY",
    "index_name": "your_index",
    "payload": "Your text to embed here. This can be any UTF-8 content up to 50000 characters.",\n    "is_query": "0",  # Set to "1" for search queries
}

resp = requests.post(url, data=params)
data = resp.json()

if resp.status_code == 200 and "embedding" in data:
    print(f"Embedding generated — {len(data['embedding'])} dimensions")
    # data["embedding"] is a 1024-element float list ready for KNN search
else:
    print(f"Error: {data.get('ERROR', resp.text)}")

Endpoint Behavior

1. Authenticates the user using email and api_key.
2. Checks for a valid payload parameter (must be 2-50,000 characters).
3. Generates vector embeddings for the provided payload.
4. Uses index_name for authentication only — the embedding is NOT stored anywhere.
5. Responds with a JSON object containing the result.

Example Response

{
  "status": "success",
  "embedding": [/* vector values */],
  "length": 4381
}

Or, for invalid input:

{
  "ERROR": "Invalid payload"
}

Use Cases

• Embed dynamic or user-generated text into your Solr index.
• Integrate with chatbots, summarization tools, or any app needing AI-powered semantic representations on the fly.
• Test or debug embedding functionality before bulk-embedding large datasets.

Support

For more information or help, visit Opensolr Support or use your Opensolr dashboard.