Performing hybrid search

After deploying your index, Orama will distribute it to over 300 global points of presence across more than 100 countries worldwide. This will guarantee the lowest possible latency for any search query, at any scale.

At the time of this writing, you can execute search queries using our official JavaScript SDK.

This SDK manages connection, cache, telemetry, and type-safety for all your search operations. It is the official method for communicating with Orama Cloud.

Installing the Orama SDK

You can find the guide on installing the SDK here.

Make sure you have the Orama SDK installed to start performing vector search at the edge!

What is hybrid search?

Hybrid search is a technique that merges full-text and vector search results into a unified list. It capitalizes on the strengths of both methods by balancing keyword-specific searches with the broader context of the overall query.

Performing hybrid search

Orama Cloud enables vector search by default. This means that you can search through your indexes using vectors generated by Orama’s embedding models.

As an alternative, you can provide your own vectors while inserting new documents into an Orama index, or use OpenAI’s embedding models to generate vectors for your documents.

Once you have at least one index containing vectors, you can perform hybrid search by using the search function:

JavaScript

import { OramaClient } from "@oramacloud/client";

const client = new OramaClient({
  endpoint: "",
  api_key: "",
});

const results = await client.search({
  term: "Super Mario videogame",
  mode: "hybrid",
  where: {
    price: {
      lt: 19.99,
    },
  },
});

Swift

import OramaCloudClient

struct MyDoc: Encodable & Decodable {
  let title: String
  let description: String
}

let clientParams = OramaClientParams(endpoint: "", apiKey: "")
let orama = OramaClient(params: clientParams)

let searchParams = ClientSearchParams.builder(
    term: "Super Mario videogame",
    mode: .hybrid
  )
  .limit(10) // optional
  .offset(0) // optional
  .returning(["title", "description"]) // optional
  .build()

let searchResults: SearchResults<MyDoc> = try await orama.search(query: searchParams)

Kotlin

import com.orama.client.OramaClient
import com.orama.model.search.*
import kotlinx.serialization.Serializable

@Serializable
data class MyDoc (
    val title: String,
    val category: String,
    val path: String,
    val content: String,
    val section: String
)

val client = OramaClient(
    endpoint = "",
    apiKey = ""
)

val searchParams = SearchParams.builder(
      term = "Super Mario videogame",
      mode = Mode.HYBRID
  )
  .where(listOf(
      Condition("price", ConditionType.LessThan(19.99))
  ))
  .build()

val results = client.search(searchParams, MyDoc.serializer())

Python

print("coming soon")

PHP

use OramaCloud\Client;
use OramaCloud\Client\Query;
use OramaCloud\Client\QueryParams\WhereOperator;
use OramaCloud\Client\QueryParams\SortByOrder;

$client = new Client([
  'api_key' => '<Your Orama Cloud API Key>',
  'endpoint' => '<Your Orama Cloud Endpoint>'
]);

$query = (new Query())
  ->term('Super Mario videogame')
  ->mode('hybrid')
  ->where('price', WhereOperator::LT, 19.99);

$results = $client->search($query);

Orama will automatically convert your search term, for instance, "Super Mario videogame", into an embedding using your OpenAI API Key. It will then search through your vectors and ultimately return the full documents in their original format.