Meilisearch | Meilisearch Cloud | Documentation | Discord | Roadmap | Website | FAQ
⚡ The Meilisearch integration for Ruby on Rails 💎
Meilisearch Rails is the Meilisearch integration for Ruby on Rails developers.
Meilisearch is an open-source search engine. Learn more about Meilisearch.
- 📖 Documentation
- 🤖 Compatibility with Meilisearch
- 🚀 Getting started
- Compatibility
- ⚙️ Settings
- 🔍 Custom search
- 🔍🔍 Multi search
- 🔍🔍 Federated search
- 🪛 Options
- ⚙️ Development workflow & contributing
- 👏 Credits
The whole usage of this gem is detailed in this README.
To learn more about Meilisearch, check out our Documentation or our API References.
This package guarantees compatibility with version v1.x of Meilisearch, but some features may not be present. Please check the issues for more info.
This package requires Ruby version 3.0 or later and Rails 6.1 or later. It may work in older versions but it is not officially supported.
With gem in command line:
gem install meilisearch-rails
In your Gemfile with bundler:
source 'https://rubygems.org' gem 'meilisearch-rails'
⚡️ Launch, scale, and streamline in minutes with Meilisearch Cloud—no maintenance, no commitment, cancel anytime. Try it free now.
🪨 Prefer to self-host? Download and deploy our fast, open-source search engine on your own infrastructure.
Create a new file config/initializers/meilisearch.rb to setup your MEILISEARCH_HOST and MEILISEARCH_API_KEY
Meilisearch::Rails.configuration = { meilisearch_url: ENV.fetch('MEILISEARCH_HOST', 'http://localhost:7700'), meilisearch_api_key: ENV.fetch('MEILISEARCH_API_KEY', 'YourMeilisearchAPIKey') }
Or you can run a rake task to create the initializer file for you:
bin/rails meilisearch:install
The gem is compatible with ActiveRecord, Mongoid and Sequel.
meilisearch block in your model.
The following code will create a Book index and add search capabilities to your Book model.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch do attribute :title, :author # only the attributes 'title', and 'author' will be sent to Meilisearch # all attributes will be sent to Meilisearch if block is left empty end end
As soon as you configure your model as mentioned above, meilisearch-rails will keep your database table data in sync with your Meilisearch instance using the ActiveRecord callbacks automatically.
We strongly recommend the use of front-end search through our JavaScript API Client or Instant Meilisearch plugin
Search returns ORM-compliant objects reloaded from your database.
# Meilisearch is typo-tolerant: hits = Book.search('harry pottre') hits.each do |hit| puts hit.title puts hit.author end
Requests made to Meilisearch may timeout and retry. To adapt the behavior to your needs, you can change the parameters during configuration:
Meilisearch::Rails.configuration = { meilisearch_url: 'YourMeilisearchUrl', meilisearch_api_key: 'YourMeilisearchAPIKey', timeout: 2, max_retries: 1, }
If your model already has methods that meilisearch-rails defines such as search and index, they will not be redefined. You can target the meilisearch-rails-defined methods by prefixing with ms_, e.g. Book.ms_search('harry potter').
You can configure the index settings by adding them inside the meilisearch block as shown below:
class Book < ApplicationRecord include Meilisearch::Rails meilisearch do searchable_attributes [:title, :author, :publisher, :description] filterable_attributes [:genre] sortable_attributes [:title] ranking_rules [ 'proximity', 'typo', 'words', 'attribute', 'sort', 'exactness', 'publication_year:desc' ] synonyms nyc: ['new york'] # The following parameters are applied when calling the search() method: attributes_to_highlight ['*'] attributes_to_crop [:description] crop_length 10 faceting max_values_per_facet: 2000 pagination max_total_hits: 1000 proximity_precision 'byWord' end end
Check the dedicated section of the documentation, for more information on the settings.
All the supported options are described in the search parameters section of the documentation.
Book.search('Harry', attributes_to_highlight: ['*'])
Then it's possible to retrieve the highlighted or cropped value by using the formatted method available in the object.
harry_book.formatted # => {"id"=>"1", "name"=>"<em>Harry</em> Potter", "description"=>...
👉 Don't forget that attributes_to_highlight, attributes_to_crop, and
crop_length can be set up in the meilisearch block of your model.
As an example of how to use the sort option, here is how you could achieve returning all books sorted by title in ascending order:
Book.search('*', sort: ['title:asc'])
👉 Don't forget to set up the sortable_attributes option in the meilisearch block of your model.
Meilisearch supports searching multiple models at the same time (see 🔍 Custom search for search options):
multi_search_results = Meilisearch::Rails.multi_search( Book => { q: 'Harry' }, Manga => { q: 'Attack' } )
Use #each_result to loop through pairs of your provided keys and the results:
<% multi_search_results.each_result do |klass, results| %> <p><%= klass.name.pluralize %></p> <ul> <% results.each do |record| %> <li><%= record.title %></li> <% end %> </ul> <% end %> <p>Books</p> <ul> <li>Harry Potter and the Philosopher's Stone</li> <li>Harry Potter and the Chamber of Secrets</li> </ul> <p>Mangas</p> <ul> <li>Attack on Titan</li> </ul>
Records are loaded when the keys are models, or when :scope option is passed:
multi_search_results = Meilisearch::Rails.multi_search( # scope may be a relation 'books' => { q: 'Harry', scope: Book.all }, # or a model 'mangas' => { q: 'Attack', scope: Manga } )
Otherwise, hashes are returned.
The index to search is inferred from the model if the key is a model, if the key is a string the key is assumed to be the index unless the :index_uid option is passed:
multi_search_results = Meilisearch::Rails.multi_search( 'western' => { q: 'Harry', scope: Book, index_uid: 'books_production' }, 'japanese' => { q: 'Attack', scope: Manga, index_uid: 'mangas_production' } )
You can search the same index multiple times by specifying :index_uid:
query = 'hero' multi_search_results = Meilisearch::Rails.multi_search( 'Isekai Manga' => { q: query, scope: Manga, filters: 'genre:isekai', index_uid: 'mangas_production' } 'Shounen Manga' => { q: query, scope: Manga, filters: 'genre:shounen', index_uid: 'mangas_production' } 'Steampunk Manga' => { q: query, scope: Manga, filters: 'genre:steampunk', index_uid: 'mangas_production' } )
DEPRECATED: You used to be able to iterate through a flattened collection with .each:
<% multi_search_results.each do |record| %> <p><%= record.title %></p> <p><%= record.author %></p> <% end %> <p>Harry Potter and the Philosopher's Stone</p> <p>J. K. Rowling</p> <p>Harry Potter and the Chamber of Secrets</p> <p>J. K. Rowling</p> <p>Attack on Titan</p> <p>Iseyama</p>
But this has been deprecated in favor of federated search.
See the official multi search documentation.
Federated search is similar to multi search, except that results are not grouped but sorted by ranking rules.
results = Meilisearch::Rails.federated_search( queries: [ { q: 'Harry', scope: Book.all }, { q: 'Attack on Titan', scope: Manga.all } ] )
An enumerable FederatedSearchResult is returned, which can be iterated through with #each:
<ul> <% results.each do |record| %> <li><%= record.title %></li> <% end %> </ul> <ul> <!-- Attack on Titan appears first even though it was specified second, it's ranked higher because it's a closer match --> <li>Attack on Titan</li> <li>Harry Potter and the Philosopher's Stone</li> <li>Harry Potter and the Chamber of Secrets</li> </ul>
The queries parameter may be a multi-search style hash with keys that are either classes, index names, or neither:
results = Meilisearch::Rails.federated_search( queries: { Book => { q: 'Harry' }, Manga => { q: 'Attack on Titan' } } )
results = Meilisearch::Rails.federated_search( queries: { 'books_production' => { q: 'Harry', scope: Book.all }, 'mangas_production' => { q: 'Attack on Titan', scope: Manga.all } } )
results = Meilisearch::Rails.federated_search( queries: { 'potter' => { q: 'Harry', scope: Book.all, index_uid: 'books_production' }, 'titan' => { q: 'Attack on Titan', scope: Manga.all, index_uid: 'mangas_production' } } )
Records are loaded when the :scope option is passed (may be a model or a relation),
or when a hash query is used with models as keys:
results = Meilisearch::Rails.federated_search( queries: [ { q: 'Harry', scope: Book }, { q: 'Attack on Titan', scope: Manga }, ] )
results = Meilisearch::Rails.federated_search( queries: { Book => { q: 'Harry' }, Manga => { q: 'Attack on Titan' } } )
If the model is not provided, hashes are returned!
Any relation passed as :scope is used as the starting point when loading records:
results = Meilisearch::Rails.federated_search( queries: [ { q: 'Harry', scope: Book.where('year <= 2006') }, { q: 'Attack on Titan', scope: Manga.where(author: Author.find_by(name: 'Iseyama')) }, ] )
In order of precedence, to figure out which index to search, Meilisearch Rails will check:
index_uidoptionsresults = Meilisearch::Rails.federated_search( queries: [ # Searching the 'fantasy_books' index { q: 'Harry', scope: Book, index_uid: 'fantasy_books' }, ] )
- The index associated with the model
results = Meilisearch::Rails.federated_search( queries: [ # Searching the index associated with the Book model # i. e. Book.index.uid { q: 'Harry', scope: Book }, ] )
- The key when using hash queries
results = Meilisearch::Rails.federated_search( queries: { # Searching index 'books_production' books_production: { q: 'Harry', scope: Book }, } )
In addition to queries, federated search also accepts :federation parameters which allow for finer control of the search:
results = Meilisearch::Rails.federated_search( queries: [ { q: 'Harry', scope: Book }, { q: 'Attack on Titan', scope: Manga }, ], federation: { offset: 10, limit: 5 } )
See a full list of accepted options in the meilisearch documentation.
The returned result from a federated search includes a .metadata attribute you can use to access everything other than the search hits:
result.metadata # { # "processingTimeMs" => 0, # "limit" => 20, # "offset" => 0, # "estimatedTotalHits" => 2, # "semanticHitCount": 0 # }
The metadata contains facet stats and pagination stats, among others. See the full response in the documentation.
More details on federated search (such as available federation: options) can be found on the official multi search documentation.
This gem supports:
Specify the :pagination_backend in the configuration file:
Meilisearch::Rails.configuration = { meilisearch_url: 'YourMeilisearchUrl', meilisearch_api_key: 'YourMeilisearchAPIKey', pagination_backend: :kaminari # :will_paginate }
Then, as soon as you use the search method, the returning results will be paginated:
# controller @hits = Book.search('harry potter') # views <% @hits.each do |hit| %> <%= hit.title %> <%= hit.author %> <% end %> <%= paginate @hits %> # if using kaminari <%= will_paginate @hits %> # if using will_paginate
The number of hits per page defaults to 20, you can customize it by adding the hits_per_page parameter to your search:
Book.search('harry potter', hits_per_page: 10)
This gem supports pagy to paginate your search results.
To use pagy with your meilisearch-rails you need to:
Add the pagy gem to your Gemfile.
Create a new initializer pagy.rb with this:
# config/initializers/pagy.rb require 'pagy/extras/meilisearch'
Then in your model you must extend Pagy::Meilisearch:
class Book < ApplicationRecord include Meilisearch::Rails extend Pagy::Meilisearch meilisearch # ... end
And in your controller and view:
# controllers/books_controller.rb def search hits = Book.pagy_search(params[:query]) @pagy, @hits = pagy_meilisearch(hits, items: 25) end # views/books/search.html.rb <%== pagy_nav(@pagy) %>
pagination_backend in the configuration block Meilisearch::Rails.configuration for pagy.
Check ddnexus/pagy for more information.
By default, HTTP connections to the Meilisearch URL are always active, but sometimes you want to disable the HTTP requests in a particular moment or environment.
you have multiple ways to achieve this.
By adding active: false in the configuration initializer:
Meilisearch::Rails.configuration = { meilisearch_url: 'YourMeilisearchUrl', meilisearch_api_key: 'YourMeilisearchAPIKey', active: false }
Or you can disable programmatically:
Meilisearch::Rails.deactivate! # all the following HTTP calls will be dismissed. # or you can pass a block to it: Meilisearch::Rails.deactivate! do # every Meilisearch call here will be dismissed, no error will be raised. # after the block, Meilisearch state will be active. end
You can also activate if you deactivated earlier:
Meilisearch::Rails.activate!
By default, the index_uid will be the class name, e.g. Book. You can customize the index_uid by using the index_uid: option.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch index_uid: 'MyCustomUID' end
You can suffix the index UID with the current Rails environment by setting it globally:
Meilisearch::Rails.configuration = { meilisearch_url: 'YourMeilisearchUrl', meilisearch_api_key: 'YourMeilisearchAPIKey', per_environment: true }
This way your index UID will look like this "Book_#{Rails.env}".
You can add a custom attribute by using the add_attribute option or by using a block.
will_save_change_to_#{attr_name}? method.
class Author < ApplicationRecord include Meilisearch::Rails meilisearch do attribute :first_name, :last_name attribute :full_name do "#{first_name} #{last_name}" end add_attribute :full_name_reversed end def full_name_reversed "#{last_name} #{first_name}" end def will_save_change_to_full_name? will_save_change_to_first_name? || will_save_change_to_last_name? end def will_save_change_to_full_name_reversed? will_save_change_to_first_name? || will_save_change_to_last_name? end end
By default, the primary key is based on your record's id. You can change this behavior by specifying the primary_key: option.
Note that the primary key must return a unique value otherwise your data could be overwritten.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch primary_key: :isbn # isbn is a column in your table definition. end
You can also set the primary_key as a method, this method will be evaluated in runtime, and its return
will be used as the reference to the document when Meilisearch needs it.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch primary_key: :my_custom_ms_id private def my_custom_ms_id "isbn_#{primary_key}" # ensure this return is unique, otherwise you'll lose data. end end
You can control if a record must be indexed by using the if: or unless: options.
As soon as you use those constraints, add_documents and delete_documents calls will be performed in order to keep the index synced with the DB. To prevent this behavior, you can create a will_save_change_to_#{attr_name}? method.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch if: :published?, unless: :premium? def published? # [...] end def premium? # [...] end def will_save_change_to_published? # return true only if you know that the 'published' state changed end end
You can index a record in several indexes using the add_index option:
class Book < ActiveRecord::Base include Meilisearch::Rails PUBLIC_INDEX_UID = 'Books' SECURED_INDEX_UID = 'PrivateBooks' # store all books in index 'SECURED_INDEX_UID' meilisearch index_uid: SECURED_INDEX_UID do searchable_attributes [:title, :author] # store all 'public' (released and not premium) books in index 'PUBLIC_INDEX_UID' add_index PUBLIC_INDEX_UID, if: :public? do searchable_attributes [:title, :author] end end private def public? released? && !premium? end end
You may want to share an index between several models. You'll need to ensure you don't have any conflict with the primary_key of the models involved.
class Cat < ActiveRecord::Base include Meilisearch::Rails meilisearch index_uid: 'Animals', primary_key: :ms_id private def ms_id "cat_#{primary_key}" # ensure the cats & dogs primary_keys are not conflicting end end class Dog < ActiveRecord::Base include Meilisearch::Rails meilisearch index_uid: 'Animals', primary_key: :ms_id private def ms_id "dog_#{primary_key}" # ensure the cats & dogs primary_keys are not conflicting end end
You can configure the auto-indexing & auto-removal process to use a queue to perform those operations in background. ActiveJob queues are used by default but you can define your own queuing mechanism:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch enqueue: true # ActiveJob will be triggered using a `meilisearch` queue end
🤔 If you are performing updates and deletions in the background, a record deletion can be committed to your database prior to the job actually executing. Thus if you were to load the record to remove it from the database then your ActiveRecord#find will fail with a RecordNotFound.
In this case you can bypass loading the record from ActiveRecord and just communicate with the index directly.
With ActiveJob:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch enqueue: :trigger_job do attribute :title, :author, :description end def self.trigger_job(record, remove) MyActiveJob.perform_later(record.id, remove) end end class MyActiveJob < ApplicationJob def perform(id, remove) if remove # The record has likely already been removed from your database so we cannot # use ActiveRecord#find to load it. # We access the underlying Meilisearch index object. Book.index.delete_document(id) else # The record should be present. Book.find(id).index! end end end
With Sidekiq:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch enqueue: :trigger_sidekiq_job do attribute :title, :author, :description end def self.trigger_sidekiq_job(record, remove) MySidekiqJob.perform_async(record.id, remove) end end class MySidekiqJob def perform(id, remove) if remove # The record has likely already been removed from your database so we cannot # use ActiveRecord#find to load it. # We access the underlying Meilisearch index object. Book.index.delete_document(id) else # The record should be present. Book.find(id).index! end end end
With DelayedJob:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch enqueue: :trigger_delayed_job do attribute :title, :author, :description end def self.trigger_delayed_job(record, remove) if remove record.delay.remove_from_index! else record.delay.index! end end end
Extend a change to a related record.
With ActiveRecord, you'll need to use touch and after_touch.
class Author < ActiveRecord::Base include Meilisearch::Rails has_many :books # If your association uses belongs_to # - use `touch: true` # - do not define an `after_save` hook after_save { books.each(&:touch) } end class Book < ActiveRecord::Base include Meilisearch::Rails belongs_to :author after_touch :index! meilisearch do attribute :title, :description, :publisher attribute :author do author.name end end end
With Sequel, you can use the touch plugin to propagate changes.
# app/models/author.rb class Author < Sequel::Model include Meilisearch::Rails one_to_many :books plugin :timestamps # Can't use the associations since it won't trigger the after_save plugin :touch # Define the associations that need to be touched here # Less performant, but allows for the after_save hook to be triggered def touch_associations apps.map(&:touch) end def touch super touch_associations end end # app/models/book.rb class Book < Sequel::Model include Meilisearch::Rails many_to_one :author after_touch :index! plugin :timestamps plugin :touch meilisearch do attribute :title, :description, :publisher attribute :author do author.name end end end
You can strip all HTML tags from your attributes with the sanitize option.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch sanitize: true end
You can force the UTF-8 encoding of all your attributes using the force_utf8_encoding option.
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch force_utf8_encoding: true end
You can eager load associations using meilisearch_import scope.
class Author < ActiveRecord::Base include Meilisearch::Rails has_many :books scope :meilisearch_import, -> { includes(:books) } end
You can manually index a record by using the index! instance method and remove it by using the remove_from_index! instance method.
book = Book.create!(title: 'The Little Prince', author: 'Antoine de Saint-Exupéry') book.index! book.remove_from_index! book.destroy!
To reindex all your records, use the reindex! class method:
Book.reindex! # You can also index a subset of your records Book.where('updated_at > ?', 10.minutes.ago).reindex!
To delete all your records, use the clear_index! class method:
Book.clear_index!
To access the index object and use the Ruby SDK methods for an index, call the index class method:
index = Book.index # index.get_settings, index.number_of_documents
You can disable exceptions that could be raised while trying to reach Meilisearch's API by using the raise_on_failure option:
class Book < ActiveRecord::Base include Meilisearch::Rails # Only raise exceptions in development environment. meilisearch raise_on_failure: Rails.env.development? end
You can force indexing and removing to be synchronous by setting the following option:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch synchronous: true end
🚨 This is only recommended for testing purposes, the gem will call the wait_for_task method that will stop your code execution until the asynchronous task has been processed by MeilSearch.
You can disable auto-indexing and auto-removing setting the following options:
class Book < ActiveRecord::Base include Meilisearch::Rails meilisearch auto_index: false, auto_remove: false end
You can temporarily disable auto-indexing using the without_auto_index scope:
Book.without_auto_index do # Inside this block, auto indexing task will not run. 1.upto(10000) { Book.create! attributes } end
Any new contribution is more than welcome in this project!
If you want to know more about the development workflow or want to contribute, please visit our contributing guidelines for detailed instructions!
The provided features and the code base is inspired by algoliasearch-rails.
Meilisearch provides and maintains many SDKs and Integration tools like this one. We want to provide everyone with an amazing search experience for any kind of project. If you want to contribute, make suggestions, or just know what's going on right now, visit us in the integration-guides repository.