This project is not covered by Drupal’s security advisory policy.
RRF Search
Reciprocal Rank Fusion (RRF) module for combining vector and traditional search results in Drupal Search API.
Features
- Implements Reciprocal Rank Fusion algorithm for search result merging
- Seamlessly integrates with Search API
- Combines vector-based and keyword-based search results
- Improves search relevance through result fusion
Requirements
- Drupal 10 or Drupal 11
- Search API module
- AI module (2.0+) with AI Search submodule
Installation
Using Composer (recommended)
composer require drupal/rrf
Then enable the module:
drush en rrf
Manual Installation
- Download the module from Drupal.org
- Extract to
web/modules/contrib/rrf - Enable via the admin interface or with Drush
Usage
Once enabled, the RRF Search module provides a Search API processor that combines results from multiple search backends using the Reciprocal Rank Fusion algorithm.
How RRF Works
Reciprocal Rank Fusion combines rankings from multiple search systems by:
- Taking results from different search methods (e.g., vector search and keyword search)
- Assigning scores based on result positions
- Merging and re-ranking results for optimal relevance
Contributing
Contributions are welcome! Please:
- Check the issue queue for existing issues
- Follow Drupal coding standards
- Submit patches or merge requests via Drupal.org
Support
- Issue tracking: Drupal.org issue queue
- Source code: DrupalCode Git repository
License
This project is licensed under the GPL-2.0-or-later license.
Project information
- Project categories: Artificial Intelligence (AI)
- Ecosystem: AI Search
1 site reports using this module- Created by harivansh on , updated
This project is not covered by the security advisory policy.
Use at your own risk! It may have publicly disclosed vulnerabilities.
