rag_search
RAG Search introduces advanced Retrieval-Augmented Generation (RAG) capabilities to your Drupal site, bridging the gap between your content architecture and Large Language Models (LLMs).
By leveraging vector embeddings and semantic search, this module allows developers and site builders to create highly contextual, conversational search experiences that go beyond traditional keyword matching.
Features
Context-Aware Responses: Feeds retrieved Drupal indexed content as context to an LLM, generating accurate, natural-language answers grounded strictly in your site's proprietary data.
This can be done by one of two ways:
- A dynamic route that can be configured in: /admin/config/rag_search/settings
- Adding a RAG Search block in the desired page
Post-Installation
Configure at : /admin/config/rag_search/settings
The fields can be overridden in each block too.
Additional Requirements
The module code is dependent on the following modules:
In addition you will need to have other modules enabled and pre-configured:
- Key
- AI Search
- An AI provider: I personally used: Gemini Provider
- A VDB Provider: I personally used Milvus VDB Provider which has a ddev integration too
.
- Setup AI provider: /admin/config/ai/providers
- Setup AI Settings: /admin/config/ai/settings
- Setup Search API: /admin/config/search/search-api
- Add Server
- Add Index
- Add Fields
- Add Processor