Pinecone vector database provider for the Backdrop CMS AI Search module. Stores and queries embeddings in Pinecone to power AI-driven semantic search experiences.
Requirements
- Backdrop CMS 1.x
- PHP 8.2 or later
ai_searchmodule- A Pinecone account with an existing index
- The Key module, with keys configured for your Pinecone API key and base URL
Installation
- Install this module using the official Backdrop CMS instructions.
Configuration
- Create Key entries (Admin -> Configuration -> System -> Keys) for:
- Your Pinecone API key
- Your Pinecone base URL (e.g.,
https://your-index-xxx.svc.pinecone.io)
- Enable this module.
- Go to Admin -> Configuration -> Search and Metadata -> Search API and create or edit a server.
- Select Pinecone as the service backend.
- Configure the server settings:
- Pinecone API Key — Select the Key that stores your Pinecone API key.
- Pinecone Hostname / Base URL — Select the Key that stores your Pinecone index base URL.
- Namespace — Optional namespace prefix. The Search API index machine name is always appended automatically.
- Default Top-K — Number of results to return per query. Defaults to
5. - Embeddings engine — Select the embedding model; its dimension must match your Pinecone index.
- Create a Search API index on that server.
- Index your content to populate the Pinecone index.
Issues
Bugs and feature requests should be reported in the Issue Queue.
Current Maintainer
Credits
- Created for Backdrop CMS by Justin Keiser.
- Developed with AI assistance.
License
This project is GPL v2 software. See the LICENSE.txt file in this directory for complete text.