sagarsdeshmukh/swayam-ai-chatbot

WordPress Swayam AI Chatbot plugin using LLPhant, Llama 3.2, and Elasticsearch

1.0.0 2026-02-25 06:10 UTC

Requires

• php: ^8.2
• elasticsearch/elasticsearch: ^8.19
• theodo-group/llphant: ^0.11.12

GPL-2.0-or-later

README

A WordPress plugin that provides an AI-powered chatbot using RAG (Retrieval-Augmented Generation) architecture with LLPhant, Llama 3.2 (via Ollama), and Elasticsearch.

Why "Swayam"?

Swayam (स्वयं)—an ancient Sanskrit word meaning "self." Your content. Your knowledge. Autonomously intelligent.

Features

• RAG-Powered Q&A: Answers questions based on your WordPress content
• Automatic Content Indexing: Syncs posts, pages, and custom post types to Elasticsearch
• Auto-Sync on Publish: Automatically updates the index when content is published/updated/deleted
• Customizable Chat Interface: Shortcode and floating widget options
• Admin Dashboard: Easy configuration with connection testing
• REST API: Programmatic access to the chatbot
• Rate Limiting: Built-in protection against spam
• PHP 8.2+ Compatible: Works with PHP 8.2, 8.3, and later versions

Download plugin on wordpress.org

Requirements

• PHP: 8.2 or higher
• WordPress: 6.0 or higher
• Ollama: Running locally with Llama 3.2 model
• Elasticsearch: 9.x with vector search support
• Composer: For dependency management

Installation

1. Install the Plugin

# Navigate to your WordPress plugins directory
cd /path/to/wordpress/wp-content/plugins/

# Clone or copy the plugin
cp -r /path/to/swayam-ai-chatbot ./

# Install dependencies
cd swayam-ai-chatbot
composer install

2. Install and Start Ollama

You can install Llama 3.2 using ollama.

For installing ollama on Linux, run the following command:

curl -fsSL https://ollama.com/install.sh | sh

For macOS or Windows use the download page.

It is recommended to install Llama 3.2-1B or 3B for optimized CPU/GPU, and RAM usage.

For installing Llama3.2-3B use the following command:

ollama run llama3.2:3b

You can start interacting to the LLama3.2 model using a chat. To exit, write /bye in the chat.

3. Install and Start Elasticsearch

curl -fsSL https://elastic.co/start-local | sh

This script will install Elasticsearch and Kibana using a docker-compose.yml file stored in elastic-start-local folder.

Elasticsearch and Kibana will run locally at http://localhost:9200 and http://localhost:5601.

All the settings of Elasticsearch and Kibana are stored in the elastic-start-local/.env file.

You can use the start and stop commands available in the elastic-start-local folder.

To stop the Elasticsearch and Kibana Docker services, use the stop command:

cd elastic-start-local
./stop.sh

To start the Elasticsearch and Kibana Docker services, use the start command:

cd elastic-start-local
./start.sh

License

GPL v3

Credits

• LLPhant - PHP LLM framework
• Ollama - Local LLM runtime
• Elasticsearch - Vector database