FAIR

Federated and Independent Repositories

Sentient AI

Plugin Banner

Sentient AI

by Maidul

Download
Description

Sentient AI adds an intelligent, customizable chatbot to your WordPress website. Powered by leading AI models, it engages users, answers questions, and provides dynamic responses using your own FAQ database or fallback AI responses.

✨ Features

  • FAQ-based response system with keyword matching.
  • AI fallback support with OpenAI, Claude, Gemini, OpenRouter, or Hugging Face.
  • Easy integration using shortcode [sentient_ai_chat] or floating chat widget.
  • Admin interface for managing FAQs and viewing query logs.
  • Automatically create FAQs from user questions and AI responses.
  • Training assistant with WordPress page import support.
  • Supports multilingual and RTL content.
  • Developer-friendly architecture (OOP, hooks, filters).
  • Optional logging with a secure file-based log viewer.
  • Translation-ready strings and text domain loading out of the box.
  • Session-based chat history persistence with one-click clear.
  • Export chat conversation as TXT from the chat header.
  • Configurable floating bubble position (bottom-right or bottom-left).

Usage

  • Use [sentient_ai_chat] shortcode in posts or pages to embed the chatbot inline.
  • Manage and add FAQs from the Sentient AI FAQs menu in the WordPress admin.
  • View logged user queries and AI responses under Sentient AI Query Logs.
  • Train your AI assistant by importing content from existing WordPress pages via the Training tab.
  • Toggle the floating widget, update the welcome greeting, and enable file logging from Sentient AI Settings.

External Services

This plugin connects to external AI service providers to generate intelligent chatbot responses when an FAQ match is not found. The plugin requires you to configure API credentials for your selected provider.

OpenAI

  • Service Purpose: Provides AI-powered responses through OpenAI’s GPT models and Assistants API
  • Data Sent: User queries/questions submitted through the chatbot, along with your configured assistant context
  • When Data is Sent: Every time a user submits a question that doesn’t match an existing FAQ entry
  • API Endpoints Used:
    • https://api.openai.com/v1/threads (Create conversation threads)
    • https://api.openai.com/v1/threads/{thread_id}/messages (Send user messages)
    • https://api.openai.com/v1/threads/{thread_id}/runs (Execute AI assistant)
    • https://api.openai.com/v1/files (Upload training files)
    • https://api.openai.com/v1/assistants/{assistant_id} (Update assistant configuration)
  • Terms of Service: https://openai.com/terms
  • Privacy Policy: https://openai.com/privacy

OpenRouter

  • Service Purpose: Provides access to multiple AI models through a unified API interface
  • Data Sent: User queries/questions submitted through the chatbot, along with your configured assistant context
  • When Data is Sent: Every time a user submits a question that doesn’t match an existing FAQ entry (when OpenRouter is selected as provider)
  • API Endpoints Used:
    • https://openrouter.ai/api/v1/files (Upload training files)
    • https://openrouter.ai/api/v1/assistants/{assistant_id} (Update assistant configuration)
  • Terms of Service: https://openrouter.ai/terms
  • Privacy Policy: https://openrouter.ai/privacy

Claude (Anthropic)

  • Service Purpose: Provides AI-powered responses using Anthropic’s Claude models
  • Data Sent: User queries/questions submitted through the chatbot
  • When Data is Sent: Every time a user submits a question that doesn’t match an existing FAQ entry (when Claude is selected as provider)
  • API Endpoints Used:
    • https://api.anthropic.com/v1/messages (Generate AI responses)
  • Terms of Service: https://www.anthropic.com/legal/consumer-terms
  • Privacy Policy: https://www.anthropic.com/legal/privacy

Google Gemini

  • Service Purpose: Provides AI-powered responses using Google’s Gemini models
  • Data Sent: User queries/questions submitted through the chatbot
  • When Data is Sent: Every time a user submits a question that doesn’t match an existing FAQ entry (when Gemini is selected as provider)
  • API Endpoints Used:
    • https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent (Generate AI responses)
  • Terms of Service: https://policies.google.com/terms
  • Privacy Policy: https://policies.google.com/privacy

Hugging Face

  • Service Purpose: Provides access to open-source AI models hosted on Hugging Face
  • Data Sent: User queries/questions submitted through the chatbot
  • When Data is Sent: Every time a user submits a question that doesn’t match an existing FAQ entry (when Hugging Face is selected as provider)
  • API Endpoints Used:
    • https://api-inference.huggingface.co/models/{model} (Generate AI responses)
  • Terms of Service: https://huggingface.co/terms-of-service
  • Privacy Policy: https://huggingface.co/privacy

Important Notes:
– You must provide your own API credentials for the service provider you choose
– Only one provider is active at a time based on your plugin settings
– No data is sent to external services if the user’s question matches an existing FAQ in your database
– The plugin does not collect, store, or transmit any personally identifiable information beyond the question text submitted by the user
– You are responsible for complying with the terms of service and privacy policies of your selected AI provider

  1. Upload the plugin folder to /wp-content/plugins/sentient-ai.
  2. Activate the plugin from the Plugins menu.
  3. Go to Sentient AI Settings to configure your preferred AI provider and API key.
  4. Place the [sentient_ai_chat] shortcode on any page, or use the floating chatbot by enabling it in settings.
Is Sentient AI free?

Yes, the core plugin is free and allows you to use your own API keys with any supported AI provider.

Do I need accounts with external AI services?

Yes. To generate AI responses you must supply API credentials for your selected provider (OpenAI, Claude, Gemini, Hugging Face, or OpenRouter). The plugin does not bundle any third-party access.

Does the plugin send data to external services?

Only when an FAQ match is not found. In that case the visitor’s question is sent to your configured AI provider to generate a reply. All requests originate from your site, and no personally identifiable information beyond the submitted prompt is transmitted by the plugin.

Does the plugin store chat logs?

You can enable database logging for troubleshooting inside Sentient AI Settings. Logs only include the question, the detected source (FAQ or AI), and the returned answer. Administrators can clear the table at any time, and uninstalling the plugin removes the log table completely.

Which AI providers and models are supported?

  • Multiple AI providers are supported including popular models and APIs
  • Configuration is done through your own API credentials

Can I customize the chatbot’s welcome message and style?

Yes. You can change the greeting message and customize the chatbot appearance using custom CSS or WordPress hooks.

Is logging optional?

Yes. Detailed logging can be enabled or disabled from the plugin settings page for privacy and performance control.

1.1.0

  • Added session-based conversation history persistence in the browser tab.
  • Added TXT export and clear history controls in chatbot header.
  • Added configurable chat bubble position (bottom-right or bottom-left).
  • Improved chat accessibility with ARIA live region and log semantics.

1.0.0

  • Initial public release
  • Support for OpenAI, Claude, Gemini, Hugging Face, and OpenRouter
  • FAQ response system with fallback AI logic
  • Shortcode and floating widget
  • Logs, auto-FAQ generation, and training assistant
Back to top