Muhammad Adnan Hanif

<p>Fast RAGbot is an intelligent chatbot that uses Retrieval-Augmented Generation (RAG) with support for multiple AI providers to provide accurate answers based exclusively on your website content.</p>
<p><strong>Key Features:</strong></p>
<ul>
<li><strong>Multi-LLM Support</strong>: Choose between Gemini, OpenAI (ChatGPT), or Claude</li>
<li><strong>Multi-Domain Indexing</strong>: Index up to 3 different domains</li>
<li><strong>Document Upload</strong>: Bulk upload PDF, DOCX, PPTX, XLSX, TXT, XML, CSV</li>
<li><strong>Conversation Memory</strong>: Maintains last 5 Q&A turns per session</li>
<li><strong>Smart Follow-ups</strong>: Suggests questions when answer not found</li>
<li><strong>Widget Customization</strong>: Custom colors, logo, position, theme CSS</li>
<li><strong>Pre-chat Form</strong>: Optional name/email collection</li>
<li><strong>Chat Logs</strong>: Full conversation logging with CSV export</li>
<li><strong>Shortcode Support</strong>: Embed chat anywhere with <code>[ragbot_chat]</code></li>
<li><strong>Grounded Responses</strong>: Answers only from your content – no hallucinations</li>
<li><strong>Source Citations</strong>: Provides URLs of source pages for transparency</li>
<li><strong>Mobile Responsive</strong>: Works perfectly on all devices</li>
<li><strong>Security First</strong>: Rate limiting, nonces, and proper sanitization</li>
</ul>
<p><strong>How It Works:</strong></p>
<ol>
<li>Crawls and indexes your website content</li>
<li>Creates semantic embeddings using Google Gemini</li>
<li>Retrieves relevant content based on user questions</li>
<li>Generates contextual answers with source citations</li>
<li>Displays responses in a floating chat widget</li>
</ol>
<p><strong>Perfect For:</strong></p>
<ul>
<li>Customer support automation</li>
<li>FAQ assistance</li>
<li>Product information queries</li>
<li>Company information lookup</li>
<li>Documentation assistance</li>
</ul>
<h3>External Services & Data Usage</h3>
<p>This plugin connects to external AI services to provide chatbot functionality. Below is a detailed explanation of what data is transmitted and how it is used.</p>
<h4>External Services Used</h4>
<p><strong>Google Gemini API</strong> (https://ai.google.dev/)<br />
* Used for: Text embeddings and AI text generation<br />
* Data sent: User questions, website content chunks, conversation history<br />
* Privacy Policy: https://policies.google.com/privacy<br />
* Terms of Service: https://policies.google.com/terms</p>
<p><strong>OpenAI API</strong> (https://openai.com/) – Optional<br />
* Used for: Text embeddings and AI text generation (when selected as active model)<br />
* Data sent: User questions, website content chunks, conversation history<br />
* Privacy Policy: https://openai.com/privacy/<br />
* Terms of Service: https://openai.com/terms/</p>
<p><strong>Claude API by Anthropic</strong> (https://anthropic.com/) – Optional<br />
* Used for: Text embeddings and AI text generation (when selected as active model)<br />
* Data sent: User questions, website content chunks, conversation history<br />
* Privacy Policy: https://www.anthropic.com/privacy<br />
* Terms of Service: https://www.anthropic.com/legal/terms</p>
<h4>What Data Is Transmitted</h4>
<ol>
<li><strong>User’s Question</strong>: The text message submitted by the website visitor</li>
<li><strong>Retrieved Document Chunks</strong>: Relevant excerpts from your indexed website content (typically 5-8 chunks of ~1000 characters each)</li>
<li><strong>Conversation History</strong>: Last 5 question-answer pairs from the current session</li>
<li><strong>Model Parameters</strong>: Temperature (0.1), max tokens (1000), and other generation settings</li>
</ol>
<h4>Data Usage & Storage</h4>
<ul>
<li>Data is transmitted <strong>only</strong> for generating responses to user questions</li>
<li><strong>No data is stored or used for training</strong> by external AI providers (per their API terms)</li>
<li>Data transmission occurs in real-time and is not cached by the plugin on external servers</li>
<li>All API communications use HTTPS encryption</li>
</ul>
<h4>Local WordPress Storage</h4>
<p>The plugin stores the following data in your WordPress database:</p>
<p><strong>Options (wp_options table)</strong>:<br />
* <code>ragbot_settings</code> – Plugin configuration including API keys, widget settings, and preferences</p>
<p><strong>Custom Tables</strong>:<br />
* <code>wp_rag_docs</code> – Indexed website pages and uploaded documents<br />
* <code>wp_rag_chunks</code> – Text chunks created from indexed content<br />
* <code>wp_rag_embeddings</code> – Vector embeddings for semantic search<br />
* <code>wp_rag_sources</code> – Content source configurations (domains, settings)<br />
* <code>wp_rag_logs</code> – Chat conversation logs (optional, includes user name/email if pre-chat form enabled)<br />
* <code>wp_rag_url_queue</code> – Queue of URLs pending indexing</p>
<p><strong>Session Data</strong>:<br />
* PHP sessions store temporary conversation history (cleared when session ends)<br />
* Browser sessionStorage stores chat UI state (cleared when tab closes)</p>
<h4>Data Control & Privacy</h4>
<p><strong>User Control</strong>:<br />
* Delete API keys anytime from Settings > Fast RAGbot > Models tab<br />
* Clear all indexed content using “Clear Index” button<br />
* Reset plugin settings to defaults<br />
* Export or delete chat logs from Settings > Fast RAGbot > Chat Logs tab</p>
<p><strong>Data Deletion</strong>:<br />
* Deactivating the plugin preserves your data<br />
* Uninstalling the plugin removes all database tables and options<br />
* Use “Clear Index” to remove indexed content without uninstalling</p>
<p><strong>Privacy Compliance</strong>:<br />
* No data is shared with third parties except your chosen AI provider<br />
* Chat logs are optional and stored locally in your database<br />
* Pre-chat form (name/email collection) is optional and disabled by default<br />
* All user inputs are sanitized and validated<br />
* Rate limiting prevents abuse (10 requests per 60 seconds per IP)</p>
<h4>Developer Privacy Policy</h4>
<p>For questions about data handling, please review:<br />
* Your chosen AI provider’s privacy policy (links above)<br />
* Your own website’s privacy policy (you are the data controller)<br />
* WordPress.org privacy guidelines: https://wordpress.org/about/privacy/</p>
<h3>Privacy Policy</h3>
<p>This plugin acts as a data processor, sending user questions to your chosen AI provider. You (the site owner) are the data controller and responsible for:<br />
* Disclosing AI service usage in your privacy policy<br />
* Obtaining user consent where required by law (GDPR, CCPA, etc.)<br />
* Ensuring compliance with local privacy regulations</p>
<p>The plugin stores chat logs locally in your database. If you enable the pre-chat form, user names and emails are stored and should be disclosed in your privacy policy.</p>
<h3>Support</h3>
<p>For support, please visit the plugin’s support forum or contact the developer.</p>
<h3>Credits</h3>
<ul>
<li>Supports embeddings and text generation using Google Gemini, OpenAI, or Claude.</li>
<li>Built with WordPress coding standards</li>
<li>Follows accessibility best practices</li>
</ul>


Fast RAGbot

AI-powered chatbot with multi-LLM support (Gemini/OpenAI/Claude), multi-domain indexing, document upload, and conversation memory.

Shazahanul Islam Shohag

<p>Smart Sense adds an AI-generated summary to the top of your WordPress search results. It retrieves relevant passages from your posts, pages, and optional custom post types, then produces a short answer with links to the source content.</p>
<p>The plugin works with OpenAI, Google Gemini, and Anthropic Claude. Choose a provider and add your API key in Settings. You can optionally enable embeddings to improve relevance.</p>
<p>Smart Sense is designed for a straightforward setup. Install it, add your API key, and enable the services you need.</p>
<h3>Key Features</h3>
<ul>
<li>AI-generated search summaries (with citations to your content)</li>
<li>Links to the posts and pages used to create the answer</li>
<li>Supports OpenAI, Google Gemini, and Anthropic Claude</li>
<li>Optional embeddings for improved relevance</li>
<li>Works with posts, pages, and custom post types</li>
<li>Simple setup in the WordPress admin</li>
</ul>
<h3>How It Works (RAG)</h3>
<ol>
<li>Index selected content from your site (posts, pages, and CPTs).</li>
<li>Retrieve relevant text snippets for a visitor’s query.</li>
<li>Generate a concise summary using the retrieved snippets.</li>
<li>Display the summary with links back to the original content.</li>
</ol>
<h3>Privacy</h3>
<p>This plugin uses third‑party AI services to generate summaries. Depending on your configuration, portions of your site content (titles, excerpts, or full text) are sent to the provider you select for processing.</p>
<h3>AI Services</h3>
<ul>
<li>
<p>OpenAI (ChatGPT)</p>
<ul>
<li>Data sent: post/page/custom post type content (text) for summary generation</li>
<li>Privacy Policy: https://openai.com/policies/privacy-policy</li>
<li>Terms of Service: https://openai.com/policies/terms-of-use</li>
</ul>
</li>
<li>
<p>Google Gemini (Google AI Studio)</p>
<ul>
<li>Data sent: post/page/custom post type content (text) for summary generation</li>
<li>Privacy Policy: https://policies.google.com/privacy</li>
<li>Terms of Service: https://ai.google.dev/terms</li>
</ul>
</li>
<li>
<p>Anthropic Claude</p>
<ul>
<li>Data sent: post/page/custom post type content (text) for summary generation</li>
<li>Privacy Policy: https://www.anthropic.com/legal/privacy</li>
<li>Terms of Service: https://www.anthropic.com/legal/terms</li>
</ul>
</li>
</ul>
<p>Personal data is not intentionally transmitted unless it appears within the content you choose to process.</p>
<h3>Embeddings</h3>
<p>If embeddings are enabled, text content may be sent to your configured provider to create vector representations that improve retrieval and relevance. Embedding usage is subject to the provider’s terms and policies listed above.</p>
<h3>Third‑Party Services</h3>
<p>This plugin can integrate with:<br />
– INSPECTOR (https://inspector.dev/) for observing and analyzing the performance of external requests.</p>
<p>To use INSPECTOR, set <code>putenv("INSPECTOR_INGESTION_KEY=your_key_here");</code> in <code>wp-config.php</code>.</p>
<h3>General Notes</h3>
<ul>
<li>The plugin stores its own settings in your WordPress database.</li>
<li>Content is sent only to the AI provider(s) you configure, for the sole purpose of generating summaries or embeddings.</li>
<li>By enabling an AI provider, you agree that portions of your content will be transmitted to that provider to deliver the plugin’s functionality.</li>
</ul>
<h3>Configuration</h3>
<p>After installation:<br />
– Obtain API keys for your chosen provider<br />
– Configure model settings<br />
– Enable the smart search feature<br />
– Test on your search page</p>


Smart Sense – AI Knowledge Base for Posts, Pages, and CPTs

Adds AI-generated summaries to your search results by retrieving relevant content from your site.

Fast RAGbot vs Smart Sense – AI Knowledge Base for Posts, Pages, and CPTs