| @@ -1,155 +1,88 @@ | ||
| 1 | -=== MxChat - AI Chatbot & Content Generation for WordPress === | |
| 1 | +=== MxChat - AI Chatbot for WordPress === | |
| 2 | 2 | Contributors: mxchat |
| 3 | 3 | Author: [MxChat](https://mxchat.ai) |
| 4 | -Tags: ai chatbot, chatgpt, woocommerce, customer support, content generation | |
| 4 | +Tags: AI, Chatbot, ChatGPT, Live Chat, Live Support | |
| 5 | 5 | Requires at least: 5.0 |
| 6 | -Tested up to: 6.9 | |
| 6 | +Tested up to: 6.8 | |
| 7 | 7 | Requires PHP: 7.2 |
| 8 | -Stable tag: 3.2.4 | |
| 8 | +Stable tag: 2.3.6 | |
| 9 | 9 | License: GPLv2 or later |
| 10 | 10 | License URI: https://www.gnu.org/licenses/gpl-2.0.html |
| 11 | 11 | |
| 12 | -MxChat is the best free AI chatbot and content generation plugin for WordPress in 2026. Train ChatGPT, Claude, Gemini, or Grok on your website content. Generate full blog posts and landing pages with AI. WooCommerce ready with RAG knowledge base, live chat handoff, and 100+ AI models. | |
| 12 | +AI chatbot with OpenAI, Gemini, Claude, Grok, DeepSeek, live agent, PDF uploads, WooCommerce, and training on website data. | |
| 13 | 13 | |
| 14 | 14 | == Description == |
| 15 | 15 | |
| 16 | -**MxChat is the most powerful free AI chatbot and content generation plugin for WordPress** — connecting your website to ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ AI models through a single, easy-to-use interface. Train your AI chatbot on your website content, WooCommerce products, PDFs, and more using advanced RAG (Retrieval-Augmented Generation) technology. Now with a built-in AI Content Generator to create full blog posts and landing pages complete with images, SEO metadata, and inline AI editing. | |
| 16 | +[Documentation](https://mxchat.ai/documentation/) | [MxChat Pro](https://mxchat.ai/) | |
| 17 | 17 | |
| 18 | -[Documentation](https://mxchat.ai/documentation/) | [Demo Videos](https://www.youtube.com/@MxChat/videos) | |
| 18 | +### 🎥 Product Demo Videos: | |
| 19 | +- [AI Theme Generator Add-On](https://www.youtube.com/watch?v=rSQDW2qbtRU&t) - Transform your chatbot's appearance in seconds with AI-powered design | |
| 20 | +- [Admin Assistant Add-On](https://www.youtube.com/watch?v=AdEA1k-UCFM) - ChatGPT-like experience directly inside your WordPress dashboard | |
| 21 | +- [WooCommerce Add-On](https://www.youtube.com/watch?v=WsqAppHRGdA) - Display product cards, recommendations, and supercharge your store | |
| 22 | +- [MxChat Forms Add-On](https://www.youtube.com/watch?v=3MrWy5dRalA&t) - Convert conversations into data collection with smart forms that trigger during chats | |
| 23 | +- [Chat with PDF & Word](https://www.youtube.com/watch?v=j_c45WWCTG0) - Let users upload and interact with documents | |
| 19 | 24 | |
| 20 | -## Why Choose MxChat as Your WordPress AI Chatbot? | |
| 25 | +[Explore all product videos on YouTube](https://www.youtube.com/@MxChat/videos) | |
| 21 | 26 | |
| 22 | -✅ **6 Major AI Providers in One Plugin**: OpenRouter, OpenAI GPT, Claude, Gemini, xAI Grok, and DeepSeek - switch between 100+ models instantly | |
| 23 | -✅ **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses | |
| 24 | -✅ **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance | |
| 25 | -✅ **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface | |
| 26 | -✅ **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance | |
| 27 | -✅ **AI Content Generator**: Create full blog posts and landing pages with AI-generated images, SEO metadata, and real-time preview editing | |
| 28 | -✅ **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more | |
| 27 | +## 💬 Why Choose MxChat AI Chatbot for Your WordPress Website? | |
| 29 | 28 | |
| 30 | -🎬 [Quick Setup with MxChat](https://www.youtube.com/watch?v=3BqoiyWaQiM) – Learn how to quickly setup and understand how your chatbot works | |
| 29 | +✅ **5 Major AI Providers in One Plugin**: OpenAI GPT, Claude, Gemini, xAI Grok, and DeepSeek - switch between 25+ models instantly | |
| 30 | +✅ **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses | |
| 31 | +✅ **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance | |
| 32 | +✅ **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface | |
| 33 | +✅ **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance | |
| 34 | +✅ **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more | |
| 31 | 35 | |
| 32 | -### 📦 Optional Premium Add-Ons | |
| 33 | -Extend the free plugin with these optional premium features: | |
| 36 | +### 2.3.5 | |
| 37 | +📝 **Improved Chat Transcript UI + New Features** | |
| 38 | +- Transcripts now show the **originating page** where the chat started. | |
| 39 | +- Added ability to view **clicked links** during the session. | |
| 40 | +- **Cleaner, more professional layout** for transcripts, making them easier to read and manage. | |
| 41 | +- You can now **click the header to select sessions** and then delete them with one click. | |
| 34 | 42 | |
| 35 | -- [Advanced Content Editor Add-On](https://mxchat.ai/advanced-content-editor/) – Smart internal linking, AI image management, readability analysis, Google Search Console integration, advanced SEO optimization, and 30-day AI Content Calendar for automated blog scheduling | |
| 36 | -- [WooCommerce Add-On](https://mxchat.ai/woocommerce/) – AI-powered shopping assistance with product-aware conversations, native product cards with images and pricing, upselling and recommendations, order inquiry handling, cart management, and real-time inventory awareness | |
| 37 | -- [Forms Action Add-On](https://mxchat.ai/forms-action/) – Capture leads and data with custom in-chat forms | |
| 38 | -- [MxChat Anywhere Add-On](https://mxchat.ai/mxchat-anywhere-deploy-your-ai-chatbot-on-any-website-with-one-script-tag/) – Deploy your chatbot on any website with one script tag — Shopify, Squarespace, Wix, static HTML, and more | |
| 39 | -- [AI Chatbot Theme Customizer Add-On](https://mxchat.ai/ai-theme-customizer/) – Instantly design chatbot themes with natural language using AI | |
| 40 | -- [Multi-Bot Add-On](https://mxchat.ai/multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities | |
| 41 | -- [Image Analysis Add-On](https://mxchat.ai/image-analysis/) – Enable AI-powered image analysis and OCR inside chats | |
| 43 | +## 🚀 Core Features That Set MxChat Apart | |
| 42 | 44 | |
| 43 | -👉 [Visit our website to view all add-ons](https://mxchat.ai) | |
| 45 | +🟢 **Advanced Action Recognition** – Smart vector embedding system understands user intent and triggers precise actions automatically | |
| 46 | +🟢 **AI Theme Generator** – Describe your ideal design in plain English and watch AI create custom CSS styling in real-time | |
| 47 | +🟢 **Pinecone Vector Storage** – Lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments | |
| 48 | +🟢 **Document Processing** – Users can upload and chat with PDFs and Word documents directly on your frontend | |
| 49 | +🟢 **Web Search Integration** – Brave search provides real-time information beyond your knowledge base | |
| 50 | +🟢 **Image Generation** – DALL-E integration for visual content creation within chat conversations | |
| 51 | +🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience | |
| 44 | 52 | |
| 45 | -## 🔥 What's New in Version 3.2.3 | |
| 53 | +## 🤖 Choose from 25+ Premium AI Models | |
| 46 | 54 | |
| 47 | -- **NEW: Embedding Model Switch Protection** — Changing your embedding model when content is already embedded silently breaks similarity matching. MxChat now warns you with a confirmation dialog before the switch and surfaces a persistent admin notice until the mismatch is resolved, so you never accidentally corrupt your knowledge base. | |
| 48 | -- **Richer Landing Pages** — The Landing Page Generator now plans more sections and writes substantially more copy per section by default, producing fuller, more conversion-ready pages out of the box. | |
| 49 | -- **Full Width Fix for Block Themes** — "Full Width" landing pages now render edge-to-edge on Twenty Twenty-Two through Twenty Twenty-Five and other block themes that previously constrained content via theme.json. | |
| 50 | -- **Cleaner Manual-Entry Citations** — Chat responses no longer leak internal `mxchat://` placeholder URLs when citing manually submitted knowledge entries. | |
| 51 | - | |
| 52 | -## Core Features That Set MxChat Apart | |
| 53 | - | |
| 54 | -🟢 **100+ AI Models** – Access ChatGPT, Claude, Gemini, Grok, DeepSeek, and 100+ models from OpenRouter with a single plugin | |
| 55 | -🟢 **Lead Management Dashboard** – Dedicated Leads tab inside Transcripts shows every captured email and name deduplicated by lead, with filters, bulk delete, CSV export, and one-click jump to each lead's latest conversation | |
| 56 | -🟢 **Chat Transcripts Dashboard** – Review all conversations, analyze chat history, track user engagement, and see exactly which knowledge sources the AI used for each response | |
| 57 | -🟢 **WooCommerce Product Training** – Train your AI chatbot on your entire product catalog including descriptions, pricing, SKUs, and categories for intelligent shopping assistance | |
| 58 | -🟢 **Live Agent Handoff** – Seamlessly escalate conversations from AI to human support via Slack when customers need personal assistance | |
| 59 | -🟢 **ACF Field Control** – Choose exactly which Advanced Custom Fields are included in your knowledge base—perfect for excluding private notes or internal data | |
| 60 | -🟢 **Advanced Action Recognition** – Smart vector embedding system understands user intent and triggers lead capture, appointments, redirects, and custom actions automatically | |
| 61 | -🟢 **Document Processing** – Let visitors upload and chat with PDFs and Word documents directly on your frontend | |
| 62 | -🟢 **Pinecone Vector Storage** – Optional lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments | |
| 63 | -🟢 **Web Search Integration** – Brave search provides real-time information beyond your knowledge base | |
| 64 | -🟢 **AI Content Generator** – Create full blog posts and landing pages from a prompt with AI images, SEO metadata, real-time preview, and inline AI editing via chat | |
| 65 | -🟢 **Image Generation** – OpenAI GPT Image and Google Imagen for visual content creation within chat conversations | |
| 66 | -🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience | |
| 67 | - | |
| 68 | -## Choose from 100+ Premium AI Models | |
| 69 | 55 | Access the world's most advanced AI models based on your specific needs: |
| 70 | 56 | |
| 71 | -**OpenRouter**: 100+ models from multiple providers with a single API key – including OpenAI, Anthropic, Google, Meta, Mistral, and more! | |
| 72 | -**OpenAI**: | |
| 73 | -GPT-5.2, GPT-5.1 Chat Latest, GPT-5.1, GPT-5, GPT-5-mini, GPT-5-nano | |
| 74 | -**Anthropic Claude**: | |
| 75 | -Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 4 Sonnet, Claude 4 Opus | |
| 76 | -**X.AI**: | |
| 77 | -Grok-4, Grok-3, Grok-3 Fast, Grok-3 Mini, Grok-3 Mini Fast, Grok-2, **Grok 4.1 Fast (Reasoning)**, **Grok 4.1 Fast (Non-Reasoning)** | |
| 78 | -**Google Gemini**: | |
| 79 | -Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite, Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, Gemini 1.5 Flash | |
| 80 | -**DeepSeek**: | |
| 81 | -DeepSeek V3 | |
| 57 | +**OpenAI**: GPT-4.1, GPT-4o, GPT-4o-mini, GPT-4-turbo, GPT-4, GPT-3.5-turbo | |
| 58 | +**X.AI**: Grok-4, Grok-3, Grok-3 Fast, Grok-3 Mini, Grok-3 Mini Fast, Grok-2 | |
| 59 | +**Claude**: Claude 4 Sonnet, Claude 4 Opus, Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3 Opus | |
| 60 | +**DeepSeek**: DeepSeek V3 | |
| 61 | +**Google Gemini**: Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, Gemini 1.5 Flash | |
| 82 | 62 | |
| 83 | -## Lead Management Dashboard — Turn Chat Traffic Into a Real Lead List | |
| 63 | +## 🛒 Supercharge Your eCommerce with AI | |
| 84 | 64 | |
| 85 | -Every email and name your chatbot captures now lands in one clean, sortable dashboard — so you can finally see your leads as a list instead of hunting through individual transcripts. | |
| 65 | +Transform online shopping with intelligent assistance: | |
| 86 | 66 | |
| 87 | -**What You Get:** | |
| 67 | +- Engage visitors in real time | |
| 68 | +- Recommend products and upsell with product cards | |
| 69 | +- Recover abandoned carts through chatbot campaigns | |
| 70 | +- Convert passive users into paying customers with live support | |
| 88 | 71 | |
| 89 | -- **One Row Per Lead** — emails captured across multiple sessions are automatically deduplicated, so each lead appears once with a conversation count and a "last seen" timestamp | |
| 90 | -- **Top Pages Capturing Leads** — instantly see which pages on your site are driving the most lead captures; click any page to filter the list to leads from that page only | |
| 91 | -- **Powerful Filtering** — search by email or name, filter by date range (24h / 7d / 30d / 90d / all-time), or filter by status (leads with a conversation vs. orphan leads who submitted the form but never chatted) | |
| 92 | -- **Orphan Lead Tracking** — visitors who drop their email in the pre-chat form but never send a message are surfaced separately so you never lose a captured contact | |
| 93 | -- **One-Click View Conversation** — jump from any lead straight into their latest full conversation in the transcripts viewer | |
| 94 | -- **Bulk Delete + CSV Export** — select multiple leads to delete or export in one action; CSV export supports email-only or email + name + conversation count + last-seen + top page | |
| 95 | -- **Clean, Responsive, Native** — works beautifully on desktop, tablet, and phone with the same polished dashboard feel as the rest of MxChat | |
| 96 | -- **Zero Setup, Zero Migration** — uses your existing chat data, no new database tables, no configuration — turn on lead capture and the dashboard just works | |
| 72 | +## 🔧 Powerful Add-On Ecosystem | |
| 97 | 73 | |
| 98 | -**Perfect for** sales teams managing inbound leads, agencies reporting to clients, and anyone who wants to see the actual ROI of their chatbot at a glance without digging through individual conversations. | |
| 74 | +**Free for All Users:** | |
| 75 | +🟢 **Similarity Tester** – Optimize action recognition with detailed query testing and similarity scores | |
| 99 | 76 | |
| 100 | -## AI Content Generator — Create Blog Posts & Landing Pages with AI | |
| 77 | +**Pro Add-Ons:** | |
| 78 | +🟢 **Admin Assistant** – ChatGPT-like interface in WordPress admin with thread management and image generation | |
| 79 | +🟢 **Theme Customizer** – Visual design editor with AI-powered chatbot theme generation from natural language | |
| 80 | +🟢 **MxChat Forms** – Create chatbot-triggered forms for lead capture and support tickets | |
| 81 | +🟢 **Chat Moderation** – Advanced security with email/IP banning and content filtering | |
| 82 | +🟢 **Smart Recommender** – Intelligent recommendation flows with customizable matching algorithms | |
| 83 | +🟢 **Perplexity Integration** – Real-time web search with authoritative, well-sourced responses | |
| 101 | 84 | |
| 102 | -MxChat includes a built-in AI Content Generator that lets you create full blog posts and landing pages directly from your WordPress dashboard — no external tools or copy-pasting required. | |
| 103 | - | |
| 104 | -**How It Works:** | |
| 105 | - | |
| 106 | -1. **Describe Your Content** — Enter a topic, title, or detailed prompt and choose between a blog post or landing page layout | |
| 107 | -2. **AI Generates Everything** — The AI produces fully styled HTML with responsive CSS, ready-to-publish content, and optional AI-generated images using DALL-E, Gemini, or Grok | |
| 108 | -3. **Real-Time Preview** — See your content exactly as it will appear on your site with a live scaled preview, including desktop and mobile viewport switching | |
| 109 | -4. **Edit with AI Chat** — Use the built-in AI chat panel to request changes like "make the heading bigger" or "change the background to blue" — the AI updates your content in real time | |
| 110 | -5. **Publish Instantly** — Content is saved as a native WordPress post or page with clean HTML, SEO metadata, and responsive design that works with any theme | |
| 111 | - | |
| 112 | -**Key Content Generator Features:** | |
| 113 | - | |
| 114 | -- Choose from multiple AI models for content generation (GPT-5, Claude, Gemini, Grok, and more) | |
| 115 | -- AI-generated images placed directly into your content with automatic media library uploads | |
| 116 | -- SEO title and meta description generation for search engine optimization | |
| 117 | -- Built-in SEO analysis with real-time scoring and one-click AI auto-optimization | |
| 118 | -- Fullwidth and standard layout options with automatic theme compatibility | |
| 119 | -- Content history to revisit and manage previously generated posts | |
| 120 | -- Works with popular page builders and themes including Elementor, Bricks, Divi, Astra, Kadence, and more | |
| 121 | -- Optional [Advanced Content Editor Add-On](https://mxchat.ai/advanced-content-editor/) for Google Search Console analytics, smart internal linking, readability analysis, and advanced SEO optimization | |
| 122 | - | |
| 123 | -## MxChat Anywhere — Deploy Your Chatbot on Any Website | |
| 124 | - | |
| 125 | -Your WordPress site powers the AI, but your chatbot doesn't have to live there. The [MxChat Anywhere Add-On](https://mxchat.ai/mxchat-anywhere-deploy-your-ai-chatbot-on-any-website-with-one-script-tag/) lets you deploy your fully configured chatbot on any website with a single script tag — Shopify, Squarespace, Wix, static HTML, SaaS apps, documentation sites, or anything with an HTML page. | |
| 126 | - | |
| 127 | -**Key Features:** | |
| 128 | - | |
| 129 | -- One script tag to add your chatbot to any site — no coding or framework required | |
| 130 | -- Full style isolation via Shadow DOM so host page CSS never breaks your chatbot | |
| 131 | -- All your MxChat settings carry over automatically — colors, themes, quick questions, email collection, streaming, and more | |
| 132 | -- Multi-bot support lets you deploy different chatbot configurations on different sites | |
| 133 | -- Secure domain whitelisting and API key authentication prevent unauthorized usage | |
| 134 | -- Lightweight vanilla JS widget with zero dependencies — no jQuery needed on the target site | |
| 135 | - | |
| 136 | -**Ideal for** SaaS products with a WordPress blog but a separate web app, e-commerce brands on Shopify, documentation sites, or any business that needs their chatbot beyond WordPress. | |
| 137 | - | |
| 138 | -## Powerful Add-On Ecosystem | |
| 139 | - | |
| 140 | -**Pro Add-Ons:** | |
| 141 | -🟢 **Advanced Content Editor** – Google Search Console integration with per-page impressions, clicks, and search queries. Smart internal linking, AI readability optimization, image ALT text generation, and advanced SEO checks | |
| 142 | -🟢 **Multi-Bot Manager** – Create and manage multiple specialized chatbots with dedicated knowledge databases for different purposes (support, sales, technical, etc.) | |
| 143 | -🟢 **Video Generation** – Generate stunning AI videos using Google's Veo 2 and Veo 3 models with audio support and multiple aspect ratios | |
| 144 | -🟢 **Admin Assistant** – ChatGPT-like interface in WordPress admin with thread management and image generation | |
| 145 | -🟢 **Chat Themes** – Visual design editor with AI-powered chatbot theme generation from natural language | |
| 146 | -🟢 **MxChat Forms** – Create chatbot-triggered forms for lead capture and support tickets | |
| 147 | -🟢 **Chat Moderation** – Advanced security with email/IP banning and content filtering | |
| 148 | -🟢 **MxChat Anywhere** – Deploy your chatbot on any website with one script tag — Shopify, Squarespace, Wix, static HTML, and custom web apps with Shadow DOM style isolation | |
| 149 | -🟢 **Perplexity Integration** – Real-time web search with authoritative, well-sourced responses | |
| 150 | -🟢 **Migration Tool** – Seamlessly switch embedding models and vector databases without losing data, with batch processing and real-time progress tracking | |
| 151 | - | |
| 152 | 85 | ## 📱 Mobile-Friendly & Fully Customizable |
| 153 | 86 | |
| 154 | 87 | MxChat’s chatbot widget adapts seamlessly to all devices — desktop, tablet, or mobile. Customize colors, greetings, and placement to match your brand and provide a smooth experience across your entire website. |
| 155 | 88 | |
| @@ -167,31 +100,18 @@ | ||
| 167 | 100 | ## 🆓 Start with MxChat’s Powerful Free Plan |
| 168 | 101 | |
| 169 | 102 | MxChat offers a fully functional free plan that includes everything you need to get started with AI chatbot and customer support. With no credit card required, you can: |
| 170 | 103 | |
| 171 | -- Access all AI models from 5 major providers | |
| 172 | -- AI Content Generator for blog posts and landing pages with SEO scoring and AI auto-optimization | |
| 173 | -- Train chatbot on unlimited website content | |
| 174 | -- Loops email capture for lead generation | |
| 175 | -- Web search and image generation capabilities | |
| 176 | -- Real-time admin debug panel | |
| 177 | -- Chat transcript review and export | |
| 178 | -- RAG support & contextual awareness | |
| 104 | +- Access all AI models from 5 major providers | |
| 105 | +- Train chatbot on unlimited website content | |
| 106 | +- Loops email capture for lead generation | |
| 107 | +- Web search and image generation capabilities | |
| 108 | +- Real-time admin debug panel | |
| 109 | +- Chat transcript review and export | |
| 110 | +- RAG support & contextual awareness | |
| 179 | 111 | |
| 180 | 112 | Whether you're running a small business or launching a new online store, MxChat’s free plan gives you the tools to offer intelligent customer support and grow your business — without paying a cent. |
| 181 | 113 | |
| 182 | -== Developer Hooks & Filters == | |
| 183 | - | |
| 184 | -MxChat provides WordPress filter hooks so developers can extend and customize chatbot behavior without modifying core plugin files. [View full documentation with code examples](https://mxchat.ai/mxchat-developer-hooks-filters/). | |
| 185 | - | |
| 186 | -= mxchat_before_process_post = | |
| 187 | - | |
| 188 | -Runs during knowledge base indexing and lets you modify a post's data before MxChat processes it. Use this to include custom field data (e.g. product specifications or ACF fields), strip internal content you don't want the chatbot to learn, or transform posts based on bot ID. Receives the WP_Post object and the bot ID. | |
| 189 | - | |
| 190 | -= mxchat_system_instructions = | |
| 191 | - | |
| 192 | -Dynamically modify the system prompt before every AI response. Use this to inject live data such as business hours, inventory status, or user-specific context into the prompt at runtime. Receives the instructions text, bot ID, and session ID. MxChat also supports WordPress shortcodes directly in the system prompt field — any registered shortcodes are automatically expanded before being sent to the AI. | |
| 193 | - | |
| 194 | 114 | ## ✅ Get Started with MxChat AI Chatbot Today |
| 195 | 115 | |
| 196 | 116 | Installing MxChat for WordPress takes just a few clicks. Get started with our free plan and upgrade anytime to access our complete add-on ecosystem and premium features. |
| 197 | 117 | |
| @@ -204,9 +124,8 @@ | ||
| 204 | 124 | |
| 205 | 125 | This plugin connects to AI service providers to generate responses: |
| 206 | 126 | |
| 207 | 127 | **Service Providers:** |
| 208 | -- [OpenRouter](https://openrouter.ai/) - [Terms](https://openrouter.ai/terms) | [Privacy](https://openrouter.ai/privacy) | |
| 209 | 128 | - [OpenAI](https://openai.com/) - [Terms](https://openai.com/policies/terms-of-use/) | [Privacy](https://openai.com/policies/privacy-policy/) |
| 210 | 129 | - [Anthropic](https://anthropic.com/) - [Terms](https://www.anthropic.com/terms) | [Privacy](https://www.anthropic.com/privacy) |
| 211 | 130 | - [Google](https://ai.google.dev/) - [Terms](https://ai.google.dev/terms) | [Privacy](https://policies.google.com/privacy) |
| 212 | 131 | - [X.AI](https://x.ai/) - [Terms](https://x.ai/terms-of-service) | [Privacy](https://x.ai/privacy-policy) |
| @@ -221,434 +140,41 @@ | ||
| 221 | 140 | 3. Navigate to the 'MxChat' settings page to configure your OpenAI API key and other settings. |
| 222 | 141 | |
| 223 | 142 | == Frequently Asked Questions == |
| 224 | 143 | |
| 225 | -= What AI models does MxChat support? = | |
| 144 | +### How do I obtain an API key for OpenAI? | |
| 226 | 145 | |
| 227 | -MxChat supports 100+ AI models including OpenAI GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Google Gemini 2.0 Flash, Gemini 1.5 Pro, xAI Grok 4, Grok 3, DeepSeek Chat, and many more. With OpenRouter integration, you get access to models from OpenAI, Anthropic, Google, Meta, Mistral, and other providers with a single API key. | |
| 146 | +You can obtain an API key by signing up on the OpenAI website. Once you have the API key, enter it in the plugin settings to start using the AI chatbot. | |
| 228 | 147 | |
| 229 | -= How do I get API keys for the AI chatbot? = | |
| 148 | +### Can I customize the chatbot’s appearance? | |
| 230 | 149 | |
| 231 | -For OpenAI, visit platform.openai.com and create an account. For Anthropic Claude, visit console.anthropic.com. For Google Gemini, visit ai.google.dev. For xAI Grok, visit x.ai. For DeepSeek, visit platform.deepseek.com. For OpenRouter (100+ models), visit openrouter.ai. Each provider offers different pricing tiers and free credits for new users. | |
| 150 | +Yes, the **Pro version** offers extensive **theme customization options**, including the ability to change the chatbot’s colors, fonts, and background to match your website’s design. | |
| 232 | 151 | |
| 233 | -= Can I train the AI chatbot on my website content? = | |
| 152 | +### How do I add the chatbot to my site? | |
| 234 | 153 | |
| 235 | -Yes. MxChat supports unlimited knowledge base training using RAG (Retrieval-Augmented Generation) technology. Import content from WordPress pages, posts, WooCommerce products, custom post types, PDFs, Word documents, text files, sitemaps, and manual Q&A entries. The AI chatbot will use your content to provide accurate, contextually relevant responses. | |
| 154 | +You can add the chatbot to your site using the `[mxchat_chatbot floating="yes"]` or `[mxchat_chatbot floating="no"]` shortcode. Additionally, you can automatically append the chatbot to your site’s body element from the settings page. | |
| 236 | 155 | |
| 237 | -= What is RAG technology and how does it work? = | |
| 156 | +### How does the knowledge submission feature work? | |
| 238 | 157 | |
| 239 | -RAG (Retrieval-Augmented Generation) is an AI technique that retrieves relevant information from your knowledge base before generating responses. When a visitor asks a question, MxChat searches your trained content using vector embeddings, finds the most relevant matches, and provides that context to the AI model. This ensures accurate, factual answers based on your actual website content rather than generic AI responses. | |
| 158 | +You can submit custom content to the knowledge base from the 'Knowledge' submenu. This content is processed using vector embeddings, allowing the AI chatbot to provide more accurate and contextually relevant responses. | |
| 240 | 159 | |
| 241 | -= Does MxChat work with WooCommerce? = | |
| 160 | +### What is the sitemap submission feature? | |
| 242 | 161 | |
| 243 | -Yes. MxChat includes full WooCommerce integration. The AI chatbot can be trained on your product catalog including titles, descriptions, pricing, SKUs, categories, and custom fields. Enable auto-sync to automatically update the knowledge base when products change. Your chatbot can answer questions about products, pricing, availability, and help customers find what they need. | |
| 162 | +The sitemap submission feature allows you to submit a sitemap URL. The plugin will fetch, extract, and add content from the URLs listed in the sitemap to the chatbot’s knowledge base, enhancing the AI’s ability to provide precise and contextually relevant answers. | |
| 244 | 163 | |
| 245 | -= Can I customize the AI chatbot appearance? = | |
| 246 | - | |
| 247 | -Yes. MxChat offers extensive customization options including custom colors, chatbot icon, AI avatar, chat bubble size, light/dark/system themes, positioning (left/right), custom CSS, greeting messages, placeholder text, and widget layouts. Use the built-in AI Theme Generator to describe your ideal design and let AI create custom styling automatically. | |
| 248 | - | |
| 249 | -= How do I add the chatbot to my WordPress site? = | |
| 250 | - | |
| 251 | -You can add the chatbot using the shortcode `[mxchat_chatbot floating="yes"]` for a floating widget or `[mxchat_chatbot floating="no"]` for an embedded chat. Alternatively, enable "Append to Body" in settings to automatically display the chatbot on all pages without shortcodes. | |
| 252 | - | |
| 253 | -= Does MxChat support streaming responses? = | |
| 254 | - | |
| 255 | -Yes. MxChat supports real-time streaming responses for OpenAI, Anthropic Claude, and xAI Grok models. Streaming displays AI responses word-by-word as they're generated, providing a faster, more engaging chat experience for your visitors. | |
| 256 | - | |
| 257 | -= What is the Chat Transcripts feature? = | |
| 258 | - | |
| 259 | -The Chat Transcripts dashboard provides comprehensive conversation management. View all chat histories, see detailed conversation flows, track which knowledge sources the AI used for each response, monitor user engagement, and analyze chat analytics including daily activity, peak hours, and user distribution. | |
| 260 | - | |
| 261 | -= Can I see which content the AI chatbot used to answer questions? = | |
| 262 | - | |
| 263 | -Yes. MxChat includes full knowledge source transparency. In the Chat Transcripts and the optional debug panel, you can see exactly which pages, posts, products, or Q&A entries the AI retrieved and used to generate each response, along with relevance scores. | |
| 264 | - | |
| 265 | -= Is Pinecone vector database required? = | |
| 266 | - | |
| 267 | -No. MxChat includes free, unlimited local vector storage in your WordPress database. Pinecone integration is optional and recommended only for enterprise-scale knowledge bases with thousands of entries requiring faster search performance. | |
| 268 | - | |
| 269 | -= Does MxChat support multiple languages? = | |
| 270 | - | |
| 271 | -Yes. The AI chatbot supports multi-language conversations and automatically responds in the language your visitors use. MxChat also supports right-to-left (RTL) languages like Arabic and Hebrew. | |
| 272 | - | |
| 273 | -= How much do AI API calls cost? = | |
| 274 | - | |
| 275 | -API costs depend on your chosen provider and model. OpenAI, Anthropic, Google, and others charge based on token usage. DeepSeek and Google Gemini offer generous free tiers. MxChat includes intelligent token optimization to minimize API costs. You can also set rate limits for guests and logged-in users to control usage. | |
| 276 | - | |
| 277 | -= Is MxChat GDPR compliant? = | |
| 278 | - | |
| 279 | -Yes. All conversation data is stored locally on your WordPress site, giving you complete control. Configure automatic data retention policies, export chat transcripts, or delete conversations as needed for compliance. | |
| 280 | - | |
| 281 | -= Can I restrict chatbot access to certain users? = | |
| 282 | - | |
| 283 | -Yes. MxChat includes role-based access controls. Restrict the chatbot to logged-in users only, specific user roles, or keep it public. You can also restrict specific knowledge base content to certain user roles. | |
| 284 | - | |
| 285 | -= Does MxChat support live chat handoff? = | |
| 286 | - | |
| 287 | -Yes. MxChat integrates with Slack for live agent handoff. When the AI cannot help or a visitor requests human support, conversations can be seamlessly transferred to your team via Slack. | |
| 288 | - | |
| 289 | -= What are Actions and how do they work? = | |
| 290 | - | |
| 291 | -Actions are custom triggers that execute when user intent is detected. Create actions for lead capture, appointment booking, support tickets, page redirects, or custom JavaScript. The AI automatically recognizes when users want to perform these actions and triggers them contextually. | |
| 292 | - | |
| 293 | -= Can visitors upload documents to chat? = | |
| 294 | - | |
| 295 | -Yes. Enable document uploads to let visitors chat with PDFs and Word documents. The AI extracts and processes document content in real-time, allowing contextual Q&A about uploaded files. | |
| 296 | - | |
| 297 | -= Does MxChat support image generation? = | |
| 298 | - | |
| 299 | -Yes. With DALL-E integration, the AI chatbot can generate images based on user descriptions directly within the chat conversation. | |
| 300 | - | |
| 301 | -= How does the knowledge base auto-sync work? = | |
| 302 | - | |
| 303 | -Enable auto-sync for posts, pages, WooCommerce products, or custom post types. When you publish or update content, MxChat automatically updates the knowledge base with the new information. No manual re-importing required. | |
| 304 | - | |
| 305 | -= Can I use Advanced Custom Fields (ACF) with MxChat? = | |
| 306 | - | |
| 307 | -Yes. MxChat fully supports Advanced Custom Fields. ACF field data is automatically included when importing content. Use the ACF Field Settings to control which custom fields are included or excluded from the knowledge base—perfect for hiding private notes or internal data from the chatbot. | |
| 308 | - | |
| 309 | -= What embedding models does MxChat support? = | |
| 310 | - | |
| 311 | -MxChat supports multiple embedding models for vector search including OpenAI text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large, Google Gemini embedding, and Voyage AI embeddings. Choose the model that best fits your accuracy and cost requirements. | |
| 312 | - | |
| 313 | -= Is there a free version of MxChat? = | |
| 314 | - | |
| 315 | -Yes. MxChat is available for free on the WordPress plugin repository with full AI chatbot functionality. Premium add-ons are available for advanced features like the AI Theme Generator and priority support. | |
| 316 | - | |
| 317 | 164 | == Screenshots == |
| 318 | 165 | |
| 319 | -1. **Chat Transcripts Insights** - Review and analyze conversations insights to see engagement rate, peak activity, and user distribution. | |
| 320 | -2. **Chat Transcripts Insights** - View 7 day activity trend graph. | |
| 321 | -3. **Knowledge & Sitemap Submission** - Submit custom content to enhance the chatbot's responses. | |
| 322 | -4. **Action Page** - Set custom action triggers to complete specific actions. | |
| 323 | -5. **Plugin Settings Page** - Configure your API key and other settings. | |
| 324 | -6. **MxChat Debug Panel** - Easily debug and view your content matching scores, citation URLs, triggered actions and more. | |
| 166 | +1. **Knowledge & Sitemap Submission** - Submit custom content to enhance the chatbot's responses. | |
| 167 | +2. **Action Page** - Set custom action triggers to complete specific actions. | |
| 168 | +3. **Plugin Settings Page** - Configure your API key and other settings. | |
| 169 | +4. **Add-ons Page** - Extend MxChat’s functionality with add-ons to customize your needs. | |
| 170 | +5. **Activation Page** - Easily upgrade to MxChat Pro by entering your activation key. Unlock advanced features like theme customization directly from the MxChat settings page. | |
| 171 | +6. **Chat Transcripts** - Review and analyze conversations to refine your AI chatbot. | |
| 325 | 172 | |
| 326 | 173 | *(Note: Screenshots will be added in future updates)* |
| 327 | 174 | |
| 328 | 175 | == Changelog == |
| 329 | 176 | |
| 330 | -= 3.2.4 - May 3, 2026 = | |
| 331 | -- Fixed: WooCommerce product Short Description Visual tab broken by a 404 on the Gutenberg meta-box script | |
| 332 | -- Fixed: User's last message now scrolls to the top of the chat after streaming replies, matching non-streaming behavior | |
| 333 | - | |
| 334 | -= 3.2.3 - April 29, 2026 = | |
| 335 | -- New: Embedding model switch protection — warning dialog when changing embedding models with content already embedded, plus a persistent admin notice while the active and selected models don't match. Each new embedding is now stamped with the model that produced it (KB, actions, action phrases, and Pinecone metadata) so mismatches are detectable | |
| 336 | -- Improved: Landing Page Generator now plans more sections and writes substantially more copy per section, producing fuller, more conversion-ready pages by default | |
| 337 | -- Fixed: Landing Page "Full Width" option not honored on WordPress block themes (Twenty Twenty-Two through Twenty Twenty-Five) — content was constrained by the theme.json layout system | |
| 338 | -- Fixed: Chatbot citing manually submitted knowledge entries with internal `mxchat://` placeholder URLs — placeholders are now correctly treated as manual entries with no citation across both WordPress-DB and Pinecone retrieval paths | |
| 339 | - | |
| 340 | -= 3.2.2 - April 21, 2026 = | |
| 341 | -- NEW: Lead Management Dashboard — dedicated Leads tab inside Transcripts that deduplicates captured emails into a single list with conversation count, last-seen, and the page that captured them. Includes top-pages analytics, search + date/status/page filters, bulk delete with two-step confirm, CSV export (email-only or email + name), and one-click "View convo" to jump to each lead's latest conversation. | |
| 342 | -- Fixed: Orphaned Pinecone chunk vectors left behind when posts or products were unpublished, trashed, deleted, or had their slugs renamed — deletion is now chunk-aware across all sync paths | |
| 343 | -- Fixed: Source count and chunk count settings were being ignored on certain paths and silently fell back to default values — the configured values now apply everywhere | |
| 344 | - | |
| 345 | -= 3.2.1 - April 17, 2026 = | |
| 346 | -- Fixed: Admin Testing Tab debug panel not displaying similarity scores, action matches, or source data — including when web search + streaming are both enabled | |
| 347 | -- Fixed: Web search responses (streaming and non-streaming) not saving RAG context to chat transcripts, causing the "sources" link to be missing | |
| 348 | - | |
| 349 | -= 3.2.0 - April 15, 2026 = | |
| 350 | -- Added: `mxchat_similarity_results` filter hook after similarity search completes, allowing add-ons to access matched sources and their URLs | |
| 351 | -- Removed: `data-no-optimize` attribute injection on MxChat CSS/JS tags, which was conflicting with third-party cache and optimization plugins | |
| 352 | - | |
| 353 | -= 3.1.9 - April 7, 2026 = | |
| 354 | -- Fixed: Session ownership issues that were causing "session expired" errors | |
| 355 | - | |
| 356 | -= 3.1.8 - April 6, 2026 = | |
| 357 | -- New: Loading indicator displayed while chat is initializing | |
| 358 | -- New: Individual trigger phrase embeddings — each key phrase now gets its own vector for more accurate action matching | |
| 359 | -- Improved: Existing actions remain fully backwards compatible with grouped legacy phrases | |
| 360 | -- New: Admin Testing Tab - embedded chatbot replica with real-time debug panel showing similarity scores, action matches, approved URLs, system prompt, and debug log | |
| 361 | -- Improved: "Delete All" in Knowledge Base now respects the active content type filter — only deletes the filtered type (e.g. Pages) instead of everything | |
| 362 | - | |
| 363 | -= 3.1.7 - April 1, 2026 = | |
| 364 | -- Fixed: Chat history not appearing for returning visitors until first message sent when chat persistence is enabled and email collection is off | |
| 365 | -- Fixed: Lead capture form not displaying for new visitors when email collection is enabled | |
| 366 | -- Fixed: Editing legacy manual knowledge base entries deleting all other manual entries sharing the same source URL | |
| 367 | -- New: Google Drive PDF links are now automatically converted to direct downloads for knowledge base import | |
| 368 | - | |
| 369 | -= 3.1.6 - March 30, 2026 = | |
| 370 | -- Fixed: Pre-chat popup reappearing on every page refresh — it now stays dismissed for 24 hours | |
| 371 | -- Fixed: Links with certain special characters in URLs being cut off | |
| 372 | -- Fixed: Chat history not loading for returning visitors | |
| 373 | -- Fixed: Links displaying as plain text instead of clickable links in chat responses | |
| 374 | - | |
| 375 | -= 3.1.5 - March 25, 2026 = | |
| 376 | -- Improved: Lowered default RAG sources limit from 6 to 3 to reduce token usage for users on lower-tier API plans | |
| 377 | -- Improved: Added per-source chunk cap of 5 to prevent any single document from dominating context | |
| 378 | -- New: RAG Chunks Limit setting — control max total chunks sent to AI (range 8–20, default 15) to balance context quality and token cost | |
| 379 | -- New: Page-level chatbot visibility — show, hide, or use global setting per page/post from the meta box | |
| 380 | -- New: Frontend debugger and transcripts now show actual sources and chunks used counts | |
| 381 | - | |
| 382 | -= 3.1.4 - March 22, 2026 = | |
| 383 | -- New: Added support for OpenAI GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-5.3 Chat models | |
| 384 | -- New: Edit Default Prompt — customize the AI system prompt for blog posts and landing pages from the Content page, saved per type across sessions | |
| 385 | -- New: Knowledge base entries can be edited inline with automatic re-chunking and re-embedding (works with both database and Pinecone) | |
| 386 | -- New: Sitemap import now supports PDF URLs — bulk import PDFs via XML sitemap | |
| 387 | -- Improved: Performance updates and bug fixes | |
| 388 | -- Fixed: Clear chat session in MxChat debugger now fully clears chat sessions and context history | |
| 389 | - | |
| 390 | -= 3.1.3 - March 16, 2026 = | |
| 391 | -- New: Content Calendar tab added to Content page — shows locked preview when Advanced Content Editor is not installed, fully functional when add-on is active | |
| 392 | -- New: Chat teaser pop-up message now supports multiple lines. | |
| 393 | -- Improved: Session cookies and tracking now deferred until first user interaction — passive visitors no longer trigger session creation or AJAX calls | |
| 394 | -- Improved: Markdown table rendering with column alignment, responsive scrolling, and alternating row styling | |
| 395 | - | |
| 396 | -= 3.1.2 - March 13, 2026 = | |
| 397 | -- New: Per-check AI fix buttons — hover any failing SEO check to see a sparkle icon that fixes just that item individually | |
| 398 | -- New: SEO dashboard now has row checkboxes with "Optimize Selected" to batch-optimize posts (requires Advanced Content Editor add-on) | |
| 399 | -- Improved: "AI Optimize" button renamed to "Optimize All" for clarity | |
| 400 | -- Improved: SEO modal now includes a "View Page" link and per-check AI fix buttons are always visible | |
| 401 | -- Improved: Post type dropdown now dynamically includes custom post types like WooCommerce Products | |
| 402 | -- Fixed: AI Optimize now runs all addon checks (readability, internal links, image ALT, featured image) in the content editor — previously only meta description, title, and slug were included | |
| 403 | -- Fixed: Chat transcripts not saving bot responses containing emojis due to database table using utf8mb3 charset — upgraded to utf8mb4 | |
| 404 | -- Fixed: WooCommerce product cards now display with image, price, and button in chat transcripts | |
| 405 | -- Fixed: "Optimize All" now runs SEO fixes sequentially to prevent race conditions — previously internal links and other content-modifying fixes could overwrite each other | |
| 406 | -- Upgraded: Image generation replaced deprecated DALL-E 3 with GPT Image (OpenAI) and added Gemini Imagen 4 action | |
| 407 | - | |
| 408 | -= 3.1.1 - March 4, 2026 = | |
| 409 | -- New: Slack agents can now transfer users back to AI mode by typing `!endchat` in the channel | |
| 410 | -- New: Agents can include a custom farewell message (e.g. `!endchat Thanks, have a nice day!`) — the message is delivered to the user before the handoff | |
| 411 | -- New: SEO analysis panel with real-time scoring for posts and pages in the Content section | |
| 412 | -- New: AI Auto-Optimize — one-click AI fixes for meta descriptions, SEO titles, and URL slugs with configurable check selection | |
| 413 | -- New: Google Search Console integration (Pro) — per-page impressions, clicks, CTR, and top search queries directly in the Content editor | |
| 414 | -- New: SEO optimize settings — choose which checks AI Optimize will run from Content > Settings | |
| 415 | -- Fixed: Stale nonce causing "Invalid nonce" errors on sites with full-page caching (WP Rocket, LiteSpeed, W3 Total Cache) — nonce is now refreshed via AJAX on page load | |
| 416 | -- Fixed: Security scanner false-positives flagging `file_put_contents` as malware — replaced with `WP_Filesystem` API for transcript and PDF temp files | |
| 417 | -- Improved: PDF parser library now lazy-loaded on demand instead of on every page request | |
| 418 | - | |
| 419 | - | |
| 420 | -= 3.1.0 - March 1, 2026 = | |
| 421 | -- Fixed: Bulk deleting selected knowledge base entries with chunked content causing network timeout error when using Pinecone | |
| 422 | -- Fixed: Manually entered knowledge base content not being used for AI context despite having high similarity scores | |
| 423 | -- Fixed: Chat input remaining blocked after live agent handoff (Slack/Telegram) | |
| 424 | -- Fixed: Pinecone knowledge base scan returning "Not In Knowledge Base" when using text-embedding-3-large (TE3 Large) due to hardcoded 1536 dimension instead of 3072 | |
| 425 | -- Fixed: Shortcode stripping silently losing all content on pages with large or deeply nested shortcodes (e.g. WPBakery/Visual Composer) due to regex backtracking | |
| 426 | -- New: Added `mxchat_before_process_post` filter hook to allow developers to modify post data before knowledge base processing | |
| 427 | -- New: Added `mxchat_system_instructions` filter hook and shortcode support in system prompt for dynamic data injection | |
| 428 | - | |
| 429 | -= 3.0.9 - February 24, 2026 = | |
| 430 | -- New: AI Content Generator — generate full blog posts and landing pages from a single prompt with AI images, SEO metadata, real-time preview, inline AI editing, and content history | |
| 431 | -- New: Advanced Content Editor premium add-on — smart internal linking, AI image management, and per-field AI meta generation | |
| 432 | -- New: Dynamic post type filtering in knowledge database dropdown — automatically pulls in all registered post types | |
| 433 | -- Improved: Compatibility with popular optimization and caching plugins | |
| 434 | - | |
| 435 | -= 3.0.8 - February 20, 2026 = | |
| 436 | -- New: Debug & optimization tools with log viewer, settings export, and reset options | |
| 437 | -- New: Added Claude Sonnet 4.6 model | |
| 438 | -- Improved: Performance optimizations and caching plugin compatibility | |
| 439 | - | |
| 440 | -= 3.0.7 - February 15, 2026 = | |
| 441 | -- New: Performance optimization | |
| 442 | -- Fixed: GPT-5.1 Chat Latest model returning API error when web search was disabled | |
| 443 | - | |
| 444 | -= 3.0.6 - February 11, 2026 = | |
| 445 | -- New: RAG Sources Limit slider - control how many knowledge base sources (3-10) are included in AI responses | |
| 446 | -- New: {visitor_name} placeholder support in Intro Message and AI Behavior settings for personalized greetings | |
| 447 | -- New: Added Claude Opus 4.6 and Claude Opus 4.5 models | |
| 448 | -- Fixed: Chat persistence OFF now correctly starts fresh AI context on page reload (previously AI retained full history) | |
| 449 | -- Deprecated: Removed all GPT-4 series and GPT-3.5 Turbo from model selection (OpenAI deprecation) | |
| 450 | -- Deprecated: Removed Claude 3.x series models (3.7 Sonnet, 3.5 Sonnet, 3 Opus, 3 Sonnet, 3 Haiku) per Anthropic deprecation | |
| 451 | -- Updated: Users on deprecated OpenAI models auto-migrated to GPT-5.1 Chat Latest (or GPT-5 Mini for mini models) | |
| 452 | -- Updated: Users on deprecated Claude models auto-migrated to Claude Opus 4.6 (or Claude Haiku 4.5 for Haiku users) | |
| 453 | - | |
| 454 | -= 3.0.5 - January 28, 2026 = | |
| 455 | -- Fixed: Updated Gemini embedding model from deprecated `gemini-embedding-exp-03-07` to stable `gemini-embedding-001` | |
| 456 | -- Fixed: Notification settings not saving on new installations | |
| 457 | -- Fixed: Save indicators not visible on settings fields (API keys, Slack, Telegram, Loops, Brave Search) | |
| 458 | -- Added: Warning notice for WordPress database users recommending Pinecone for large knowledge bases | |
| 459 | -- Improved: Minor admin UI updates for better user experience | |
| 460 | - | |
| 461 | -= 3.0.4 - January 24, 2026 = | |
| 462 | -- New: Added latest Google Gemini models (3 Pro Preview, 3 Flash Preview, 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite) | |
| 463 | -- New: Transcript translation feature - auto-translate chat transcripts to any language | |
| 464 | -- New: Action scores visible in transcript sources modal - see document rankings and triggered actions | |
| 465 | -- Fixed: Lead capture forms not working due to multi-bot class ID changes | |
| 466 | - | |
| 467 | -= 3.0.3 - January 21, 2026 = | |
| 468 | -- Fixed: Bug when web search was enabled the chat input was not enabled again. | |
| 469 | - | |
| 470 | -= 3.0.2 - January 21, 2026 = | |
| 471 | -- New: Telegram Live Agent integration for live chat handoff via Telegram forum topics | |
| 472 | -- New: Telegram settings page (Settings > Integrations > Telegram) | |
| 473 | -- New: Telegram action type in Actions page for intent-based handoff | |
| 474 | -- New: Citation Links toggle to enable/disable source URLs in AI responses (Chatbot > Behavior) | |
| 475 | -- Changed: Renamed "Live Agent" settings tab to "Slack" | |
| 476 | - | |
| 477 | -= 3.0.1 - January 18, 2026 = | |
| 478 | -- New: Multi-select entries with bulk "Delete Selected" in knowledge base | |
| 479 | -- New: OpenAI Vector Store integration for knowledge retrieval | |
| 480 | -- New: Custom Post Meta whitelist for including non-ACF meta fields in embeddings | |
| 481 | -- Improved: WordPress database search now filters to matching records only | |
| 482 | -- Improved: WordPress import shows 100 items by default with cross-page selection | |
| 483 | -- Fixed: ACF Field Settings now displays correctly in Knowledge Base sidebar | |
| 484 | -- Changed: Chatbot CSS selectors migrated from IDs to classes for multi-bot support | |
| 485 | -- Note: AI Theme Customizer users must update add-on and click "Migrate" on their theme | |
| 486 | - | |
| 487 | -= 3.0.0 - January 14, 2026 = | |
| 488 | -- New: Complete admin UI overhaul with modern sidebar navigation across all pages | |
| 489 | -- New: Clean, professional design with consistent styling throughout the plugin | |
| 490 | -- New: Automatic sitemap detection with one-click "Process Sitemap" button | |
| 491 | -- New: Real-time knowledge base updates - new entries appear instantly without page refresh | |
| 492 | -- New: Consolidated Pro Upgrade and Add-ons pages into a unified interface | |
| 493 | -- New: Improved mobile responsiveness with collapsible menus and slide-up detail panels | |
| 494 | - | |
| 495 | -= 2.6.4 - January 6, 2026 = | |
| 496 | -- New: ACF Field Control for Knowledge Base imports. Users with Advanced Custom Fields can now control which ACF fields are included when importing content to the knowledge base. A new "ACF Field Settings" section appears in the Knowledge Database Settings tab, displaying all registered ACF field groups and their fields with toggle switches. This allows you to exclude sensitive fields like private notes or internal data from being embedded in the chatbot's knowledge base. | |
| 497 | -- Fixed: Knowledge Database entries now display in correct newest-to-oldest order. Previously, entries appeared in seemingly random order because the sorting was based on source URL rather than timestamp. New submissions now correctly appear at the top of the list. | |
| 498 | -- Fixed: Knowledge Database pagination now works correctly when searching. Previously, clicking to page 2 or beyond while viewing search results would show an empty table because the search parameters were lost during pagination. The search query and security nonce are now properly preserved across all paginated pages. | |
| 499 | -- Fixed: Manual content submissions no longer display a broken "View Source" link. When submitting direct content without a source URL, the Knowledge Database now correctly shows "Manual Content" instead of an empty or invalid link. This applies to both the main table view and individual entry displays. | |
| 500 | -- Fixed: Editing knowledge entries with manual content no longer shows internal mxchat:// URLs in the source field. The URL field now correctly appears empty for manual content entries, allowing users to optionally add a real source URL if desired. | |
| 501 | -- Fixed: Knowledge entries with short content can now be edited properly. Previously, if the content was too short to trigger the expand/collapse accordion, the edit textarea was hidden and inaccessible. The edit button now automatically expands the content area regardless of content length. | |
| 502 | - | |
| 503 | -= 2.6.3 - December 31, 2025 = | |
| 504 | -- New: Text chunking for RAG - large content is automatically split into semantic chunks for improved retrieval accuracy | |
| 505 | -- New: Chunk count display in WordPress Import modal - shows "(X chunks)" badge for multi-chunk content | |
| 506 | -- New: Collapsible chunk groups in Knowledge Base table - entries with multiple chunks are grouped under a single expandable row | |
| 507 | -- New: Chunk labels show "Chunk 1 of 5", "Chunk 2 of 5" etc. when chunks are expanded | |
| 508 | -- New: Chunking settings in Knowledge Database Settings tab - configure chunk size (default 4000 chars) | |
| 509 | -- New: Option to show/hide frontend debug panel in Chatbot Settings | |
| 510 | -- Enhancement: Improved retrieval - finds best matching chunks, then fetches all chunks for top URLs and reassembles | |
| 511 | -- Enhancement: Chat input is now disabled while waiting for bot response, preventing duplicate message submissions | |
| 512 | -- Enhancement: When streaming is turned on it automatically checks if compatible and disables if not. | |
| 513 | -- Fixed: Markdown formatting now preserved correctly when streaming is disabled (newlines were being stripped) | |
| 514 | - | |
| 515 | -= 2.6.2 - December 22, 2025 = | |
| 516 | -- Fixed: Critical error when viewing Knowledge Database with large Pinecone datasets (10K+ products) | |
| 517 | -- Fixed: Optimized Pinecone API queries to prevent memory exhaustion and PHP timeouts | |
| 518 | -- Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100% | |
| 519 | -- New: Post type visibility control - include or exclude specific post types from auto-display chatbot | |
| 520 | -- New: Semantic search in admin now searches ALL Pinecone records using embedded query vectors | |
| 521 | - | |
| 522 | -= 2.6.1 - December 17, 2025 = | |
| 523 | -- Fixed: Send button now includes aria-label for screen reader accessibility | |
| 524 | -- Fixed: Translations now load from /wp-content/languages/plugins/ first, preserving custom translations during updates | |
| 525 | - | |
| 526 | -= 2.6.0 - December 12, 2025 = | |
| 527 | -- New: OpenAI GPT-5.2 model support - best general-purpose and agentic model with fast responses | |
| 528 | -- New: Markdown rendering in transcripts - bot responses display formatted text with clickable links, bold, italic, code blocks, and headers | |
| 529 | -- New: Retrieved documents viewer in transcripts - click "Sources →" link on any bot response to see knowledge base documents used, similarity scores, and citation URLs | |
| 530 | -- Improved: Session security now auto-recovers when user IP changes instead of showing "Unauthorized access" error | |
| 531 | -- Improved: Seamless experience for mobile users switching between WiFi and cellular networks | |
| 532 | - | |
| 533 | -= 2.5.9 - December 6, 2025 = | |
| 534 | -- Fix: Shortcode stripping now preserves content inside shortcodes instead of removing it entirely | |
| 535 | - | |
| 536 | -= 2.5.8 - December 5, 2025 = | |
| 537 | -- New: Auto-email full transcript feature - sends transcript as .txt file attachment after 15, 30, or 60 minutes of user inactivity | |
| 538 | -- New: Conditional transcript emails - option to only send transcripts when visitors provide contact info (email or phone/WhatsApp) in chat | |
| 539 | -- New: Smart contact detection - automatically detects email addresses and phone numbers (including international WhatsApp formats) in chat messages | |
| 540 | -- Compatibility: Tested and compatible with WordPress 6.9 | |
| 541 | - | |
| 542 | -= 2.5.7 - December 2, 2025 = | |
| 543 | -- Fix: Streaming fallback bug - bot responses now properly saved to chat transcripts when streaming fails and falls back to regular response mode | |
| 544 | -- Enhancement: Added comprehensive metrics dashboard to Transcripts page with 3 tabs (Overview, Activity, Insights) | |
| 545 | -- Enhancement: Added 7-day activity trend chart with custom visualization | |
| 546 | -- Enhancement: Added new metrics including daily/weekly/monthly chat counts, peak activity hours, and engagement rates | |
| 547 | -- Enhancement: Added auto-delete transcripts feature with configurable intervals (1 week, 2 weeks, 1 month) for better database management and privacy | |
| 548 | -- Enhancement: WooCommerce product imports now include complete pricing metadata (regular price, sale price, price ranges for variable products, SKU, categories) | |
| 549 | -- Improvement: Updated transcript settings modal for better usability on desktop and mobile | |
| 550 | -- Improvement: Various CSS fixes for metrics dashboard display | |
| 551 | - | |
| 552 | -= 2.5.6 - November 30, 2025 = | |
| 553 | -- Security: Improved session ID validation with server-side checks | |
| 554 | -- Security: Added session ownership verification to prevent unauthorized access to chat sessions | |
| 555 | -- Fixed: Database error "Unknown column 'bot_id'" for multi-bot configurations with automatic migration | |
| 556 | -- Improvement: Enhanced session security with consistent ownership verification | |
| 557 | -- Improvement: Added automatic database schema migration system | |
| 558 | -- Improvement: WooCommerce import improvements to support Custom Tabs information | |
| 559 | -- Improvement: Database management with a new filtering option. Filter by posts, pages, products, PDF | |
| 560 | - | |
| 561 | -= 2.5.5 - November 21, 2025 = | |
| 562 | -- Fixed: Issue with non-streaming mode failing to format URLs and paragraphs correctly | |
| 563 | -- Fixed: Bug with shortcodes still appearing in the knowledge database | |
| 564 | -- Enhancement: Minor adjustments to improve compatibility with multi-bot setups requiring email-to-chat forms | |
| 565 | -- New: Added Grok 4.1 Fast (Reasoning) model — 2M context, reasoning | |
| 566 | -- New: Added Grok 4.1 Fast (Non-Reasoning) model — 2M context, faster responses | |
| 567 | -- New: Added OpenAI GPT-5.1 model — flagship for coding & agentic tasks with low reasoning and 400K context | |
| 568 | - | |
| 569 | -= 2.5.4 - November 12, 2025 = | |
| 570 | -- New: Accordion-Style Knowledge Base Viewer for cleaner, expandable database entry previews | |
| 571 | -- New: Smart Shortcode Stripping for WPBakery and Elementor during content submission to improve vectorization accuracy | |
| 572 | -- New: Unique Citation URLs when submitting direct content, allowing multiple linked submissions without overwriting | |
| 573 | -- Improvement: WooCommerce products now include both short and full descriptions during data processing | |
| 574 | - | |
| 575 | -= 2.5.3 - November 9, 2025 = | |
| 576 | -- New: Dedicated API Key Management Tab - All API keys organized in one central location for easier management | |
| 577 | -- Improvement: GPT-5 performance optimization with minimal reasoning effort mode for significantly faster response times | |
| 578 | -- Fix: Resolved URL and PDF link encoding issues causing broken or unclickable links in responses | |
| 579 | -- Improvement: Various performance enhancements for improved stability and faster processing | |
| 580 | - | |
| 581 | -= 2.5.2 - November 3, 2025 = | |
| 582 | -- New: URL Hallucination Prevention System - AI only cites URLs from knowledge base or system instructions, with automatic removal of invalid links | |
| 583 | -- Improvement: Brand new robust queue-based processing system for sitemap and PDF imports with real-time progress tracking | |
| 584 | -- Improvement: Optimized knowledge retrieval from 5 to 3 documents for faster response times and improved accuracy | |
| 585 | -- Improvement: Increased URL column size to TEXT type for support of long URLs and special characters (Hebrew, Arabic, etc.) | |
| 586 | -- Fix: Resolved URL double-encoding issue causing malformed PDF and document links | |
| 587 | -- Fix: Corrected citation-style bracket handling for AI responses containing [URL] format | |
| 588 | -- Fix: Fixed empty markdown link processing to prevent broken link generation | |
| 589 | - | |
| 590 | -= 2.5.1 - October 30, 2025 = | |
| 591 | -- New: Tag-based role restrictions for chatbot knowledge base - automatically control what content the chatbot can access based on WordPress tags and user roles | |
| 592 | -- Update: Migrated users from deprecated Claude 3.5 Sonnet to Claude 3.7 Sonnet with improved performance | |
| 593 | -- Fix: Removed deprecated Claude model from selection options | |
| 594 | - | |
| 595 | -= 2.5.0 - October 25, 2025 = | |
| 596 | -- Fix: Resolved PDF URL encoding issue that caused broken links to PDF documents | |
| 597 | -- Fix: Improved UI feedback when selecting chat models | |
| 598 | -- Fix: Enhanced OpenRouter flow selection interface | |
| 599 | - | |
| 600 | -= 2.4.8 - October 16, 2025 = | |
| 601 | -- New: OpenRouter integration - access 100+ AI models with a single API key | |
| 602 | -- New: Added Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5 support | |
| 603 | - | |
| 604 | -= 2.4.7 - October 13, 2025 = | |
| 605 | -- Security: Fixed Server-Side Request Forgery (SSRF) vulnerability in PDF processing (CVE-2025-10705) | |
| 606 | - | |
| 607 | -= 2.4.5 - September 30, 2025 = | |
| 608 | -- Bug Fix: Restored missing CSS properties for popular questions collapse/toggle buttons that were accidentally removed during code cleanup. | |
| 609 | -- Bug Fix: Fixed button hover, focus, and active states for question navigation controls. | |
| 610 | -- Bug Fix: Restored proper SVG styling and display logic for collapsible question buttons. | |
| 611 | - | |
| 612 | -= 2.4.4 - September 24, 2025 = | |
| 613 | -- Bug Fix: Default similarity is now accurate across all settings. | |
| 614 | -- Bug Fix: Improved streaming responses to prevent dropped characters or words. | |
| 615 | -- Enhanced: Removed unnecessary Pinecone caching in the knowledge database for more accurate results. | |
| 616 | - | |
| 617 | -= 2.4.3 - September 23, 2025 = | |
| 618 | -- Added: Support for upcoming multi-bot update that allows for more customized settings such as individual chat models. | |
| 619 | -- Improved: CSS for chatbot UI & more robust markdown support. | |
| 620 | - | |
| 621 | -= 2.4.2 - September 18, 2025 = | |
| 622 | -- Added: Multi-bot support via the new Multi-Bot Manager premium add-on. | |
| 623 | -- Improved: Minor CSS adjustments for better compatibility. | |
| 624 | -- Updated: Add-on links and references throughout the plugin. | |
| 625 | - | |
| 626 | -= 2.4.1 - September 4, 2025 = | |
| 627 | -- Fixed: Email collection form not submitting properly when "Require email to chat" is enabled. | |
| 628 | -- Improved: PDF processing now provides clearer error messages with repair suggestions when corrupted files are detected. | |
| 629 | - | |
| 630 | -= 2.4.0 - September 3, 2025 = | |
| 631 | -- Added new MxChat Video Generation add-on with support for Google Veo 2 and Veo 3 models, featuring audio generation and multiple aspect ratios. | |
| 632 | -- Fixed console error when "Require email to chat" option is disabled by adding proper validation check. | |
| 633 | -- Resolved "error chat history not found" message when chat persistence is enabled but user has no existing chat history. | |
| 634 | -- Fixed agent indicator not updating properly when switching between live agent and chatbot modes without page refresh. | |
| 635 | - | |
| 636 | -= 2.3.9 - August 17, 2025 = | |
| 637 | -- Updated Slack channel naming logic to prioritize client’s name, falling back to email, then chat ID. | |
| 638 | -- Added streaming response support for DeepSeek models. | |
| 639 | -- Enabled multiple direct content entries without requiring a source URL. | |
| 640 | -- Fixed auto sync drafts so posts moved from posted to draft are removed from the knowledge database. | |
| 641 | -- Implemented role-based chatbot information access restrictions for enhanced security and relevance. | |
| 642 | -- Added option in the admin panel’s post edit page to hide the floating chatbot on specific pages. | |
| 643 | - | |
| 644 | -= 2.3.8 - August 12, 2025 = | |
| 645 | -- Fixed extra backslashes appearing in knowledgebase content during editing. | |
| 646 | -- Added optional name field to Require Email to Chat form; transcripts now display email and name if enabled. | |
| 647 | -- Updated Slack channel naming for live agent notifications: uses user's email if logged in, email if Require Email to Chat is enabled, or chat ID otherwise. | |
| 648 | - | |
| 649 | -= 2.3.7 - August 8, 2025 = | |
| 650 | -- New Models: Added GPT-5 family (GPT-5, GPT-5 Mini, GPT-5 Nano) to expand capabilities with faster, smarter, and more cost-efficient options. | |
| 651 | 177 | = 2.3.6 - August 6, 2025 = |
| 652 | 178 | - Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles. |
| 653 | 179 | - New Feature: Added streaming test button to help users verify if streaming is compatible with their setup. |
| 654 | 180 | |
| @@ -719,9 +245,9 @@ | ||
| 719 | 245 | - Fixed Pinecone setting not toggling on for users who previously did not have the add-on. |
| 720 | 246 | |
| 721 | 247 | = 2.2.1 = |
| 722 | 248 | - Added Claude Sonnet 4 and Claude Opus 4 chat models. |
| 723 | -- Integrated Google Gemini embedding model (gemini-embedding-001). | |
| 249 | +- Integrated Google Gemini embedding model (gemini-embedding-exp-03-07). | |
| 724 | 250 | - Built Pinecone vector database support directly into core plugin. |
| 725 | 251 | - Removed dependency on separate Pinecone add-on. |
| 726 | 252 | |
| 727 | 253 | = 2.2.0 = |
| @@ -739,8 +265,9 @@ | ||
| 739 | 265 | = 2.1.7 = |
| 740 | 266 | - Fixed Pro activation issues when the plugin has been translated. |
| 741 | 267 | - Improved tab behavior to always default to the first tab. |
| 742 | 268 | - Major rework to rate limits: added custom rate limit timeframes and messages for each individual role. |
| 269 | +- Added support for new MxChat Smart Recommender add-on. | |
| 743 | 270 | - Fixed bug with Loops where manual list selection from dropdown was required for functionality. |
| 744 | 271 | |
| 745 | 272 | = 2.1.6 = |
| 746 | 273 | - Added new AI models: GPT-4.1 and the complete suite of Grok 3 models. |
| @@ -973,10 +500,11 @@ | ||
| 973 | 500 | * Fixed error when users didn't have WooCommerce it would return "Error communicating with server". |
| 974 | 501 | |
| 975 | 502 | == Upgrade Notice == |
| 976 | 503 | |
| 977 | -= 3.2.4 = | |
| 978 | -Fixes the WooCommerce Short Description Visual editor and restores scroll-to-top of the user's last message on streaming replies. | |
| 504 | += 2.3.6 = | |
| 505 | +- Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles. | |
| 506 | +- New Feature: Added streaming test button to help users verify if streaming is compatible with their setup. | |
| 979 | 507 | |
| 980 | 508 | == License & Warranty == |
| 981 | 509 | |
| 982 | 510 | This plugin is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. |
