PluginProbe
MxChat – AI Chatbot & Content Generation for WordPress / 2.6.2
MxChat – AI Chatbot & Content Generation for WordPress v2.6.2
3.2.21 3.2.20 3.2.19 3.2.18 3.2.17 3.2.16 3.2.15 3.2.14 3.2.12 3.2.13 3.2.11 3.2.10 3.2.9 3.2.8 3.2.7 3.2.6 3.2.5 3.2.4 3.2.3 3.2.2 3.2.1 2.0.3 2.0.4 2.0.5 2.0.6 All 152 releases
mxchat-basic / readme.txt

readme.txt in MxChat – AI Chatbot & Content Generation for WordPress 2.6.2, at readme.txt

678 lines 41.2 KB
No matching file
Up and down to move Enter to open Esc to close
Raw Download Zip
1 === MxChat - AI Chatbot for WordPress ===
2 Contributors: mxchat
3 Author: [MxChat](https://mxchat.ai)
4 Tags: AI, Chatbot, ChatGPT, Live Chat, Live Support
5 Requires at least: 5.0
6 Tested up to: 6.9
7 Requires PHP: 7.2
8 Stable tag: 2.6.2
9 License: GPLv2 or later
10 License URI: https://www.gnu.org/licenses/gpl-2.0.html
11
12 AI chatbot with OpenAI, Gemini, Claude, Grok, DeepSeek, OpenRouter, live agent, WooCommerce, and training on website data.
13
14 == Description ==
15
16 [Documentation](https://mxchat.ai/documentation/)
17
18 ## Why Choose MxChat AI Chatbot for Your WordPress Website?
19
20
21 **6 Major AI Providers in One Plugin**: OpenRouter, OpenAI GPT, Claude, Gemini, xAI Grok, and DeepSeek - switch between 100+ models instantly
22
23 **Train on Your Website Data**: Advanced RAG technology learns from sitemaps, PDFs, URLs, or manual input for ultra-relevant responses
24
25 **Live Agent Handoff via Slack**: Seamlessly escalate from AI to human support when customers need personal assistance
26
27 **Real-Time Debug Panel**: See exactly what your chatbot retrieves and triggers with our admin testing interface
28
29 **Boost Sales with WooCommerce**: Product cards, cart management, and AI-powered shopping assistance
30
31 **Extensive Add-On Ecosystem**: Forms, moderation, recommendations, theme customization, and more
32
33 ### 📦 Optional Premium Add-Ons
34 Extend the free plugin with these optional premium features:
35
36 - [Forms Action Add-On](https://mxchat.ai/forms-action/) – Capture leads and data with custom in-chat forms
37 - [WooCommerce Add-On](https://mxchat.ai/woocommerce/) – AI-powered shopping assistance and product recommendations
38 - [AI Theme Customizer Add-On](https://mxchat.ai/ai-theme-customizer/) – Instantly design chatbot themes with natural language
39 - [Multi-Bot Add-On](https://mxchat.ai/multi-bot/) – Run unlimited AI chatbots with custom knowledge and personalities
40 - [Image Analysis Add-On](https://mxchat.ai/image-analysis/) – Enable AI-powered image analysis and OCR inside chats
41
42 👉 [Visit our website to view all add-ons](https://mxchat.ai)
43
44 ### 🎥 Product Demo Videos
45 [Explore all product videos on YouTube](https://www.youtube.com/@MxChat/videos)
46
47 ## 🔥 What's New in Version 2.6.2
48
49 🚀 **Large Pinecone Database Fix**
50 - Fixed: Critical error when viewing Knowledge Database with large datasets (10K+ products)
51 - Fixed: Optimized Pinecone queries to prevent memory exhaustion and timeouts
52
53 📐 **Viewport-Aware Chatbot Sizing**
54 - Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100%
55
56 🎯 **Post Type Visibility Control**
57 - New: Control which post types display the auto-display chatbot (include or exclude specific post types)
58
59 ## Core Features That Set MxChat Apart
60
61 🟢 **Advanced Action Recognition** – Smart vector embedding system understands user intent and triggers precise actions automatically
62 🟢 **AI Theme Generator** – Describe your ideal design in plain English and watch AI create custom CSS styling in real-time
63 🟢 **Pinecone Vector Storage** – Lightning-fast knowledge retrieval for large datasets and enterprise-scale deployments
64 🟢 **Document Processing** – Users can upload and chat with PDFs and Word documents directly on your frontend
65 🟢 **Web Search Integration** – Brave search provides real-time information beyond your knowledge base
66 🟢 **Image Generation** – DALL-E integration for visual content creation within chat conversations
67 🟢 **Streaming Responses** – Real-time response streaming for OpenAI, Claude, and Grok models for the fastest possible chat experience
68
69 ## Choose from 100+ Premium AI Models
70 Access the world's most advanced AI models based on your specific needs:
71
72 **OpenRouter**: 100+ models from multiple providers with a single API key – including OpenAI, Anthropic, Google, Meta, Mistral, and more!
73 **OpenAI**:
74 GPT-5.2, GPT-5, GPT-5-mini, GPT-5-nano, GPT-5.1, GPT-4.1, GPT-4o, GPT-4o-mini, GPT-4-turbo, GPT-4, GPT-3.5-turbo
75 **Anthropic Claude**:
76 Claude Sonnet 4.5, Claude Opus 4.1, Claude Haiku 4.5, Claude 4 Sonnet, Claude 4 Opus, Claude 3.7 Sonnet, Claude 3.5 Sonnet (deprecated), Claude 3 Opus
77 **X.AI**:
78 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)**
79 **Google Gemini**:
80 Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, Gemini 1.5 Flash
81 **DeepSeek**:
82 DeepSeek V3
83
84 ## Supercharge Your eCommerce with AI
85
86 Transform online shopping with intelligent assistance through direct WooCommerce integration:
87
88 - Engage visitors in real time with product-aware conversations
89 - Recommend products and upsell with native WooCommerce product cards
90 - Access order history, inventory, and customer data seamlessly
91 - Convert passive users into paying customers with live support
92 - Handle order inquiries and status updates directly through chat
93
94 ## Powerful Add-On Ecosystem
95
96 **Pro Add-Ons:**
97 🟢 **Multi-Bot Manager** – Create and manage multiple specialized chatbots with dedicated knowledge databases for different purposes (support, sales, technical, etc.)
98 🟢 **Video Generation** – Generate stunning AI videos using Google's Veo 2 and Veo 3 models with audio support and multiple aspect ratios
99 🟢 **Admin Assistant** – ChatGPT-like interface in WordPress admin with thread management and image generation
100 🟢 **Theme Customizer** – Visual design editor with AI-powered chatbot theme generation from natural language
101 🟢 **MxChat Forms** – Create chatbot-triggered forms for lead capture and support tickets
102 🟢 **Chat Moderation** – Advanced security with email/IP banning and content filtering
103 🟢 **Perplexity Integration** – Real-time web search with authoritative, well-sourced responses
104 🟢 **Migration Tool** – Seamlessly switch embedding models and vector databases without losing data, with batch processing and real-time progress tracking
105
106 ## 📱 Mobile-Friendly & Fully Customizable
107
108 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.
109
110 ## 🔐 Reliable, Fast, Secure
111
112 MxChat is optimized for performance and security. Your AI chatbot runs smoothly, loads fast, and protects your customer data with enterprise-grade security measures.
113
114 ## 🌟 What Makes MxChat the Best AI Chatbot for WordPress?
115
116 - Used by hundreds of WordPress websites worldwide
117 - 5-star average rating from satisfied customers
118 - Native WordPress integration - no external dependencies
119 - Setup in under 2 minutes with simple API key configuration
120
121 ## 🆓 Start with MxChat’s Powerful Free Plan
122
123 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:
124
125 - Access all AI models from 5 major providers
126 - Train chatbot on unlimited website content
127 - Loops email capture for lead generation
128 - Web search and image generation capabilities
129 - Real-time admin debug panel
130 - Chat transcript review and export
131 - RAG support & contextual awareness
132
133 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.
134
135 ## �
136 Get Started with MxChat AI Chatbot Today
137
138 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.
139
140 ## 💰 Pricing
141
142 Most powerful features are included in the free plan. Upgrade to Pro for the complete add-on ecosystem and advanced capabilities.
143 [View all pricing options](https://mxchat.ai/)
144
145 == Use of Third-Party Services ==
146
147 This plugin connects to AI service providers to generate responses:
148
149 **Service Providers:**
150 - [OpenRouter](https://openrouter.ai/) - [Terms](https://openrouter.ai/terms) | [Privacy](https://openrouter.ai/privacy)
151 - [OpenAI](https://openai.com/) - [Terms](https://openai.com/policies/terms-of-use/) | [Privacy](https://openai.com/policies/privacy-policy/)
152 - [Anthropic](https://anthropic.com/) - [Terms](https://www.anthropic.com/terms) | [Privacy](https://www.anthropic.com/privacy)
153 - [Google](https://ai.google.dev/) - [Terms](https://ai.google.dev/terms) | [Privacy](https://policies.google.com/privacy)
154 - [X.AI](https://x.ai/) - [Terms](https://x.ai/terms-of-service) | [Privacy](https://x.ai/privacy-policy)
155 - [DeepSeek](https://deepseek.com/) - [Terms](https://deepseek.com/terms) | [Privacy](https://deepseek.com/privacy)
156
157 Please ensure compliance with applicable terms and data privacy laws.
158
159 == Installation ==
160
161 1. Upload the `mxchat` folder to the `/wp-content/plugins/` directory.
162 2. Activate the plugin through the 'Plugins' menu in WordPress.
163 3. Navigate to the 'MxChat' settings page to configure your OpenAI API key and other settings.
164
165 == Frequently Asked Questions ==
166
167 ### How do I obtain an API key for OpenAI?
168
169 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.
170
171 ### Can I customize the chatbot’s appearance?
172
173 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.
174
175 ### How do I add the chatbot to my site?
176
177 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.
178
179 ### How does the knowledge submission feature work?
180
181 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.
182
183 ### What is the sitemap submission feature?
184
185 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.
186
187 == Screenshots ==
188
189 1. **Knowledge & Sitemap Submission** - Submit custom content to enhance the chatbot's responses.
190 2. **Action Page** - Set custom action triggers to complete specific actions.
191 3. **Plugin Settings Page** - Configure your API key and other settings.
192 4. **MxChat Debug Panel** - Easily debug and view your content matching scores, citation URLs, triggered actions and more.
193 5. **Chat Transcripts Activity** - View 7 day activity trend graph.
194 6. **Chat Transcripts Insights** - Review and analyze conversations insights to see engagement rate, peak activity, and user distribution.
195
196 *(Note: Screenshots will be added in future updates)*
197
198 == Changelog ==
199
200 = 2.6.2 - December 22, 2025 =
201 - Fixed: Critical error when viewing Knowledge Database with large Pinecone datasets (10K+ products)
202 - Fixed: Optimized Pinecone API queries to prevent memory exhaustion and PHP timeouts
203 - Fixed: Chatbot no longer gets cut off when browser has bookmarks bar or is zoomed above 100%
204 - New: Post type visibility control - include or exclude specific post types from auto-display chatbot
205 - New: Semantic search in admin now searches ALL Pinecone records using embedded query vectors
206
207 = 2.6.1 - December 17, 2025 =
208 - Fixed: Send button now includes aria-label for screen reader accessibility
209 - Fixed: Translations now load from /wp-content/languages/plugins/ first, preserving custom translations during updates
210
211 = 2.6.0 - December 12, 2025 =
212 - New: OpenAI GPT-5.2 model support - best general-purpose and agentic model with fast responses
213 - New: Markdown rendering in transcripts - bot responses display formatted text with clickable links, bold, italic, code blocks, and headers
214 - New: Retrieved documents viewer in transcripts - click "Sources →" link on any bot response to see knowledge base documents used, similarity scores, and citation URLs
215 - Improved: Session security now auto-recovers when user IP changes instead of showing "Unauthorized access" error
216 - Improved: Seamless experience for mobile users switching between WiFi and cellular networks
217
218 = 2.5.9 - December 6, 2025 =
219 - Fix: Shortcode stripping now preserves content inside shortcodes instead of removing it entirely
220
221 = 2.5.8 - December 5, 2025 =
222 - New: Auto-email full transcript feature - sends transcript as .txt file attachment after 15, 30, or 60 minutes of user inactivity
223 - New: Conditional transcript emails - option to only send transcripts when visitors provide contact info (email or phone/WhatsApp) in chat
224 - New: Smart contact detection - automatically detects email addresses and phone numbers (including international WhatsApp formats) in chat messages
225 - Compatibility: Tested and compatible with WordPress 6.9
226
227 = 2.5.7 - December 2, 2025 =
228 - Fix: Streaming fallback bug - bot responses now properly saved to chat transcripts when streaming fails and falls back to regular response mode
229 - Enhancement: Added comprehensive metrics dashboard to Transcripts page with 3 tabs (Overview, Activity, Insights)
230 - Enhancement: Added 7-day activity trend chart with custom visualization
231 - Enhancement: Added new metrics including daily/weekly/monthly chat counts, peak activity hours, and engagement rates
232 - Enhancement: Added auto-delete transcripts feature with configurable intervals (1 week, 2 weeks, 1 month) for better database management and privacy
233 - Enhancement: WooCommerce product imports now include complete pricing metadata (regular price, sale price, price ranges for variable products, SKU, categories)
234 - Improvement: Updated transcript settings modal for better usability on desktop and mobile
235 - Improvement: Various CSS fixes for metrics dashboard display
236
237 = 2.5.6 - November 30, 2025 =
238 - Security: Improved session ID validation with server-side checks
239 - Security: Added session ownership verification to prevent unauthorized access to chat sessions
240 - Fixed: Database error "Unknown column 'bot_id'" for multi-bot configurations with automatic migration
241 - Improvement: Enhanced session security with consistent ownership verification
242 - Improvement: Added automatic database schema migration system
243 - Improvement: WooCommerce import improvements to support Custom Tabs information
244 - Improvement: Database management with a new filtering option. Filter by posts, pages, products, PDF
245
246 = 2.5.5 - November 21, 2025 =
247 - Fixed: Issue with non-streaming mode failing to format URLs and paragraphs correctly
248 - Fixed: Bug with shortcodes still appearing in the knowledge database
249 - Enhancement: Minor adjustments to improve compatibility with multi-bot setups requiring email-to-chat forms
250 - New: Added Grok 4.1 Fast (Reasoning) model — 2M context, reasoning
251 - New: Added Grok 4.1 Fast (Non-Reasoning) model — 2M context, faster responses
252 - New: Added OpenAI GPT-5.1 model — flagship for coding & agentic tasks with low reasoning and 400K context
253
254 = 2.5.4 - November 12, 2025 =
255 - New: Accordion-Style Knowledge Base Viewer for cleaner, expandable database entry previews
256 - New: Smart Shortcode Stripping for WPBakery and Elementor during content submission to improve vectorization accuracy
257 - New: Unique Citation URLs when submitting direct content, allowing multiple linked submissions without overwriting
258 - Improvement: WooCommerce products now include both short and full descriptions during data processing
259
260 = 2.5.3 - November 9, 2025 =
261 - New: Dedicated API Key Management Tab - All API keys organized in one central location for easier management
262 - Improvement: GPT-5 performance optimization with minimal reasoning effort mode for significantly faster response times
263 - Fix: Resolved URL and PDF link encoding issues causing broken or unclickable links in responses
264 - Improvement: Various performance enhancements for improved stability and faster processing
265
266 = 2.5.2 - November 3, 2025 =
267 - New: URL Hallucination Prevention System - AI only cites URLs from knowledge base or system instructions, with automatic removal of invalid links
268 - Improvement: Brand new robust queue-based processing system for sitemap and PDF imports with real-time progress tracking
269 - Improvement: Optimized knowledge retrieval from 5 to 3 documents for faster response times and improved accuracy
270 - Improvement: Increased URL column size to TEXT type for support of long URLs and special characters (Hebrew, Arabic, etc.)
271 - Fix: Resolved URL double-encoding issue causing malformed PDF and document links
272 - Fix: Corrected citation-style bracket handling for AI responses containing [URL] format
273 - Fix: Fixed empty markdown link processing to prevent broken link generation
274
275 = 2.5.1 - October 30, 2025 =
276 - New: Tag-based role restrictions for chatbot knowledge base - automatically control what content the chatbot can access based on WordPress tags and user roles
277 - Update: Migrated users from deprecated Claude 3.5 Sonnet to Claude 3.7 Sonnet with improved performance
278 - Fix: Removed deprecated Claude model from selection options
279
280 = 2.5.0 - October 25, 2025 =
281 - Fix: Resolved PDF URL encoding issue that caused broken links to PDF documents
282 - Fix: Improved UI feedback when selecting chat models
283 - Fix: Enhanced OpenRouter flow selection interface
284
285 = 2.4.8 - October 16, 2025 =
286 - New: OpenRouter integration - access 100+ AI models with a single API key
287 - New: Added Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5 support
288
289 = 2.4.7 - October 13, 2025 =
290 - Security: Fixed Server-Side Request Forgery (SSRF) vulnerability in PDF processing (CVE-2025-10705)
291
292 = 2.4.5 - September 30, 2025 =
293 - Bug Fix: Restored missing CSS properties for popular questions collapse/toggle buttons that were accidentally removed during code cleanup.
294 - Bug Fix: Fixed button hover, focus, and active states for question navigation controls.
295 - Bug Fix: Restored proper SVG styling and display logic for collapsible question buttons.
296
297 = 2.4.4 - September 24, 2025 =
298 - Bug Fix: Default similarity is now accurate across all settings.
299 - Bug Fix: Improved streaming responses to prevent dropped characters or words.
300 - Enhanced: Removed unnecessary Pinecone caching in the knowledge database for more accurate results.
301
302 = 2.4.3 - September 23, 2025 =
303 - Added: Support for upcoming multi-bot update that allows for more customized settings such as individual chat models.
304 - Improved: CSS for chatbot UI & more robust markdown support.
305
306 = 2.4.2 - September 18, 2025 =
307 - Added: Multi-bot support via the new Multi-Bot Manager premium add-on.
308 - Improved: Minor CSS adjustments for better compatibility.
309 - Updated: Add-on links and references throughout the plugin.
310
311 = 2.4.1 - September 4, 2025 =
312 - Fixed: Email collection form not submitting properly when "Require email to chat" is enabled.
313 - Improved: PDF processing now provides clearer error messages with repair suggestions when corrupted files are detected.
314
315 = 2.4.0 - September 3, 2025 =
316 - Added new MxChat Video Generation add-on with support for Google Veo 2 and Veo 3 models, featuring audio generation and multiple aspect ratios.
317 - Fixed console error when "Require email to chat" option is disabled by adding proper validation check.
318 - Resolved "error chat history not found" message when chat persistence is enabled but user has no existing chat history.
319 - Fixed agent indicator not updating properly when switching between live agent and chatbot modes without page refresh.
320
321 = 2.3.9 - August 17, 2025 =
322 - Updated Slack channel naming logic to prioritize client’s name, falling back to email, then chat ID.
323 - Added streaming response support for DeepSeek models.
324 - Enabled multiple direct content entries without requiring a source URL.
325 - Fixed auto sync drafts so posts moved from posted to draft are removed from the knowledge database.
326 - Implemented role-based chatbot information access restrictions for enhanced security and relevance.
327 - Added option in the admin panel’s post edit page to hide the floating chatbot on specific pages.
328
329 = 2.3.8 - August 12, 2025 =
330 - Fixed extra backslashes appearing in knowledgebase content during editing.
331 - Added optional name field to Require Email to Chat form; transcripts now display email and name if enabled.
332 - 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.
333
334 = 2.3.7 - August 8, 2025 =
335 - 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.
336 = 2.3.6 - August 6, 2025 =
337 - Bug Fix: Fixed streaming fallback to properly display responses when streaming fails, preventing blank chat bubbles.
338 - New Feature: Added streaming test button to help users verify if streaming is compatible with their setup.
339
340 = 2.3.5 - August 6, 2025 =
341 - Redesigned chat transcript UI for a cleaner, more professional experience.
342 - Transcripts now show the page where the chat started and any links clicked.
343 - Added ability to select and delete transcripts directly from the header.
344
345 = 2.3.4 - July 30, 2025 =
346 - Fixed streaming compatibility issues with Cloudflare and WP Engine by implementing automatic fallback to regular chat when streaming is buffered.
347 - Enhanced email capture intents to use AI-generated conversational responses instead of hard-coded messages, allowing for more natural user interactions while maintaining the same functionality.
348
349 = 2.3.3 - July 29, 2025 =
350 - Improved streaming performance by fixing output buffering issues using enhanced flush logic.
351 - Added contextual awareness support via the new `data-mxchat-context` HTML attribute.
352 - Revamped license key management system with domain linking, deactivation, and real-time usage dashboard.
353 - Fixed transcript timestamp display to use WordPress site's local timezone correctly.
354
355 = 2.3.2 - July 24, 2025 =
356 - Added full support for OpenAI Assistants API via the new Assistant add-on.
357 - Improved email collection form performance and reliability with better loading states and timeout handling.
358 - Enhanced WooCommerce product labeling accuracy in WordPress import with improved URL matching.
359 - Fixed ACF field processing errors when handling WP_Post objects and relationship fields.
360
361 = 2.3.1 - July 20, 2025 =
362 - Enhanced hyperlink functionality to include mailto links, enabling email addresses in bot responses to be clickable.
363 - Added full support for the new MxChat Image Analysis add-on, allowing users to upload and analyze images directly in chat using OpenAI Vision and Grok APIs.
364 - Added message filtering hooks system for developers to customize prompts and responses without modifying core plugin files.
365
366 = 2.3.0 - July 13, 2025 =
367 - Added Grok-4 model support, the world's smartest AI model available.
368 - Added streaming response support for all Grok models (Grok-4, Grok-3, etc.), delivering real-time response generation for faster and smoother chat experiences.
369
370 = 2.2.9 - July 6, 2025 =
371 - Improved quick question UI: suggestions now collapse after user input and can be toggled with up/down icons
372 - Increased sitemap batch processing limit from 5 to 50 for faster indexing
373 - Expanded action similarity threshold range to support values from 10 to 95
374
375 = 2.2.8 - June 27, 2025 =
376 - Added brand new contextual awareness option that automatically provides chatbot access to current page content and URL for contextually relevant responses
377 - Enhanced WordPress knowledge base import to include Advanced Custom Fields (ACF) data for more comprehensive content training
378 - Major README structure update with improved formatting and visual presentation
379
380 = 2.2.7 =
381 - Fixed a bug that occured when deleting all pinecone records & added support for markdown hyperlinking in rate limit messages.
382
383 = 2.2.6 =
384 - Brand New Admin Debug Panel – Added a comprehensive frontend debug panel for administrators! You can now see retrieved documents, triggered actions, and other debug and setting information in real-time while testing your chatbot, making it easier than ever to fine-tune your bot's performance.
385 - Fixed Pinecone Single Entry Deletion – Resolved a bug that prevented individual entries from being properly deleted from Pinecone vector storage.
386 - Improved Pinecone UI Records Retrieval – Enhanced the Pinecone database panel with better record loading and display functionality for smoother management of your vector database.
387 - Fixed WordPress KB Entry Editing – Resolved an issue where editing knowledge base entries in the WordPress database wasn't working properly, ensuring seamless content management.
388
389 = 2.2.5 =
390 - Streaming Response Support – You can now enable streaming responses for OpenAI and Claude models. This delivers a faster, smoother chat experience for users by displaying replies in real-time as they’re generated.
391 - Slack Live Agent Fix – Resolved a minor bug that occasionally caused duplicate messages in Slack during live agent conversations.
392 - Pinecone UI Update – Fixed a UI display issue in the Pinecone database panel when using the TE3 model.
393
394 = 2.2.4 =
395 - Critical update to error when working with large databases in Pinecone.
396
397 = 2.2.3 =
398 - Various critical bug fixes that occured from the codebase refactoring.
399
400 = 2.2.2 =
401 - Enhanced Slack integration: live agent handoff now creates new Slack channels per conversation; agents can reply directly in channel to chat with website users.
402 - Major codebase refactoring for improved organization and optimization.
403 - Improved sitemap and PDF processing: added retry mechanism, display of failed pages/URLs, and manual batch processing button.
404 - Fixed Pinecone setting not toggling on for users who previously did not have the add-on.
405
406 = 2.2.1 =
407 - Added Claude Sonnet 4 and Claude Opus 4 chat models.
408 - Integrated Google Gemini embedding model (gemini-embedding-exp-03-07).
409 - Built Pinecone vector database support directly into core plugin.
410 - Removed dependency on separate Pinecone add-on.
411
412 = 2.2.0 =
413 - Added WordPress Content Importer for posts and pages.
414 - Implemented tabbed interface for knowledge base management.
415 - Added content filtering by type and knowledge base status.
416 - Added bulk import with real-time progress tracking.
417
418 = 2.1.9 =
419 - Added email notification feature for new chat sessions.
420 - Implemented pagination on transcripts page (50 per page) to improve performance.
421 - Fixed bug with Brave image search not returning images correctly from the API.
422 - Enhanced performance by changing chat transcripts to disable autoload.
423
424 = 2.1.7 =
425 - Fixed Pro activation issues when the plugin has been translated.
426 - Improved tab behavior to always default to the first tab.
427 - Major rework to rate limits: added custom rate limit timeframes and messages for each individual role.
428 - Fixed bug with Loops where manual list selection from dropdown was required for functionality.
429
430 = 2.1.6 =
431 - Added new AI models: GPT-4.1 and the complete suite of Grok 3 models.
432 - Updated AI service providers to use their official SVG logos for better visual representation.
433 - Fixed an issue where API key fields would try to autosave when no data was entered.
434 - Various other minor bug fixes for improved stability and performance.
435
436 = 2.1.5 =
437 - Added RTL Language support, allowing languages that align right to automatically do so in both chat input and AI responses.
438 - Improved error messaging for API calls in the frontend of the chatbot, and enhanced error messages when submitting sitemaps, URLs, and PDFs.
439 - Fixed an auto save issue that caused an error if no changes were made.
440 - Various other minor bug fixes for improved stability and performance.
441
442 = 2.1.4 =
443 - Added the ability to easily customize the "AI Agent" text displayed in the top bar for greater personalization.
444 - Fixed a bug where data scraping failed to retrieve all content from certain websites.
445 - Added HTML support in the intro message for richer customization.
446 - Resolved an issue where API input fields triggered browser autofill, improving user input accuracy.
447
448 = 2.1.3 =
449 - Added support for Google Gemini models: Gemini 2.0 Flash, Gemini 2.0 Flash-Lite, Gemini 1.5 Pro, and Gemini 1.5 Flash.
450 - Improved chat model selection UI for a more intuitive user experience.
451 - Redesigned embedding model selection UI for better clarity and usability.
452 - Enhanced error handling for sitemap submissions with more helpful user feedback.
453 - Fixed an issue in the knowledge database where editing entries erased or prevented changes to citation URLs.
454
455 = 2.1.2 =
456 - Rebranded intents page to "Actions" with a revamped UI, displaying pro/add-on requirements and brief descriptions.
457 - Added ability to toggle actions on/off without deleting; moved image generation action from pro to free tier.
458 - Introduced advanced knowledge base sync feature to pull in custom post data.
459
460 = 2.1.1 =
461 - Made Claude and X.AI API models available to all users.
462 - Improved API key management UI - only showing relevant API key fields based on selected models.
463 - Enhanced knowledge import interface with clear credit requirement warnings.
464 - Fixed embedding error notifications for better clarity.
465
466 = 2.1.0 =
467 - Fixed a bug impacting the header color in the output.
468 - Updated embedding error notification when submitting sitemaps or PDFs.
469 - Improved context extraction parser.
470
471 = 2.0.9 =
472 - Revamped UI on the main settings page to match the rest of the plugin.
473 - Added real-time updates for sitemap and PDF processing.
474 - Renamed "MxChat Intent Tester" add-on to "MxChat Similarity Tester".
475 - Various minor bug fixes and improvements.
476
477 = 2.0.8 =
478 - Minor bug fix impacting similarity adjustment.
479
480 = 2.0.7 =
481 - **Perplexity Integration Add-On** – Added Perplexity web search, integrated into intent management with a toolbar toggle.
482 - **Sonnet 3.7 Support** – Introduced Anthropic’s Claude Sonnet 3.7, the latest high-intelligence model.
483 - **Bug Fixes & Improvements** – Fixed title tag formatting in responses and tightened knowledge database similarity range to 20.
484
485 = 2.0.5 =
486 - **Auto-Expanding AI Instructions** – AI instructions text field now auto-expands to fit content.
487 - **Chat Transcripts UI & Export** – Redesigned chat transcripts UI and added Excel export feature.
488 - **Quick Questions Rebrand** – Renamed "Popular Questions" to "Quick Questions" with updated copy.
489 - **Security Enhancement** – Improved security to better prevent XSS attacks.
490 - **Intent Testing Add-On** – Integrated new Intent Tester add-on for enhanced chatbot performance.
491
492 = 2.0.4 =
493 - **Markdown Response Fix** – Resolved markdown formatting issues in the chatbot UI.
494 - **Agent Mode Customization** – Improved indicator text theme and background styling.
495 - **WooCommerce Core Extraction** – Moved WooCommerce features to the dedicated MxChat WooCommerce add-on.
496
497 = 2.0.3 =
498 - **Bug Fix:** Resolved issues preventing DeepSeek and Claude models from working correctly.
499 - **New:** Added integration for the MxChat Form Collection add-on (Pro only).
500 - **New:** Forms now display dynamically within the chat interface in real-time.
501 - **New:** Automatic intent handling for seamless form triggering.
502 - **Update:** Improved submission management with CSV export functionality.
503
504 = 2.0.2 =
505 - **Bug Fix:** Auto-sync now properly deletes posts/pages when enabled.
506 - **Update:** Theme customization moved to an add-on with live preview support.
507 - **New:** Added MxChat Moderation plugin to ban users by email or IP.
508
509 = 2.0.1 =
510 - **Bug Fix:** Fixed a DivisionByZeroError in sitemap processing that occurred when submitting an empty or malformed sitemap.
511 - **Bug Fix:** Resolved a similar DivisionByZeroError in PDF processing to prevent crashes when handling PDFs with 0 pages.
512
513 = 2.0.0 =
514 - **New UI & Branding:** Redesigned the entire plugin interface to align with the new MXChat brand for a modern and seamless experience.
515 - **Add-Ons System Introduced:** Added a dedicated Add-Ons page, allowing users to extend the plugin with optional features. Add-ons are completely optional and do not impact core functionality.
516 - **First Add-On Released – Pinecone DB Manager:** Now available for free! This add-on provides an intuitive interface for managing your Pinecone vector database directly within MXChat.
517
518 = 1.6.5 =
519 - Optimized knowledge database retrieval to prevent memory issues with large product databases (2000+ products)
520 - Fixed bug with tab switching control in chat interface
521
522 = 1.6.4 =
523 - Added chat notifications for improved user experience when chat persistence is enabled.
524 - Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
525 - Improved Slack integration: When a user requests a live agent, the last five messages from the conversation are now sent to Slack for better context.
526
527 = 1.6.4 =
528 - Added chat notifications for improved user experience when chat persistence is enabled.
529 - Made the entire plugin fully translatable, allowing compatibility with translation services like Loco Translate.
530 - Improved Slack integration: When a user requests a live agent, the last five messages from the conversation are now sent to Slack for better context.
531
532 = 1.6.3 =
533 - Added the new "Rate Limit by User Role" feature, replacing the previous rate limit for logged-in users.
534 - Introduced DeepSeek as a new AI service provider, with full support for their models.
535 - Integrated DeepSeek V3, enhancing chatbot natural language understanding and performance.
536
537 = 1.6.2 =
538 - Fixed a bug preventing the ability to save edits in the knowledge database.
539
540 = 1.6.0 =
541 - Redesigned knowledgebase UI for a cleaner, more user-friendly interface.
542 - Introduced auto-sync functionality for posts and pages, enabling automatic addition of new or updated content to the knowledgebase.
543 - Enhanced XML sitemap submission to prevent duplicate entries by checking and updating existing pages or adding new ones as needed.
544 - Reworked chatbot settings to enable individual autosave after updates, removing the need for manual saving.
545 - Fixed paragraph formatting in the chatbot UI to display line breaks and improve readability.
546
547 = 1.5.9 =
548 - Enhanced transcripts page with new analytics dashboard and improved UI
549 - Added support for X.AI's Grok model
550 - Improved message formatting to preserve paragraphs in intro messages
551 - Updated admin panel interface with better organization and styling
552 - Added better mobile responsiveness across admin screens
553
554 = 1.5.8 =
555 - Introduced a new setting to require an email address before starting a chat. When enabled, this email will be displayed at the top of the chat transcript if needed.
556
557 = 1.5.7 =
558 - Enhanced Complianz plugin integration to support the premium version and improve reliability.
559 - Fixed an issue where names were not appearing in chat transcripts for logged-in users.
560 - Added the ability to customize the title bar icon in the theme settings.
561 - Grouped intents by category in dropdown menus for better organization and usability.
562
563 = 1.5.6 =
564 - Improved "Add to Cart" and product recommendation intents for WooCommerce.
565 - Enhanced Brave Search intent for more accurate and structured results.
566 - Added an **Edit** button to the intent management section for easier adjustments.
567 - Fixed the Word document upload toolbar button for seamless functionality.
568
569 = 1.5.5 =
570 - Chat transcripts now display in newest-to-oldest order and are mobile responsive.
571 - Updated various setting texts with clearer descriptions for better usability.
572 - Fixed issue with rate limit not working properly.
573 - Added Word document upload to the frontend toolbar for direct chatbot interface use.
574 - Improved chatbot's contextual response accuracy.
575 - Major enhancements to "Add to Cart," "Checkout," and "Chat with PDF via URL" intents.
576
577 = 1.5.4 =
578 - Enhanced chat transcripts layout for improved readability, better formatting support (e.g., bold, italics), and inclusion of test agent names from **MxChat AI Agents**.
579 - Introduced **MxChat AI Agents**, now available free for Pro users for a limited time, providing a revolutionary way to test and deploy your chatbot.
580
581 = 1.5.3 =
582 - Major bug fix to the similarity threshold comparison which prevented the chatbot from finding relevant content.
583
584 = 1.5.2 =
585 - Enhanced checkout intent functionality to work more robustly, no longer requiring add-to-cart intent trigger.
586 - Fixed issue with send button not displaying properly on iPhone/iOS devices.
587 - Added admin control for similarity threshold matching to fine-tune relevant content results.
588
589 = 1.5.1 =
590 - Vastly improved the ability for the chatbot to give contextually relevant responses from the knowledge database.
591 - Fixed the issue with loops in the lead capture intent.
592 - Updated the PDF upload icon in the frontend chatbot UI to a clearer design, now showing a PDF file icon.
593 - Enhanced the order history intent, recommendation intent, and product card intent for more robust and contextually relevant responses.
594
595 = 1.5 =
596 - **Live Agent Transfer**: Seamless integration for live agent handoffs and AI chatbot switching.
597 - **PDF Toolbar**: Added PDF upload to the chatbot interface and knowledge base processing with cron jobs.
598
599 = 1.4.6 =
600 - **Product Recommendation Intent**: Added personalized product recommendations based on order history, cart contents, and trending items.
601 - **Custom Chatbot Icon**: Users can upload custom PNG icons for a more personalized chatbot appearance.
602 - **Codeblock Copy Button**: Introduced a copy button for codeblocks to simplify copying code snippets.
603 - **Expanded Popular Questions**: Increased flexibility by allowing more than the default three popular questions.
604 - **CSS Compatibility Fixes**: Improved chatbot CSS for better theme compatibility.
605
606 = 1.4.5 =
607 - **Fixed "Open Links in New Tab" Setting**: Resolved an issue where the setting to open links in a new tab was not functioning as expected.
608
609 = 1.4.4 =
610 - **Custom Rate Limits**: Set different rate limits for logged-in and logged-out users.
611 - **PDF Intent Enhancements**: Added customizable trigger, success, and error messages, plus a max PDF page limit setting.
612 - **Improved Flexibility**: Greater control over chatbot behavior and user interactions.
613
614 = 1.4.3 =
615 - **PDF Intent**: Added support for processing and analyzing PDF content via provided URLs using vector embeddings.
616 - **Compatibility Fix**: Fixed a rendering issue that prevented the chatbot from displaying in certain environments.
617
618 = 1.4.2 =
619 - **Fixed Knowledge Search**: Fixed a bug impacting the ability to search knowledge database information.
620
621 = 1.4.1 =
622 - **Fixed Intent Loading Issue**: Fixed a bug which prevented new intents from being shown on certain installs.
623
624 = 1.4 =
625 - **Customizable Sensitivity Threshold**: Added support for individual sensitivity thresholds on each intent, offering more precise control over intent recognition.
626 - **Enhanced Usability Improvements**: Introduced a "Delete All" button for quick knowledgebase management, resolved activation key UI issues to prevent unnecessary re-activation, and improved chatbot viewport scrolling for better visibility of longer responses.
627
628 = 1.3 =
629 - **Advanced Intent Recognition**: Introduced vector embedding for enhanced intent detection, improving chatbot responsiveness.
630 - **New Integrations**: Added **Brave Web Search**, **Brave Image Search**, and **DALL-E Image Generation** intents.
631 - **Security Update**: Minor update to unserialization handling for enhanced security.
632
633 = 1.2.1 =
634 - **Product Card Display**: Added a dynamic product card for WooCommerce users, showing product image, price, and an "Add to Cart" button triggered by product-related keywords.
635 - Enhanced **Popular Questions** and **Pre-Chat Message** functionalities for improved user engagement and streamlined chat initiation.
636
637 = 1.2 =
638 - Added **Popular Questions Buttons** with one free question and two available in the **Pro version**.
639 - Added **Inline Edit Button** to the Knowledge Database for easy content management.
640
641 = 1.1.9 =
642 - Added integration with Claude (Anthropic) API (Pro feature) for advanced conversational models like `Claude 3.5 Sonnet` and `Claude 3 Haiku`.
643
644 = 1.1.8 =
645 - Added integration with X.AI API (Pro feature) for advanced chat completions using models like `grok-beta`.
646 - Introduced new model selection dropdown that separates OpenAI and X.AI models, with X.AI models disabled for free users.
647 - Enhanced API key management, allowing users to input and manage both OpenAI and X.AI API keys in settings.
648
649 = 1.1.7 =
650 * Added chat session persistence option for users to maintain conversations across visits for up to 24 hours.
651 * Updated navigation tabs CSS and scripts to prevent conflicts with other plugins.
652 * Rate limit settings are now available to all users, offering better control over chat usage.
653
654 = 1.1.6 =
655 * Minor CSS update.
656
657 = 1.1.5 =
658 * Fixed error when users didn't have WooCommerce it would return "Error communicating with server".
659
660 == Upgrade Notice ==
661
662 = 2.6.2 =
663 Critical fix for large Pinecone databases and viewport cutoff issues when browser is zoomed or has bookmarks bar.
664
665 == License & Warranty ==
666
667 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.
668
669 This plugin is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
670
671 == Credits ==
672
673 This plugin incorporates the following third-party library:
674
675 - **Smalot PDF Parser**: Used for parsing and extracting text from PDF files. This library is developed by Smalot and distributed under the MIT License. For more details, visit the [Smalot PDF Parser GitHub repository](https://github.com/smalot/pdfparser).
676
677 This plugin was developed by [MxChat](https://mxchat.ai/).
678