Response Language setting fix: AI now correctly responds in the configured language. Recommended for all users.<\/p>","1.5.5":"
Major update: Complete Free\/Pro code separation, 50% smaller frontend JS, security hardening (CSS escaping, output sanitization), and unique prefix. Recommended for all users.<\/p>","1.5.2":"
Plugin Check compliance fixes and artificial limits removed. Recommended update.<\/p>","1.5.0":"
Major update: Gutenberg block, Abilities API, language auto-detect, OpenRouter. Recommended update for all users.<\/p>","1.4.0":"
Feature release: Web search integration (AI auto-searches the web when knowledge base is insufficient), cross-site embed support, PDF\/DOCX knowledge upload, vector embedding hybrid search, and updated AI model lists. Recommended update for all users.<\/p>","1.3.2":"
Security hardening: session ID header transport, XSS prevention via DOM API, rate-limited logging, and offline message dedup. Breaking change:<\/strong> GET requests no longer accept Enhanced rate limiting, server-side PDF export, and diagnostic option namespace migration ( Major feature release: Response caching, audit logs, conversion tracking, offline messages, and answer templates. Reduces API costs and adds business-critical Pro features. Recommended update for all users.<\/p>","1.2.23":" Sortable admin tables, knowledge base draft workflow, enhanced content extraction, and session management improvements. Recommended update for all users.<\/p>","1.2.22":" Improved AI chat accuracy with better default prompts. All feature prompts now customizable. Added raplsaich_system_prompt filter. Recommended update for all users.<\/p>","1.2.21":" Added knowledge base export support, budget management integration, and comprehensive debugging guide. Recommended update for Pro users.<\/p>","1.2.20":" Knowledge page prefill support for quick FAQ creation from analytics.<\/p>","1.2.18":" Security and performance improvements. Fixed message duplication bug affecting AI response accuracy. Recommended update for all users.<\/p>","1.2.5":" Security and code quality improvements. Recommended update for all users.<\/p>","1.0.0":" Initial release of Rapls AI Chatbot. Configure your AI provider API key to get started.<\/p>"},"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3493381,"resolution":"128x128","location":"assets","locale":""},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3493381,"resolution":"256x256","location":"assets","locale":""}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3493381,"resolution":"1544x500","location":"assets","locale":""},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3493381,"resolution":"772x250","location":"assets","locale":""}},"assets_blueprints":{},"all_blocks":{"rapls-ai-chatbot\/chatbot":{"$schema":"https:\/\/schemas.wp.org\/trunk\/block.json","apiVersion":3,"name":"rapls-ai-chatbot\/chatbot","version":"1.5.0","title":"AI Chatbot","category":"widgets","icon":"format-chat","description":"Embed an AI chatbot inline on your page.","keywords":["chat","ai","chatbot","assistant","rapls"],"supports":{"html":false,"multiple":false},"attributes":{"height":{"type":"string","default":"500px"},"theme":{"type":"string","default":""},"bot":{"type":"string","default":""}},"textdomain":"rapls-ai-chatbot","editorScript":"file:.\/editor.js","render":"file:.\/render.php"}},"tagged_versions":["1.5.6"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3493381,"resolution":"1","location":"assets","locale":""},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3493381,"resolution":"2","location":"assets","locale":""},"screenshot-3.png":{"filename":"screenshot-3.png","revision":3493381,"resolution":"3","location":"assets","locale":""},"screenshot-4.png":{"filename":"screenshot-4.png","revision":3493381,"resolution":"4","location":"assets","locale":""},"screenshot-5.png":{"filename":"screenshot-5.png","revision":3493381,"resolution":"5","location":"assets","locale":""},"screenshot-6.png":{"filename":"screenshot-6.png","revision":3493381,"resolution":"6","location":"assets","locale":""},"screenshot-7.png":{"filename":"screenshot-7.png","revision":3493381,"resolution":"7","location":"assets","locale":""}},"screenshots":{"1":"Dashboard \u2014 Overview of conversations, messages, and usage statistics with cost tracking","2":"Settings \u2014 Configure AI provider, model selection, and chat behavior","3":"Site Learning \u2014 Automatic content indexing and manual learning controls","4":"Knowledge Base \u2014 Custom Q&A management with priority levels and PDF\/DOCX upload","5":"Conversation History \u2014 View and manage all chat conversations","6":"Chatbot Widget \u2014 Clean, modern chat interface on your website","7":"Analytics Dashboard (Pro) \u2014 Conversation insights, satisfaction tracking, and FAQ analysis"},"jetpack_post_was_ever_published":false},"plugin_section":[],"plugin_tags":[2353,2364,229563,224606,194533],"plugin_category":[],"plugin_contributors":[253146],"plugin_business_model":[],"class_list":["post-292250","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-chatbot","plugin_tags-claude","plugin_tags-gemini","plugin_tags-openai","plugin_contributors-rapls","plugin_committers-rapls"],"banners":{"banner":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/banner-772x250.png?rev=3493381","banner_2x":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/banner-1544x500.png?rev=3493381","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/icon-128x128.png?rev=3493381","icon_2x":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/icon-256x256.png?rev=3493381","generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-1.png?rev=3493381","caption":"Dashboard \u2014 Overview of conversations, messages, and usage statistics with cost tracking"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-2.png?rev=3493381","caption":"Settings \u2014 Configure AI provider, model selection, and chat behavior"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-3.png?rev=3493381","caption":"Site Learning \u2014 Automatic content indexing and manual learning controls"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-4.png?rev=3493381","caption":"Knowledge Base \u2014 Custom Q&A management with priority levels and PDF\/DOCX upload"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-5.png?rev=3493381","caption":"Conversation History \u2014 View and manage all chat conversations"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-6.png?rev=3493381","caption":"Chatbot Widget \u2014 Clean, modern chat interface on your website"},{"src":"https:\/\/ps.w.org\/rapls-ai-chatbot\/assets\/screenshot-7.png?rev=3493381","caption":"Analytics Dashboard (Pro) \u2014 Conversation insights, satisfaction tracking, and FAQ analysis"}],"raw_content":"\n Rapls AI Chatbot add an AI chatbot to your site with OpenAI, Claude, Gemini, or OpenRouter. Includes site learning, knowledge base, and web search.<\/p>\n\n OpenAI:<\/strong>\n* GPT-5.2, GPT-5.1, GPT-5 series (Latest generation)\n* GPT-4.1 series (Long context, 1M tokens)\n* GPT-4o, GPT-4o-mini (Multimodal)\n* o1, o3, o4-mini (Reasoning models)<\/p>\n\n Anthropic Claude:<\/strong>\n* Claude Opus 4.6 (Most powerful)\n* Claude Sonnet 4.5 (Recommended \u2014 fast and powerful)\n* Claude Haiku 4.5 (Recommended \u2014 fastest)\n* Claude Opus 4.5, Opus 4.1, Sonnet 4, 3.7 Sonnet<\/p>\n\n Google Gemini:<\/strong>\n* Gemini 3 Pro\/Flash (Preview, latest)\n* Gemini 2.5 Pro\/Flash (Recommended)\n* Gemini 2.0 Flash (Stable)\n* Gemini 1.5 Pro\/Flash (Legacy)<\/p>\n\n OpenRouter:<\/strong>\n* Access 100+ models from multiple providers through a single API key<\/p>\n\n The dashboard provides an at-a-glance overview of your chatbot's activity:<\/p>\n\n AI Settings<\/strong> \u2014 Configure your AI provider, model, and API key. Enable vector search (RAG) with embedding provider. Set up MCP server with API key generation and Claude Desktop configuration example.<\/p>\n\n Chat Settings<\/strong> \u2014 Customize bot name, avatar (emoji or image), welcome messages (13 languages: English, Japanese, Chinese, Korean, Spanish, French, German, Portuguese, Italian, Russian, Arabic, Thai, Vietnamese), system prompt, response language, message history count, feedback buttons, and API quota error message. Advanced: context prompts for knowledge matching, Q&A format, and site learning; feature prompts for regeneration instructions, good\/bad example learning, and conversation summary.<\/p>\n\n Display Settings<\/strong> \u2014 Choose from 6 free themes (Default, Simple, Classic, Light, Minimal, Flat). Configure badge position (4-corner grid), margins, primary\/secondary colors, mobile display, Markdown rendering, typing indicator, maximum input length, page exclusion, footer text, and cross-site embed options (script or iframe).<\/p>\n\n Security Settings<\/strong> \u2014 Enable reCAPTCHA v3 with site key, secret key, and score threshold. Configure access control: consent strict mode, rate limiting, Cloudflare integration, reverse proxy trust, reCAPTCHA failure mode. View security diagnostics (read-only): allowed origins, trusted proxies, IP detection, API key status, WP Consent API, rate limiting, reCAPTCHA, SSL\/TLS, CSRF.<\/p>\n\n Data Management<\/strong> \u2014 Enable\/disable conversation history with configurable retention period. Import\/export settings (optionally including knowledge base). Reset all settings to defaults.<\/p>\n\n The plugin crawls and indexes your published content for context-aware AI responses:<\/p>\n\n With vector embedding enabled, hybrid search combines keyword matching (40%) and vector similarity (60%) for better retrieval accuracy.<\/p>\n\n The free version is fully functional with no artificial limits \u2014 you pay only your own AI API costs. An optional Pro add-on is available for business-oriented features.<\/p>\n\n What Free includes:<\/strong><\/p>\n\n What Pro adds:<\/strong><\/p>\n\n Learn more at raplsworks.com<\/a><\/p>\n\n This plugin connects to the following external third-party services. No data is sent to any service until you configure an API key and enable the feature in the plugin settings.<\/strong> Each service requires the site administrator to create an account and obtain API credentials. By using these services, you agree to their respective terms and privacy policies listed below.<\/p>\n\n Used when you select OpenAI as your AI provider. User messages and optionally site content are sent to generate AI responses.<\/p>\n\n Used when you select Anthropic Claude as your AI provider. User messages and optionally site content are sent to generate AI responses.<\/p>\n\n Used when you select Google Gemini as your AI provider. User messages and optionally site content are sent to generate AI responses.<\/p>\n\n Used when you select OpenRouter as your AI provider. OpenRouter is a unified API gateway that routes requests to various AI models.<\/p>\n\n Used only if you enable reCAPTCHA in the plugin settings for spam protection. The visitor's IP address and interaction data are sent to Google for verification.<\/p>\n\n Used only if you enable the LINE integration via the Pro add-on. Connects to the LINE Messaging API for chatbot-to-LINE messaging.<\/p>\n\n The plugin includes an optional embed loader script ( You can disable these features in the plugin settings:\n* Conversation history saving\n* Site content crawling\/learning\n* Google reCAPTCHA verification\n* Web search<\/p>\n\n When conversation history is enabled, the plugin stores:\n* Chat messages (user and AI responses)\n* Session identifiers\n* Page URLs where chats occurred\n* Hashed IP addresses (SHA-256, not reversible)\n* Timestamps<\/p>\n\n Conversation data is automatically deleted after the configured retention period (default: 90 days). Administrators can manually delete conversations at any time.<\/p>\n\n Site administrators can:\n* View all conversation history\n* Delete individual or all conversations\n* Export settings (does not include conversation data)\n* Disable history saving entirely= Developer Information =<\/p>\n\n The plugin provides hooks and filters for customization:<\/p>\n\n The plugin registers REST API endpoints under the Session authentication:<\/strong> Pass the session ID via the Free:<\/strong><\/p>\n\n The Pro add-on registers additional endpoints for analytics, scenarios, LINE, and more. See the Pro documentation for details.<\/p>\n\n Extension settings are stored under the The plugin creates the following database tables:<\/p>\n\n When uninstalled with \"Delete data on uninstall\" enabled, the plugin removes all database tables, options, and transients. Without this setting, data is preserved for re-installation.<\/p>\n\n Release ZIPs are CI-verified for packaging correctness. Report any issues via the support forum.<\/p>\n\n You'll need an API key from at least one AI provider:<\/p>\n\n The plugin provides 7 MCP tools: get_site_info, search_content, get_knowledge, manage_knowledge, get_conversations, get_settings, search_products (Pro).<\/p>\n\n\n Each provider has different strengths:\n* OpenAI GPT-4o-mini<\/strong> \u2014 Best balance of cost and performance for most use cases\n* Claude Sonnet 4.5<\/strong> \u2014 Excellent for nuanced, helpful responses\n* Gemini 2.5 Flash<\/strong> \u2014 Fast and cost-effective, good for high-volume sites\n* OpenRouter<\/strong> \u2014 Access to 100+ models from multiple providers with a single API key<\/p><\/dd>\n The plugin itself is free. You pay for AI API usage directly to your chosen provider. Typical costs:\n* GPT-4o-mini: ~$0.15\/1M input tokens, ~$0.60\/1M output tokens\n* Claude Haiku 4.5: ~$0.80\/1M input tokens, ~$4.00\/1M output tokens\n* Gemini 2.5 Flash: ~$0.15\/1M input tokens, ~$0.60\/1M output tokens<\/p><\/dd>\n You can configure multiple API keys, but only one provider is active at a time. You can switch between providers in the settings.<\/p><\/dd>\n The plugin crawls your published content and creates a searchable index. When users ask questions, relevant content is included in the AI context for accurate, site-specific responses. With vector embedding enabled, hybrid search combines keyword matching (40%) and vector similarity (60%) for better retrieval.<\/p><\/dd>\n When the knowledge base and site content don't have a sufficient answer, the AI automatically searches the web using each provider's built-in capability (OpenAI web_search_preview, Claude web_search, Gemini google_search). Web sources are shown with a globe icon.<\/p><\/dd>\n?session_id=<\/code> \u2014 use the X-RAPLSAICH-Session<\/code> header instead. Recommended update for all users.<\/p>","1.3.1":"raplsaich_diag_*<\/code>). Recommended update for all users.<\/p>","1.3.0":"Key Features<\/h4>\n\n
\n
Supported AI Models<\/h4>\n\n
Dashboard<\/h4>\n\n
\n
Settings (5 Tabs)<\/h4>\n\n
Knowledge Base<\/h4>\n\n
\n
Site Learning<\/h4>\n\n
\n
Free vs Pro<\/h4>\n\n
\n
\n
\n
External Services<\/h3>\n\n
1. OpenAI (GPT models) \u2014 AI Provider<\/h4>\n\n
\n
2. Anthropic (Claude models) \u2014 AI Provider<\/h4>\n\n
\n
3. Google (Gemini models) \u2014 AI Provider<\/h4>\n\n
\n
4. OpenRouter \u2014 AI Provider<\/h4>\n\n
\n
5. Google reCAPTCHA v3 (Optional)<\/h4>\n\n
\n
6. LINE Messaging API (Pro Add-on, Optional)<\/h4>\n\n
\n
Cross-Site Embed<\/h4>\n\n
embed-loader.js<\/code>) for embedding the chatbot on external websites via an iframe. This script does not load any external CDN resources or third-party scripts \u2014 it creates an iframe pointing back to your own WordPress site. All data processing occurs on your server.<\/p>\n\nData Transmitted to External Services<\/h4>\n\n
\n
Data Storage<\/h4>\n\n
\n
User Controls<\/h4>\n\n
Privacy<\/h3>\n\n
Data Collected<\/h4>\n\n
Data Retention<\/h4>\n\n
User Rights<\/h4>\n\n
Available Filters<\/h4>\n\n
\n
raplsaich_system_prompt<\/code> \u2014 Modify the system prompt sent to AI<\/li>\nraplsaich_context<\/code> \u2014 Modify the context from site learning<\/li>\nraplsaich_ai_response<\/code> \u2014 Filter the AI response before display<\/li>\nraplsaich_chatbot_enabled<\/code> \u2014 Control chatbot visibility programmatically<\/li>\nraplsaich_allowed_origins<\/code> \u2014 Add allowed origin hosts for same-origin check<\/li>\nraplsaich_chat_response_data<\/code> \u2014 Filter chat response data before returning to client<\/li>\nraplsaich_gpt5_token_multiplier<\/code> \u2014 GPT-5 reasoning token multiplier (default: 4, range: 1-8)<\/li>\n<\/ul>\n\nExample: Custom System Prompt<\/h4>\n\n
add_filter( 'raplsaich_system_prompt', function( $prompt, $settings ) {\n return $prompt . \"\\n\\nAlways end responses with a friendly emoji.\";\n}, 10, 2 );\n<\/code><\/pre>\n\nExample: Conditionally Hide Chatbot<\/h4>\n\n
add_filter( 'raplsaich_chatbot_enabled', function( $enabled ) {\n \/\/ Hide on checkout page\n if ( is_page( 'checkout' ) ) {\n return false;\n }\n return $enabled;\n} );\n<\/code><\/pre>\n\nREST API Endpoints<\/h4>\n\n
rapls-ai-chatbot\/v1<\/code> namespace:<\/p>\n\nX-RAPLSAICH-Session<\/code> HTTP header (recommended). When the header is present, any session_id in the request body is ignored (prevents APM\/WAF body-logging leakage). Query string parameters (?session_id=...<\/code>) are not<\/strong> accepted for GET requests to prevent session leakage in server access logs.<\/p>\n\n\n
GET \/rapls-ai-chatbot\/v1\/session<\/code> \u2014 Get or create a chat session<\/li>\nPOST \/rapls-ai-chatbot\/v1\/chat<\/code> \u2014 Send a message and receive AI response<\/li>\nGET \/rapls-ai-chatbot\/v1\/history\/{session_id}<\/code> \u2014 Get conversation history<\/li>\nPOST \/rapls-ai-chatbot\/v1\/feedback<\/code> \u2014 Rate a response (thumbs up\/down)<\/li>\nPOST \/rapls-ai-chatbot\/v1\/regenerate<\/code> \u2014 Regenerate AI response<\/li>\nGET \/rapls-ai-chatbot\/v1\/message-limit<\/code> \u2014 Check message limits<\/li>\nPOST \/rapls-ai-chatbot\/v1\/lead<\/code> \u2014 Submit lead form<\/li>\nGET \/rapls-ai-chatbot\/v1\/lead-config<\/code> \u2014 Lead form configuration<\/li>\n<\/ul>\n\nSettings Architecture<\/h4>\n\n
extensions<\/code> key in raplsaich_settings<\/code>. For backward compatibility, the legacy pro_features<\/code> key is read as a fallback but all new settings are written to extensions<\/code>.<\/p>\n\nDatabase Tables<\/h4>\n\n
\n
{prefix}_aichat_conversations<\/code> \u2014 Chat sessions<\/li>\n{prefix}_aichat_messages<\/code> \u2014 Individual messages with token tracking<\/li>\n{prefix}_aichat_index<\/code> \u2014 Site learning content index<\/li>\n{prefix}_aichat_knowledge<\/code> \u2014 Custom knowledge base entries<\/li>\n{prefix}_aichat_leads<\/code> \u2014 Lead capture data<\/li>\n<\/ul>\n\nUninstallation<\/h4>\n\n
Development<\/h3>\n\n
Credits<\/h4>\n\n
\n
\n
rapls-ai-chatbot<\/code> folder to the \/wp-content\/plugins\/<\/code> directory<\/li>\nAPI Key Setup<\/h4>\n\n
\n
MCP Server Setup<\/h4>\n\n
\n
\n
Which AI provider should I choose?<\/h3><\/dt>\n
How much does it cost to use?<\/h3><\/dt>\n
Can I use multiple AI providers?<\/h3><\/dt>\n
How does Site Learning work?<\/h3><\/dt>\n
How does Web Search work?<\/h3><\/dt>\n
What is the MCP Server?<\/h3><\/dt>\n