Fast RAGbot vs RAG Chat for Amazon Bedrock

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

RAG Chat for Amazon Bedrock is a WordPress plugin that seamlessly integrates your WordPress content with Amazon Bedrock Knowledge Bases to create an intelligent RAG (Retrieval-Augmented Generation) chatbot system. Key Features: Direct Amazon Bedrock Integration: Connects directly to Amazon Bedrock Knowledge Bases without external servers Automatic Content Synchronization: Automatically syncs WordPress posts and pages to Amazon Bedrock when content is created, updated, or deleted Real-time Chat Interface: Provides a chat widget for visitors to interact with your content using AI Comprehensive Admin Interface: Four dedicated admin pages for configuration and content management AWS Security: Uses AWS Signature Version 4 authentication for secure API communication Content Management: Track sync status and manage which content is synchronized to Amazon Bedrock How It Works: Configure your AWS credentials and Amazon Bedrock Knowledge Base in the plugin settings New WordPress posts and pages are automatically synchronized to Amazon Bedrock when saved or deleted Existing content can be synchronized using the export function in the Content Management page Visitors can use the chat interface to ask questions about your content Amazon Bedrock retrieves relevant content and generates intelligent responses using your WordPress data Requirements: AWS account with Amazon Bedrock access Amazon Bedrock Knowledge Base configured Valid AWS credentials (Access Key ID and Secret Access Key) Demo: See the plugin in action: Live Demo Troubleshooting Plugin Installation & Setup Issues Plugin activation fails Ensure your WordPress version meets the minimum requirement (6.6+) Check that your PHP version is 7.4 or higher Verify there are no plugin conflicts by temporarily deactivating other plugins The chat interface doesn’t appear on my page Make sure you’ve inserted the shortcode [rag_chat_ab_chat] in the correct location Check that the plugin is activated Verify your AWS credentials are correctly configured in the plugin settings Content Synchronization Issues Content sync is failing Verify your AWS credentials have the correct permissions Check that your Knowledge Base ID and Data Source ID are correct Ensure your Knowledge Base has a “Custom” type data source For existing content, use the “Export Posts and Pages to Amazon Bedrock” feature on the Content Management page Export operation times out If you have many posts and pages, “Export Posts and Pages to Amazon Bedrock” may take a long time and cause timeout errors depending on your PHP settings. To reduce the risk of timeout: Export content in smaller batches by selecting specific date ranges Consider increasing your PHP execution time limit if you have server access Contact your hosting provider if timeout issues persist For large-scale exports, we offer a dedicated bulk export PHP script that runs independently on your server and can handle large volumes of content without web browser timeout limitations. Contact us at https://tally.so/r/3jjoga for more information about our bulk export solution AWS Authentication & Permissions AWS permission errors Double-check all required IAM permissions are granted to your user Verify your AWS Access Key ID and Secret Access Key are correct Ensure your AWS account has access to Amazon Bedrock in the selected region Check the AWS CloudTrail logs for detailed error information AWS Marketplace subscription error If you encounter “Model access is denied” with “aws-marketplace:ViewSubscriptions” permission errors: Your IAM user needs the aws-marketplace:ViewSubscriptions permission Add this permission to your IAM user’s policy Wait 15 minutes after fixing the permissions before trying again This is required for AWS Marketplace subscription completion Model Access & Configuration Model use case details required If you encounter an error like “Model use case details have not been submitted for this account. Fill out the Anthropic use case details form before using the model”: Anthropic requires use case details before using their models Fill out the Anthropic use case details form in your AWS console Wait 15 minutes after submitting before trying again See the AWS documentation: https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html Inference profile required error If you get an error like “Invocation of model ID anthropic.claude-haiku-4-5-20251001-v1:0 with on-demand throughput isn’t supported. Retry your request with the ID or ARN of an inference profile”: Some models require using inference profiles instead of direct model invocation Use the ID or ARN of an inference profile that contains the model Configure inference profiles in your Amazon Bedrock settings See the AWS documentation: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html Chat responses are not working Verify that your AWS region is correct in the plugin settings Check that your Knowledge Base contains synchronized content Ensure your IAM user has bedrock:RetrieveAndGenerate permissions Try asking questions related to your synchronized content External services This plugin uses the following Amazon Bedrock API endpoints provided by Amazon Web Services, Inc.: PUT https://bedrock-agent.{$region}.amazonaws.com/knowledgebases/{$knowledge_base_id}/datasources/{$data_source_id} Called when a post or page is created or updated. Used to add / update content on Amazon Bedrock. The whole content (post or page) is sent. POST https://bedrock-agent.{$region}.amazonaws.com/knowledgebases/{$knowledge_base_id}/datasources/{$data_source_id}/documents/deleteDocuments Called when a post is deleted or moved to trash. Used to delete content from Amazon Bedrock. Only the post / page ID is sent. POST https://bedrock-agent-runtime.{$region}.amazonaws.com/retrieveAndGenerate Called when a visitor asks a question. Used to generate responses using Amazon Bedrock’s AI. The query that the user enters is sent. The response contains a session ID, and it will be send to this endpoint in the subsequent requests along with the query. Please see the following links for more information about Amazon Web Services: AWS Service Terms AWS Privacy Related Projects This plugin is based on WP RAG (https://github.com/mobalab/wp-rag), which provides RAG functionality using external servers and OpenAI’s APIs. RAG Chat for Amazon Bedrock offers a different approach by integrating directly with Amazon Bedrock Knowledge Bases for users who prefer AWS-native solutions.