Selvakumar Duraipandian

<p><strong>The Problem:</strong><br />
WordPress outputs HTML that’s difficult for AI systems to parse accurately. Important content gets lost in markup, scripts, and styling.</p>
<p><strong>The Solution:</strong><br />
AgentMark provides clean Markdown versions of your posts and pages through simple <code>.md</code> endpoints, plus an industry-standard <code>llms.txt</code> file that helps AI agents discover your best content.</p>
<h4>Use Cases</h4>
<ul>
<li><strong>AI Search Engines</strong>: Help tools like Perplexity, Claude, and ChatGPT cite your content accurately</li>
<li><strong>RAG Systems</strong>: Enable companies to build knowledge bases from your public content</li>
<li><strong>Documentation</strong>: Provide developers with clean, parseable API docs</li>
<li><strong>Content Syndication</strong>: Share articles in a universal, lightweight format</li>
<li><strong>Knowledge Graphs</strong>: Help semantic web tools understand your site structure</li>
</ul>
<h4>Key Features</h4>
<ul>
<li><strong>Zero Configuration</strong>: Works out of the box with sensible defaults</li>
<li><strong>Markdown Endpoints</strong>: Access any post/page as Markdown by adding <code>.md</code> to the URL</li>
<li><strong>llms.txt Standard</strong>: Auto-generates discovery file for AI agents</li>
<li><strong>YAML Front Matter</strong>: Rich metadata for better AI understanding</li>
<li><strong>Flexible</strong>: Control which post types are exposed</li>
<li><strong>Performance</strong>: Built-in caching and rate limiting</li>
<li><strong>Privacy-Focused</strong>: Per-post control over AI access</li>
<li><strong>Standards-Compliant</strong>: Follows emerging llms.txt specification</li>
</ul>
<h4>Business Value</h4>
<ul>
<li><strong>Future-Proof</strong>: Position your content for the AI-driven web</li>
<li><strong>Zero Cost</strong>: No API fees or external dependencies</li>
<li><strong>SEO Boost</strong>: Alternate content formats can improve discoverability</li>
<li><strong>Competitive Edge</strong>: Early adoption of AI-friendly formats</li>
<li><strong>Analytics</strong>: Track which content AI agents prefer</li>
</ul>


AgentMark

AI-Ready Markdown Endpoints & llms.txt discovery for WordPress. Clean, machine-readable content for AI agents and RAG systems.

mobalabkashima

<p>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.</p>
<p><strong>Key Features:</strong></p>
<ul>
<li><strong>Direct Amazon Bedrock Integration</strong>: Connects directly to Amazon Bedrock Knowledge Bases without external servers</li>
<li><strong>Automatic Content Synchronization</strong>: Automatically syncs WordPress posts and pages to Amazon Bedrock when content is created, updated, or deleted</li>
<li><strong>Real-time Chat Interface</strong>: Provides a chat widget for visitors to interact with your content using AI</li>
<li><strong>Comprehensive Admin Interface</strong>: Four dedicated admin pages for configuration and content management</li>
<li><strong>AWS Security</strong>: Uses AWS Signature Version 4 authentication for secure API communication</li>
<li><strong>Content Management</strong>: Track sync status and manage which content is synchronized to Amazon Bedrock</li>
</ul>
<p><strong>How It Works:</strong></p>
<ol>
<li>Configure your AWS credentials and Amazon Bedrock Knowledge Base in the plugin settings</li>
<li>New WordPress posts and pages are automatically synchronized to Amazon Bedrock when saved or deleted</li>
<li>Existing content can be synchronized using the export function in the Content Management page</li>
<li>Visitors can use the chat interface to ask questions about your content</li>
<li>Amazon Bedrock retrieves relevant content and generates intelligent responses using your WordPress data</li>
</ol>
<p><strong>Requirements:</strong></p>
<ul>
<li>AWS account with Amazon Bedrock access</li>
<li>Amazon Bedrock Knowledge Base configured</li>
<li>Valid AWS credentials (Access Key ID and Secret Access Key)</li>
</ul>
<p><strong>Demo:</strong></p>
<p>See the plugin in action: <a href="https://wp-rag-demo.mobalab.net/ask-rag-chat-for-amazon-bedrock/" rel="nofollow ugc">Live Demo</a></p>
<h3>Troubleshooting</h3>
<p><strong>Plugin Installation & Setup Issues</strong></p>
<h4>Plugin activation fails</h4>
<ol>
<li>Ensure your WordPress version meets the minimum requirement (6.6+)</li>
<li>Check that your PHP version is 7.4 or higher</li>
<li>Verify there are no plugin conflicts by temporarily deactivating other plugins</li>
</ol>
<h4>The chat interface doesn’t appear on my page</h4>
<ol>
<li>Make sure you’ve inserted the shortcode <code>[rag_chat_ab_chat]</code> in the correct location</li>
<li>Check that the plugin is activated</li>
<li>Verify your AWS credentials are correctly configured in the plugin settings</li>
</ol>
<p><strong>Content Synchronization Issues</strong></p>
<h4>Content sync is failing</h4>
<ol>
<li>Verify your AWS credentials have the correct permissions</li>
<li>Check that your Knowledge Base ID and Data Source ID are correct</li>
<li>Ensure your Knowledge Base has a “Custom” type data source</li>
<li>For existing content, use the “Export Posts and Pages to Amazon Bedrock” feature on the Content Management page</li>
</ol>
<h4>Export operation times out</h4>
<p>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:</p>
<ol>
<li>Export content in smaller batches by selecting specific date ranges</li>
<li>Consider increasing your PHP execution time limit if you have server access</li>
<li>Contact your hosting provider if timeout issues persist</li>
<li>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 <a href="https://tally.so/r/3jjoga" rel="nofollow ugc">https://tally.so/r/3jjoga</a> for more information about our bulk export solution</li>
</ol>
<p><strong>AWS Authentication & Permissions</strong></p>
<h4>AWS permission errors</h4>
<ol>
<li>Double-check all required IAM permissions are granted to your user</li>
<li>Verify your AWS Access Key ID and Secret Access Key are correct</li>
<li>Ensure your AWS account has access to Amazon Bedrock in the selected region</li>
<li>Check the AWS CloudTrail logs for detailed error information</li>
</ol>
<h4>AWS Marketplace subscription error</h4>
<p>If you encounter “Model access is denied” with “aws-marketplace:ViewSubscriptions” permission errors:</p>
<ol>
<li>Your IAM user needs the <code>aws-marketplace:ViewSubscriptions</code> permission</li>
<li>Add this permission to your IAM user’s policy</li>
<li>Wait 15 minutes after fixing the permissions before trying again</li>
<li>This is required for AWS Marketplace subscription completion</li>
</ol>
<p><strong>Model Access & Configuration</strong></p>
<h4>Model use case details required</h4>
<p>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”:</p>
<ol>
<li>Anthropic requires use case details before using their models</li>
<li>Fill out the Anthropic use case details form in your AWS console</li>
<li>Wait 15 minutes after submitting before trying again</li>
<li>See the AWS documentation: https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html</li>
</ol>
<h4>Inference profile required error</h4>
<p>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”:</p>
<ol>
<li>Some models require using inference profiles instead of direct model invocation</li>
<li>Use the ID or ARN of an inference profile that contains the model</li>
<li>Configure inference profiles in your Amazon Bedrock settings</li>
<li>See the AWS documentation: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html</li>
</ol>
<h4>Chat responses are not working</h4>
<ol>
<li>Verify that your AWS region is correct in the plugin settings</li>
<li>Check that your Knowledge Base contains synchronized content</li>
<li>Ensure your IAM user has <code>bedrock:RetrieveAndGenerate</code> permissions</li>
<li>Try asking questions related to your synchronized content</li>
</ol>
<h3>External services</h3>
<p>This plugin uses the following Amazon Bedrock API endpoints provided by Amazon Web Services, Inc.:</p>
<ul>
<li>PUT https://bedrock-agent.{$region}.amazonaws.com/knowledgebases/{$knowledge_base_id}/datasources/{$data_source_id}
<ul>
<li>Called when a post or page is created or updated.</li>
<li>Used to add / update content on Amazon Bedrock.</li>
<li>The whole content (post or page) is sent.</li>
</ul>
</li>
<li>POST https://bedrock-agent.{$region}.amazonaws.com/knowledgebases/{$knowledge_base_id}/datasources/{$data_source_id}/documents/deleteDocuments
<ul>
<li>Called when a post is deleted or moved to trash.</li>
<li>Used to delete content from Amazon Bedrock.</li>
<li>Only the post / page ID is sent.</li>
</ul>
</li>
<li>POST https://bedrock-agent-runtime.{$region}.amazonaws.com/retrieveAndGenerate
<ul>
<li>Called when a visitor asks a question.</li>
<li>Used to generate responses using Amazon Bedrock’s AI.</li>
<li>The query that the user enters is sent.</li>
<li>The response contains a session ID, and it will be send to this endpoint in the subsequent requests along with the query.</li>
</ul>
</li>
</ul>
<p>Please see the following links for more information about Amazon Web Services:</p>
<ul>
<li><a href="https://aws.amazon.com/service-terms/" rel="nofollow ugc">AWS Service Terms</a></li>
<li><a href="https://aws.amazon.com/privacy/" rel="nofollow ugc">AWS Privacy</a></li>
</ul>
<h3>Related Projects</h3>
<p>This plugin is based on <strong>WP RAG</strong> (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.</p>


RAG Chat for Amazon Bedrock

Integrate WordPress content with Amazon Bedrock Knowledge Bases to create an intelligent RAG (Retrieval-Augmented Generation) chatbot system.

AgentMark vs RAG Chat for Amazon Bedrock