Kantari Samy

<p>Vexalyn AI Summary adds a sidebar panel to the Gutenberg editor that lets you generate a summary of your article with a single click using Ollama — either self-hosted or via Ollama Cloud.</p>
<p>Once generated, the summary is instantly inserted at the top of your article as native Gutenberg blocks (group, heading, paragraphs, signature). You can validate, cancel, or regenerate before publishing.</p>
<p><strong>Features</strong></p>
<ul>
<li>Works with Ollama Cloud or any self-hosted Ollama instance</li>
<li>Choose the model from a live list fetched from your Ollama API</li>
<li>Fully customizable prompt with built-in examples</li>
<li>Summary inserted as native blocks: group or details > heading/summary > content > signature</li>
<li>Choice between Group block and Details/Summary block for the summary wrapper</li>
<li>Generate a dedicated excerpt with configurable word count, review/edit/validate flow</li>
<li>Visual highlight of inserted blocks while awaiting validation</li>
<li>Test your connection and your prompt directly from the settings page</li>
<li>CSS class on the group block is configurable for easy theme styling</li>
<li>Developer filter to customize the thinking messages displayed during generation</li>
</ul>
<p><strong>Requirements</strong></p>
<ul>
<li>An Ollama instance (local or remote) or an Ollama Cloud account</li>
</ul>
<p>No build step required. No Composer, no npm.</p>
<h3>External services</h3>
<p>This plugin connects to the Ollama API to generate AI summaries using language models.</p>
<p>Ollama can be used in two ways:</p>
<ul>
<li><strong>Cloud</strong>: your requests are sent to Ollama’s hosted infrastructure at https://api.ollama.com — no local installation required, an API key is needed.</li>
<li><strong>Self-hosted</strong>: Ollama runs entirely on your own server or machine; no data ever leaves your infrastructure.</li>
</ul>
<p><strong>Data sent to the Ollama API:</strong></p>
<ul>
<li>Article content entered by the user for summary generation</li>
<li>Selected model name</li>
<li>Configuration parameters (prompt)</li>
</ul>
<p><strong>When:</strong> only when the user manually clicks the “Generate summary” button — no automatic or background processing occurs.</p>
<p>No tracking of any kind is performed by this plugin. Summary generation is always triggered by an explicit user action.</p>
<p>Privacy policy: https://ollama.com/privacy<br />
Terms of service: https://ollama.com/terms</p>


Vexalyn AI Summary for Ollama

Generate article summaries with Ollama AI directly from the Gutenberg editor sidebar.

carmelosantana

<p>Easily draft a post or page from any conversation. Dynamically create new content on the fly or with remote resources collected via <code>agents</code>. <strong>Alpaca Bot</strong> offers a familiar chat interface on both desktop and mobile. You can expect a seamless chat experience on any device!</p>
<p>An <a href="https://github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> instance is required. <a href="https://github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> makes it incredibly easy to self-host large language models locally or in the cloud.</p>
<h3>Features</h3>
<ul>
<li>Chose to store conversation history <strong>privately</strong> in your <code>wp_</code> database or not at all.</li>
<li>Use <code>[alpacabot_agent]</code> to execute tasks on your behalf, generate dynamic content and more.</li>
<li>Chat with dozens of pre-trained LLMs or <a href="https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings" rel="nofollow ugc">train your own</a>.</li>
<li>Switch conversational model on the fly.</li>
<li>Create your own custom <a href="https://github.com/ollama/ollama/blob/main/docs/modelfile.md#system" rel="nofollow ugc">system messages</a> for highly predictable or formatted responses.</li>
</ul>
<h3>Usage</h3>
<h4>Text Completion</h4>
<p>You have two options to communicate with your AI models;</p>
<ol>
<li>Click <strong>Alpaca Bot</strong> found in the admin menu, below Dashboard and above Posts.</li>
<li><strong>Use the shortcode</strong> <code>[alpacabot]</code> to generate a response within any post or page.</li>
</ol>
<h4>Agents</h4>
<p>Use the <code>[alpacabot_agent]</code> shortcode to execute tasks on your behalf. Agents are a powerful way to empower your AI models to perform tasks on your behalf.</p>
<p>For example, you can use the <code>[alpacabot_agent]</code> shortcode to retrieve content from a remote source. <code>[alpacabot_agent]</code>s can interact directly with your models and help summarize a webpage or rewrite content.</p>
<p>Example</p>
<p>Basic webpage summarization:</p>
<pre><code>[alpacabot_agent name=summarize model=tinyllama url=https://example.com/]
</code></pre>
<h3>Shortcodes</h3>
<h4><code>[alpacabot]</code> – Chat with Alpaca Bot</h4>
<p><em>Chat with Alpaca Bot from any post or page.</em></p>
<p>Attributes</p>
<ul>
<li><code>model</code> – The model to use for the text generation. <em>(optional)</em></li>
<li><code>system</code> – Specifies the <a href="https://github.com/ollama/ollama/blob/main/docs/modelfile.md#system" rel="nofollow ugc">system message</a> that will be set in the template. <em>(optional)</em></li>
</ul>
<h4><code>[alpacabot_agent]</code> – Execute tasks on your behalf</h4>
<p><em>Execute tasks via Agents.</em></p>
<p>Attributes</p>
<p>The following are core attributes that are supported by all agents.</p>
<ul>
<li><code>name</code> – The agent to execute.</li>
</ul>
<p>Agent’s communicating with <a href="https:/github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> support <code>[alpacabot]</code> attributes.</p>
<h4>Caching</h4>
<p>Requests can be cached by setting the <code>cache</code> attribute. <code>cache</code> supports short and long term options.</p>
<p>By default responses are cached to the current post or page.</p>
<p>Transient</p>
<p>Numeric values are treated as seconds and will cache the response for the specified duration.</p>
<ul>
<li><code>cache=60</code> – Cache the response for 60 seconds.</li>
<li><code>cache=3600</code> – Cache the response for 1 hour.</li>
</ul>
<p>Post Meta</p>
<p>This is useful for caching responses permanently and associating them with a specific post or page.</p>
<ul>
<li><code>cache=postmeta</code> – Cache to current post or page.</li>
</ul>
<p>Option</p>
<p>Use WordPress option storage to cache permanently but not associated with a specific post or page.</p>
<p>This can be useful for sharing responses across multiple pages.</p>
<ul>
<li><code>cache=option</code> – Cache to WordPress options.</li>
</ul>
<p>Disable</p>
<p>The following values can disable caching.</p>
<ul>
<li><code>cache=0</code> – Disable caching.</li>
<li><code>cache=disable</code> – Disable caching.</li>
<li><code>cache=false</code> – Disable caching.</li>
</ul>
<h3>Core Agents</h3>
<p>The following are core agents that are provided by the <strong>Alpaca Bot</strong> plugin.</p>
<h4><code>get</code></h4>
<p>Retrieve content from a remote source.</p>
<p>Attributes</p>
<ul>
<li><code>url</code> – The URL to retrieve content from.</li>
</ul>
<h4><code>summarize</code></h4>
<p>Summarize remote content.</p>
<p>Attributes</p>
<ul>
<li><code>url</code> – The URL to summarize.</li>
<li><code>length</code> – Describe the length of the summary.</li>
<li><code>content</code> – The type of content we want to summarize.</li>
</ul>
<h3>Support</h3>
<p>If you need help or have questions, please join our <a href="https://discord.gg/vWQTHphkVt" rel="nofollow ugc">Discord</a> community.</p>
<p>Premium support and video calls are available to our <a href="https://www.patreon.com/carmelosantana" rel="nofollow ugc">Patreon</a> subscribers. We can help setup your <a href="https://github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> instance, troubleshoot issues, demonstrate shortcode functionality and more.</p>
<p>Patreon’s also receive;</p>
<ul>
<li>Access to our hosted <a href="https:/github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> instances.</li>
<li>Priority feature requests.</li>
<li>Early access to new features and releases.</li>
<li>Video and community support.</li>
</ul>
<p>Please consider <a href="https://www.patreon.com/carmelosantana" rel="nofollow ugc">becoming a Patreon</a> today!</p>
<h3>Made Possible By</h3>
<ul>
<li>Emma Delaney’s <a href="https://emma-delaney.medium.com/how-to-create-your-own-chatgpt-in-html-css-and-javascript-78e32b70b4be" rel="nofollow ugc">How to Create Your Own ChatGPT in HTML CSS and JavaScript</a></li>
<li>Google <a href="https://material.io/resources/icons/?style=baseline" rel="nofollow ugc">Material Design Icons</a> – Apache-2.0 license</li>
<li><a href="https://github.com/chinchang/hint.css" rel="nofollow ugc">Hint.css</a> A CSS only tooltip library – MIT license</li>
<li><a href="https://github.com/DavidBelicza/PHP-Science-TextRank" rel="nofollow ugc">TextRank</a> Automatic text summarization for PHP – MIT license</li>
<li><a href="https://github.com/ollama/ollama" rel="nofollow ugc">Ollama</a> Get up and running with large language models locally – MIT license</li>
<li><a href="https://github.com/erusev/parsedown" rel="nofollow ugc">Parsedown</a> A better Markdown parser – MIT license</li>
</ul>


Alpaca Bot

A privately hosted WordPress AI chatbot. Chat with your own hosted LLMs and automate workflows with agents.

Vexalyn AI Summary for Ollama vs Alpaca Bot