<?xml version="1.0" encoding="UTF-8" standalone="no"?><rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" version="2.0">

<channel>
	<title>SmartTutorials.net</title>
	<atom:link href="https://smarttutorials.net/feed/" rel="self" type="application/rss+xml"/>
	<link>https://smarttutorials.net/</link>
	<description>Tutorials on AI, LLMs and agents</description>
	<lastBuildDate>Wed, 18 Nov 2026 01:26:22 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	

<image>
	<url>https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/smarttutorials-site-icon.png?fit=32%2C32&amp;ssl=1</url>
	<title>SmartTutorials.net</title>
	<link>https://smarttutorials.net/</link>
	<width>32</width>
	<height>32</height>
</image> 
<site xmlns="com-wordpress:feed-additions:1">62095646</site>	<itunes:explicit>no</itunes:explicit><itunes:subtitle>Tutorials on AI, LLMs and agents</itunes:subtitle><item>
		<title>Agent security and governance: keep AI agents useful and contained</title>
		<link>https://smarttutorials.net/agent-security-and-governance/</link>
					<comments>https://smarttutorials.net/agent-security-and-governance/#respond</comments>
		
		<dc:creator/>
		<pubDate>Thu, 19 Nov 2026 03:30:00 +0000</pubDate>
				<category><![CDATA[Agents]]></category>
		<category><![CDATA[Security]]></category>
		<category><![CDATA[ai-agents]]></category>
		<category><![CDATA[governance]]></category>
		<category><![CDATA[llm]]></category>
		<category><![CDATA[owasp]]></category>
		<category><![CDATA[security]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20620</guid>

					<description><![CDATA[An agent can read, decide and act. Here is how to give it enough power to be useful, and enough fences that a mistake or a hostile prompt stays small.]]></description>
										<content:encoded><![CDATA[<p>A chatbot gives you words. An agent gives you actions, and actions have side effects. That changes the security question from “is the answer right?” to “what can this thing do when it is wrong?”</p>
<h2 id="a-chatbot-answers.-an-agent-acts.">1. A chatbot answers. An agent acts.</h2>
<p>In chat, the worst case is a wrong answer that a person reads and judges. With an agent, the worst case is a wrong action: a file deleted, an email sent, a payment made.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-chat-vs-agent.png?ssl=1" alt="Chat versus agent" /><figcaption aria-hidden="true">Chat versus agent</figcaption></figure>
<h2 id="where-an-agent-gets-attacked">2. Where an agent gets attacked</h2>
<p>An agent reads untrusted content (web pages, email, shared documents, tool output) and then acts on powerful systems (shell, databases, cloud APIs, email). Attackers aim at the gap between the two.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-attack-surface.png?ssl=1" alt="Attack surface" /><figcaption aria-hidden="true">Attack surface</figcaption></figure>
<p>The OWASP Top 10 for LLM Applications (2025) names the risks that matter most here:</p>
<ol type="1">
<li><strong>LLM01 Prompt injection</strong>: content steers the agent.</li>
<li><strong>LLM06 Excessive agency</strong>: too many rights or too much autonomy.</li>
<li><strong>LLM03 Supply chain</strong>: a poisoned tool, server or plugin.</li>
<li><strong>LLM10 Unbounded consumption</strong>: runaway loops and cost.</li>
</ol>
<h2 id="every-action-passes-through-the-same-checkpoints">3. Every action passes through the same checkpoints</h2>
<p>Do not rely on the model to behave. Put checkpoints outside it.</p>
<ol type="1">
<li><strong>Identity</strong>: the agent gets its own account, not yours.</li>
<li><strong>Policy gate</strong>: scoped permissions, and each action is allowed, sent to a human, or denied.</li>
<li><strong>Sandbox</strong>: limited files, network and time.</li>
<li><strong>Audit log</strong>: who, what, when and why, append-only.</li>
<li><strong>Kill switch</strong>: one step that stops the agent.</li>
</ol>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-governance-layers.png?ssl=1" alt="Governance layers" /><figcaption aria-hidden="true">Governance layers</figcaption></figure>
<p>Design for the day the model is wrong. Every layer should still hold when the prompt is hostile or the agent is mistaken.</p>
<h2 id="approval-should-scale-with-risk">4. Approval should scale with risk</h2>
<p>Not every action needs a person.</p>
<ul>
<li><strong>Read-only</strong> (list files, read logs, run tests): auto-approve.</li>
<li><strong>Reversible changes</strong> (edit a config after a backup, restart a service with a health check and auto-revert): auto, with a safety net.</li>
<li><strong>Destructive or shared</strong> (delete data, rotate secrets, touch another tenant, spend money, change permissions or firewalls): a human approves.</li>
</ul>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-risk-tiers.png?ssl=1" alt="Risk tiers" /><figcaption aria-hidden="true">Risk tiers</figcaption></figure>
<p>Ask only where it counts. If the agent asks about everything, people click through and the gate protects nothing.</p>
<h2 id="make-mistakes-cheap-snapshot-change-verify-revert">5. Make mistakes cheap: snapshot, change, verify, revert</h2>
<p>Take a snapshot and write a revert script. Make one small change. Verify with health checks against real URLs. If healthy, keep it and log it. If not, auto-revert and alert.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-safe-change-loop.png?ssl=1" alt="Safe change loop" /><figcaption aria-hidden="true">Safe change loop</figcaption></figure>
<p>A real example from our own server work: editing a <code>.env</code> with <code>sed -i</code> silently dropped the file’s group and the site returned 500. The revert path restored it within a minute. The lesson is not that the agent erred. It is that the step was small, checked and undoable.</p>
<h2 id="govern-with-data-review-tighten-repeat">6. Govern with data: review, tighten, repeat</h2>
<p>Log every call: tool, arguments, result, approval and cost. Review weekly. Adjust policy, then redeploy it versioned like code.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-policy-loop.png?ssl=1" alt="Policy loop" /><figcaption aria-hidden="true">Policy loop</figcaption></figure>
<p>Count denials, human approvals, rollbacks, new tools or scopes, and tokens per task. Rising denials mean the agent is pushing on a boundary. Falling approvals may mean people stopped reading them.</p>
<h2 id="checklist">Checklist</h2>
<ul>
<li>Separate identity for every agent.</li>
<li>Least-privilege scopes, deny by default.</li>
<li>Untrusted content is data, never instructions.</li>
<li>Humans approve destructive and shared actions.</li>
<li>Snapshot, verify, auto-revert.</li>
<li>Append-only audit log and a tested kill switch.</li>
</ul>
<h2 id="sources">Sources</h2>
<ul>
<li>OWASP Top 10 for LLM Applications (2025).</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/agent-security-and-governance/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20620</post-id>	</item>
		<item>
		<title>Multi-agent systems: when one agent is not enough</title>
		<link>https://smarttutorials.net/multi-agent-systems-orchestrator-workers/</link>
					<comments>https://smarttutorials.net/multi-agent-systems-orchestrator-workers/#respond</comments>
		
		<dc:creator/>
		<pubDate>Wed, 18 Nov 2026 03:30:00 +0000</pubDate>
				<category><![CDATA[Agents]]></category>
		<category><![CDATA[LLMs]]></category>
		<category><![CDATA[ai-agents]]></category>
		<category><![CDATA[evals]]></category>
		<category><![CDATA[llm]]></category>
		<category><![CDATA[multi-agent]]></category>
		<category><![CDATA[orchestration]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20652</guid>

					<description><![CDATA[A plain-English guide to workflows, agents and orchestrator-workers: how they differ, what they cost in tokens, and how to know if you need one.]]></description>
										<content:encoded><![CDATA[<p>Multi-agent systems are everywhere in demos and rare in production. This post explains what they are, when they help, and what they cost, using one idea per picture.</p>
<h2 id="workflow-or-agent-who-chooses-the-next-step">1. Workflow or agent: who chooses the next step?</h2>
<p>Both use a language model. The difference is who decides what happens next.</p>
<p>In a <strong>workflow</strong>, your code decides. Summarise, then extract, then format. It is predictable, cheap and easy to test.</p>
<p>In an <strong>agent</strong>, the model decides. It plans, picks a tool, reads the result and chooses again until it thinks it is done. It is flexible, costs more and needs guardrails.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-workflow-vs-agent.png?ssl=1" alt="Workflow versus agent" /><figcaption aria-hidden="true">Workflow versus agent</figcaption></figure>
<p><em>Rule: if you can write the steps down in advance, write a workflow.</em></p>
<h2 id="five-patterns-from-simplest-to-most-agentic">2. Five patterns, from simplest to most agentic</h2>
<p>Anthropic’s “Building effective agents” guide names five building blocks. Learn them in this order.</p>
<ol type="1">
<li><strong>Prompt chaining</strong>: each step builds on the last, with optional checks between steps.</li>
<li><strong>Routing</strong>: classify the input, then send it to a specialised prompt.</li>
<li><strong>Parallelization</strong>: split the work or repeat it, then merge the results.</li>
<li><strong>Orchestrator-workers</strong>: a lead model plans on the fly and delegates.</li>
<li><strong>Evaluator-optimizer</strong>: one model drafts, another critiques, repeat.</li>
</ol>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-five-patterns.png?ssl=1" alt="Five patterns" /><figcaption aria-hidden="true">Five patterns</figcaption></figure>
<p>Start with the simplest pattern that works. Add complexity only when it measurably improves results.</p>
<h2 id="orchestrator-workers-step-by-step">3. Orchestrator-workers, step by step</h2>
<p>This is what most people mean by “multi-agent”.</p>
<p>A lead agent receives the query, makes a plan and saves it to memory so it survives a long run. It spawns subagents that work in parallel, each with its own context and tools. Each returns condensed findings, not its whole context. The lead merges them, attaches sources and answers.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-orchestrator-workers.png?ssl=1" alt="Orchestrator-workers" /><figcaption aria-hidden="true">Orchestrator-workers</figcaption></figure>
<p>Two practical tips. Give each subagent a precise task, because vague hand-offs cause duplicated work. And let subagents write large outputs to storage and pass back a reference, which saves tokens.</p>
<h2 id="the-bill">4. The bill</h2>
<p>Anthropic reported that, in its own research workloads, agents used about four times the tokens of a chat turn, and multi-agent systems about fifteen times. Your numbers will differ, but the shape holds: more agents means more tokens.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-token-cost.png?ssl=1" alt="Token cost" /><figcaption aria-hidden="true">Token cost</figcaption></figure>
<p>Multi-agent systems work mainly because they spend enough tokens to solve the problem. That is fine when the task is valuable and splits cleanly. It is waste when it does not.</p>
<h2 id="should-this-task-be-multi-agent">5. Should this task be multi-agent?</h2>
<p>Ask three questions.</p>
<ol type="1">
<li>Can the work split into independent parts? If not, use a single agent with tools, or a workflow.</li>
<li>Does the value justify roughly fifteen times the tokens? If not, stay with a single agent and measure first.</li>
<li>Do the parts need shared context or each other’s results? If yes, keep it single.</li>
</ol>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-should-you.png?ssl=1" alt="Decision tree" /><figcaption aria-hidden="true">Decision tree</figcaption></figure>
<p>Common failure modes: spawning dozens of subagents for a simple question, vague hand-offs, duplicated work and searching forever.</p>
<h2 id="evaluate-it-like-a-product-not-a-demo">6. Evaluate it like a product, not a demo</h2>
<p>Start with about twenty real queries. Run the system and trace every step. Score the results with an LLM judge using one rubric, then have a person spot-check what the judge misses. Fix prompts, tool descriptions and delegation, then rerun.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-eval-loop.png?ssl=1" alt="Eval loop" /><figcaption aria-hidden="true">Eval loop</figcaption></figure>
<p>Useful rubric items: factual accuracy, citation accuracy, completeness, source quality and tool efficiency.</p>
<h2 id="takeaways">Takeaways</h2>
<ul>
<li>Prefer workflows. Reach for agents when the path cannot be written down.</li>
<li>Multi-agent is one pattern, not a goal. It costs about an order of magnitude more tokens.</li>
<li>Delegate with precise tasks and condensed returns.</li>
<li>Measure with real queries before you scale.</li>
</ul>
<h2 id="sources">Sources</h2>
<ul>
<li>Anthropic, “Building effective agents”.</li>
<li>Anthropic Engineering, “How we built our multi-agent research system”.</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/multi-agent-systems-orchestrator-workers/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20652</post-id>	</item>
		<item>
		<title>Hugging Face now routes open-model chat requests through OpenRouter: what changes for builders</title>
		<link>https://smarttutorials.net/hugging-face-inference-providers-openrouter/</link>
					<comments>https://smarttutorials.net/hugging-face-inference-providers-openrouter/#respond</comments>
		
		<dc:creator/>
		<pubDate>Wed, 18 Nov 2026 01:26:22 +0000</pubDate>
				<category><![CDATA[LLM Engineering]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20676</guid>

					<description><![CDATA[On November 16, 2026 Hugging Face said chat-model requests on Inference Providers now run through OpenRouter. Here is what stays the same, what breaks, and how to use the routing options.]]></description>
										<content:encoded><![CDATA[<h2 id="1-what-happened">1. What happened</h2>
<p>On November 16, 2026, Hugging Face announced a partnership with OpenRouter. Language-model requests sent to Hugging Face Inference Providers are now routed by OpenRouter instead of Hugging Face&#8217;s own router. OpenRouter published a matching announcement the same day. Hugging Face&#8217;s docs now say routing is powered by OpenRouter and that a failed or rate-limited provider triggers automatic failover.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-request-path.png?ssl=1" alt="Request path" /></p>
<h2 id="2-why-it-matters-to-builders">2. Why it matters to builders</h2>
<p>One Hugging Face token reaches any open-weight chat model that at least one provider serves, at the provider&#8217;s price with no Hugging Face markup. The post says existing code keeps working.</p>
<p>There is one breaking change. Chat-model requests can no longer use your own provider API key. They are billed to your Hugging Face account or organization. Custom keys still work for image and video providers. If you relied on bring-your-own-key for a negotiated rate or a data agreement, check this before you rely on the new path.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-stays-changes.png?ssl=1" alt="What stays and what changes" /></p>
<h2 id="3-how-the-routing-works">3. How the routing works</h2>
<p>The router accepts OpenAI Chat Completions and Responses requests and Anthropic Messages requests for every chat model. It spreads traffic across more than 80 providers using live price, speed and reliability, and retries on another provider within the same call if one fails.</p>
<p>You steer it with a suffix on the model ID: <code>:fastest</code>, <code>:cheapest</code>, or a provider name such as <code>:novita</code>. The router also keeps a conversation on the provider that holds its prompt cache. You can make that explicit with a stable UUID in the <code>X-HF-Session-Id</code> header. Administrators can switch off individual providers, and the router will not send their requests there.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-routing-suffixes.png?ssl=1" alt="Routing suffixes" /></p>
<h2 id="4-what-to-do">4. What to do</h2>
<p>The example below follows Hugging Face&#8217;s documentation. We have not run it ourselves.</p>
<div class="sourceCode" id="cb1">
<pre class="sourceCode python"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> os</span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> openai <span class="im">import</span> OpenAI</span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a>client <span class="op">=</span> OpenAI(</span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a>    base_url<span class="op">=</span><span class="st">&quot;https://router.huggingface.co/v1&quot;</span>,</span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>    api_key<span class="op">=</span>os.environ[<span class="st">&quot;HF_TOKEN&quot;</span>],</span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a>completion <span class="op">=</span> client.chat.completions.create(</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a>    model<span class="op">=</span><span class="st">&quot;deepseek-ai/DeepSeek-V4.1-Flash:cheapest&quot;</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>    messages<span class="op">=</span>[{<span class="st">&quot;role&quot;</span>: <span class="st">&quot;user&quot;</span>, <span class="st">&quot;content&quot;</span>: <span class="st">&quot;Hello&quot;</span>}],</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a>    extra_headers<span class="op">=</span>{<span class="st">&quot;X-HF-Bill-To&quot;</span>: <span class="st">&quot;my-org-name&quot;</span>},  <span class="co"># Team/Enterprise billing</span></span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a>)</span></code></pre>
</div>
<p>A sensible order of work, which is our suggestion and not an official procedure:</p>
<ol type="1">
<li>Search your code for provider keys used on chat calls. Those requests now bill through Hugging Face.</li>
<li>Decide per workload between default routing, <code>:fastest</code> and <code>:cheapest</code>.</li>
<li>Disable any provider your compliance rules exclude.</li>
<li>Compare spend by provider on the usage page after a week.</li>
</ol>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-migration.png?ssl=1" alt="Migration checklist" /></p>
<h2 id="5-what-is-still-unknown">5. What is still unknown</h2>
<p>OpenRouter says its rebuilt routing cut capacity errors by 46%, improved time to first token by 16.9% and raised throughput by 16.3%, according to the Hugging Face post. These are vendor figures. We could not see the baseline or the workload behind them. The first phase is described as only the start: linking OpenRouter accounts to Hugging Face and routing more task types are listed as next steps, without dates.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-reported-unknown.png?ssl=1" alt="Reported versus unknown" /></p>
<h2 id="takeaways">Takeaways</h2>
<ul>
<li>Your base URL and token stay the same; the routing engine behind them changed.</li>
<li>Bring-your-own-key no longer works for chat models on this path.</li>
<li>Model-ID suffixes give you per-request control over price versus speed.</li>
<li>Treat the performance percentages as claims until you measure your own traffic.</li>
</ul>
<h2 id="sources">Sources</h2>
<ul>
<li>Hugging Face, &#8220;Hugging Face and OpenRouter join forces to make open-weight models easy to run&#8221;, 2026-11-16: <a href="https://huggingface.co/blog/openrouter">https://huggingface.co/blog/openrouter</a></li>
<li>OpenRouter, &#8220;OpenRouter Now Powers Inference on Hugging Face&#8221;, 2026-11-16: <a href="https://openrouter.ai/announcements">https://openrouter.ai/announcements</a></li>
<li>Hugging Face Inference Providers documentation (accessed 2026-11-17): <a href="https://huggingface.co/docs/inference-providers/index">https://huggingface.co/docs/inference-providers/index</a></li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/hugging-face-inference-providers-openrouter/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20676</post-id>	</item>
		<item>
		<title>MCP explained: the Model Context Protocol in plain English</title>
		<link>https://smarttutorials.net/mcp-model-context-protocol-guide/</link>
					<comments>https://smarttutorials.net/mcp-model-context-protocol-guide/#respond</comments>
		
		<dc:creator/>
		<pubDate>Tue, 17 Nov 2026 03:30:00 +0000</pubDate>
				<category><![CDATA[Agents]]></category>
		<category><![CDATA[LLMs]]></category>
		<category><![CDATA[ai-agents]]></category>
		<category><![CDATA[llm]]></category>
		<category><![CDATA[mcp]]></category>
		<category><![CDATA[security]]></category>
		<category><![CDATA[tools]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20644</guid>

					<description><![CDATA[MCP is a shared plug for connecting AI apps to tools and data. This guide covers the architecture, the building blocks, a request end to end, and the security traps.]]></description>
										<content:encoded><![CDATA[<p>Every AI app wants to read your files, query your database and call your APIs. Without a standard, each app wires up each tool by hand. The Model Context Protocol (MCP) is the standard.</p>
<p><em>Details here follow the protocol revision dated 2026-07-28. Check the current spec before you build.</em></p>
<h2 id="one-protocol-instead-of-every-app-wiring-every-tool">1. One protocol instead of every app wiring every tool</h2>
<p>Without MCP, N apps and M tools mean N x M custom integrations. With MCP each side speaks the protocol once, so the work becomes N + M.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-n-times-m.png?ssl=1" alt="N times M" /><figcaption aria-hidden="true">N times M</figcaption></figure>
<h2 id="host-clients-and-servers">2. Host, clients and servers</h2>
<p>The <strong>host</strong> is the AI application. Inside it, one <strong>MCP client</strong> per server holds a dedicated connection. A <strong>server</strong> exposes capabilities, either locally over stdio or remotely over Streamable HTTP. Messages are JSON-RPC 2.0.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-architecture.png?ssl=1" alt="Architecture" /><figcaption aria-hidden="true">Architecture</figcaption></figure>
<h2 id="what-a-server-can-offer-and-what-a-client-can-offer-back">3. What a server can offer, and what a client can offer back</h2>
<p>Servers offer three primitives.</p>
<ul>
<li><strong>Tools</strong>: actions the model can call, such as <code>search_orders(query)</code>.</li>
<li><strong>Resources</strong>: context data to read, such as file contents or a schema.</li>
<li><strong>Prompts</strong>: reusable templates.</li>
</ul>
<p>Clients can offer <strong>elicitation</strong>, which lets a server ask the user for input or confirmation. Sampling and logging are deprecated from the 2026-07-28 revision; prefer your own LLM API calls, plus OpenTelemetry or stderr for logs.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-primitives.png?ssl=1" alt="Primitives" /><figcaption aria-hidden="true">Primitives</figcaption></figure>
<h2 id="a-request-end-to-end">4. A request, end to end</h2>
<ol type="1">
<li><code>server/discover</code>: the client learns versions, capabilities and identity, which can be cached.</li>
<li><code>tools/list</code>: the client gets tool names, schemas and descriptions.</li>
<li><code>tools/call</code>: the client sends a name and arguments and receives result content.</li>
<li><code>subscriptions/listen</code>: the client opts in to notifications such as a changed tool list.</li>
</ol>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-request-flow.png?ssl=1" alt="Request flow" /><figcaption aria-hidden="true">Request flow</figcaption></figure>
<h2 id="from-idea-to-a-server-your-host-can-use">5. From idea to a server your host can use</h2>
<p>Write the server with an official SDK, starting with one small tool. Run it in the MCP Inspector and call it by hand. Add it to a host’s config, reviewing the exact command. Try real prompts and check the model picks the right tool. Then review scopes, errors and who called what.</p>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-build-and-test.png?ssl=1" alt="Build and test" /><figcaption aria-hidden="true">Build and test</figcaption></figure>
<p>Tool names and descriptions matter as much as the code. They are what the model reads to decide when to call.</p>
<h2 id="six-ways-it-goes-wrong-and-the-fix-for-each">6. Six ways it goes wrong, and the fix for each</h2>
<figure>
<img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-threats.png?ssl=1" alt="Threats" /><figcaption aria-hidden="true">Threats</figcaption></figure>
<table>
<colgroup>
<col style="width: 33%" />
<col style="width: 33%" />
<col style="width: 33%" />
</colgroup>
<thead>
<tr>
<th>Risk</th>
<th>What happens</th>
<th>Fix</th>
</tr>
</thead>
<tbody>
<tr>
<td>Confused deputy</td>
<td>A proxy reuses one OAuth client ID and a consent cookie</td>
<td>Store per-client consent server-side, match redirect URIs exactly</td>
</tr>
<tr>
<td>Token passthrough</td>
<td>A server forwards tokens it never validated</td>
<td>Accept only tokens issued for this server</td>
</tr>
<tr>
<td>SSRF</td>
<td>A malicious server points discovery at internal URLs</td>
<td>HTTPS only, block private and link-local ranges, use an egress proxy</td>
</tr>
<tr>
<td>Local server compromise</td>
<td>One-click setup runs an unknown command</td>
<td>Show the exact command, ask first, sandbox with minimal rights</td>
</tr>
<tr>
<td>Over-broad scopes</td>
<td>A stolen token can do everything</td>
<td>Start with read, step up on demand, log elevations</td>
</tr>
<tr>
<td>State handle hijacking</td>
<td>A guessed ID opens another user’s state</td>
<td>Random handles bound to the verified user</td>
</tr>
</tbody>
</table>
<h2 id="takeaways">Takeaways</h2>
<ul>
<li>MCP turns N x M integrations into N + M.</li>
<li>Host, client, server; stdio locally, Streamable HTTP remotely.</li>
<li>Tools act, resources inform, prompts template.</li>
<li>Treat every server as untrusted code with access to your data.</li>
</ul>
<h2 id="sources">Sources</h2>
<ul>
<li>Model Context Protocol specification and security best practices (modelcontextprotocol.io).</li>
<li>OWASP Top 10 for LLM Applications (2025).</li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/mcp-model-context-protocol-guide/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20644</post-id>	</item>
		<item>
		<title>Create a Narrated Video with a Local LLM (Free, Offline Tutorial)</title>
		<link>https://smarttutorials.net/create-narrated-video-local-llm/</link>
					<comments>https://smarttutorials.net/create-narrated-video-local-llm/#respond</comments>
		
		<dc:creator><![CDATA[muni]]></dc:creator>
		<pubDate>Tue, 17 Nov 2026 02:56:45 +0000</pubDate>
				<category><![CDATA[LLM Engineering]]></category>
		<category><![CDATA[LLMs]]></category>
		<category><![CDATA[ai-video]]></category>
		<category><![CDATA[ffmpeg]]></category>
		<category><![CDATA[gpt-oss]]></category>
		<category><![CDATA[kokoro-tts]]></category>
		<category><![CDATA[local-llm]]></category>
		<category><![CDATA[offline-ai]]></category>
		<category><![CDATA[ollama]]></category>
		<category><![CDATA[python]]></category>
		<category><![CDATA[text-to-speech]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20677</guid>

					<description><![CDATA[Build a free, offline pipeline that turns a text brief into a narrated MP4. Ollama writes the script, Kokoro speaks it, Pillow draws the slides and ffmpeg assembles the video.]]></description>
										<content:encoded><![CDATA[<p>Making a video usually means a lot of tools, a subscription for the voice-over, and a pile of footage to edit. What if you could type a few lines describing a video and get back a finished MP4 with slides and a natural voice-over, all on your own computer?</p>
<p>In this tutorial you will create a <strong>narrated video with a local LLM</strong>. An open language model writes the script, an open text-to-speech model speaks it, and ffmpeg assembles the result. It is free, it works offline, and no API key is involved. Your text never leaves your machine.</p>
<figure class="wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio">
<div class="wp-block-embed__wrapper" style="position:relative;padding-bottom:56.25%;height:0;overflow:hidden"><iframe src="https://www.youtube.com/embed/0VHA6d5-ZE4?rel=0" title="Create a Narrated Video with a Local LLM (Free, Offline, No API Keys)" style="position:absolute;top:0;left:0;width:100%;height:100%;border:0" loading="lazy" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div><figcaption>Watch the demo: a narrated video made with a local LLM, using the script in this tutorial (<a href="https://youtu.be/0VHA6d5-ZE4" rel="noopener">watch on YouTube</a>)</figcaption></figure>
<p><script type="application/ld+json">{"@context": "https://schema.org", "@type": "VideoObject", "name": "Create a Narrated Video with a Local LLM (Free, Offline, No API Keys)", "description": "Create a narrated video with a local LLM, free and offline. Ollama writes the storyboard, Kokoro speaks the narration, Pillow draws the slides and ffmpeg assembles the MP4.", "thumbnailUrl": ["https://i.ytimg.com/vi/0VHA6d5-ZE4/maxresdefault.jpg"], "uploadDate": "2026-11-17", "duration": "PT1M15S", "embedUrl": "https://www.youtube.com/embed/0VHA6d5-ZE4", "contentUrl": "https://youtu.be/0VHA6d5-ZE4"}</script></p>
<p><em>The video above was made with the script from this tutorial. Prefer YouTube? <a href="https://youtu.be/0VHA6d5-ZE4" rel="noopener">Watch it there</a> and subscribe for more.</em></p>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" fetchpriority="high" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=2400%2C1400&#038;ssl=1" alt="One text file in, one narrated video out. A brief.txt file goes into make_video.py and a final.mp4 video comes out." class="wp-image-20679" width="2400" height="1400" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-big-picture.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="(max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 1: one text file in, one narrated video out</figcaption></figure>
<p><strong>In this guide</strong></p>
<ul>
<li><a href="#what-you-will-build">What you will build</a></li>
<li><a href="#what-you-need">What you need</a></li>
<li><a href="#step-1-install-ffmpeg-and-python-tools">Step 1. Install ffmpeg and Python tools</a></li>
<li><a href="#step-2-install-ollama-and-download-an-open-llm">Step 2. Install Ollama and download an open LLM</a></li>
<li><a href="#step-3-create-the-project-folder-and-python-environment">Step 3. Create the project folder and Python environment</a></li>
<li><a href="#step-4-download-the-voice-kokoro-text-to-speech">Step 4. Download the voice (Kokoro text-to-speech)</a></li>
<li><a href="#step-5-download-the-font">Step 5. Download the font</a></li>
<li><a href="#how-the-local-llm-video-pipeline-works">How the local LLM video pipeline works</a></li>
<li><a href="#the-complete-python-script">The complete Python script</a></li>
<li><a href="#step-6-make-your-first-video">Step 6. Make your first video</a></li>
<li><a href="#step-7-polish-the-video-with-the-edit-loop">Step 7. Polish the video with the edit loop</a></li>
<li><a href="#troubleshooting">Troubleshooting</a></li>
<li><a href="#make-it-yours">Make it yours</a></li>
<li><a href="#frequently-asked-questions">Frequently asked questions</a></li>
<li><a href="#summary">Summary</a></li>
</ul>
<h2 id="what-you-will-build">What you will build</h2>
<p>You will build one Python script, <code>make_video.py</code>, that turns a plain-text brief into a narrated video. It uses four open source tools:</p>
<div style="overflow-x:auto">
<table>
<thead>
<tr>
<th>Job</th>
<th>Tool</th>
<th>What it does</th>
</tr>
</thead>
<tbody>
<tr>
<td>Write the storyboard</td>
<td><a href="https://ollama.com" rel="noopener">Ollama</a> running an open LLM (<code>gpt-oss</code>, 20B)</td>
<td>Turns your brief into scenes: headline, bullets and narration</td>
</tr>
<tr>
<td>Speak the narration</td>
<td><a href="https://github.com/hexgrad/kokoro" rel="noopener">Kokoro</a> text-to-speech</td>
<td>Natural-sounding voice that runs on the CPU</td>
</tr>
<tr>
<td>Draw the slides</td>
<td><a href="https://python-pillow.github.io/" rel="noopener">Pillow</a></td>
<td>One 1920&#215;1080 image per scene</td>
</tr>
<tr>
<td>Animate and assemble</td>
<td><a href="https://ffmpeg.org" rel="noopener">ffmpeg</a></td>
<td>Slow zoom, fades, audio and the final MP4</td>
</tr>
</tbody>
</table>
</div>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=2400%2C1400&#038;ssl=1" alt="Four open source tools, one job each: Ollama writes the storyboard, Kokoro speaks the narration, Pillow draws the slides and ffmpeg assembles the video." class="wp-image-20680" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-four-tools.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 2: the four tools and what each one does</figcaption></figure>
<p><strong>Key takeaways</strong></p>
<ul>
<li>A local LLM writes the <em>content</em>. The layout and editing are ordinary code, so the result is predictable.</li>
<li>The length of each voice-over decides the length of each scene, so picture and sound always match.</li>
<li>You edit one JSON file to polish the video, and re-rendering takes under a minute.</li>
</ul>
<blockquote>
<p><strong>Scope.</strong> This is not a text-to-video generator. It is a fast, reliable way to produce explainer and tutorial videos where you stay in control of every word.</p>
</blockquote>
<p><strong>Tested on:</strong> Debian-based Linux (Kali), Python 3.14, 16 CPU threads, 62 GB RAM and a 4 GB NVIDIA GPU. For a 6-scene, 75-second video, the LLM step took about 2 to 3 minutes and the voice and rendering about 45 seconds. A smaller model is faster.</p>
<h2 id="what-you-need">What you need</h2>
<div style="overflow-x:auto">
<table>
<thead>
<tr>
<th>You need</th>
<th>Notes</th>
</tr>
</thead>
<tbody>
<tr>
<td>Linux (commands use <code>apt</code>)</td>
<td>macOS and Windows should work with small changes, see the section on other systems below. I have only tested Linux.</td>
</tr>
<tr>
<td>8 GB of RAM or more</td>
<td>More RAM lets you run larger models. A GPU helps but is not required.</td>
</tr>
<tr>
<td>About 15 GB of free disk</td>
<td>13 GB for the <code>gpt-oss</code> model, about 340 MB for the voice, plus Python packages. A 3B model needs only about 2 GB.</td>
</tr>
<tr>
<td>An internet connection for setup</td>
<td>After setup, everything runs offline.</td>
</tr>
</tbody>
</table>
</div>
<p>Estimated setup time: 15 to 30 minutes, mostly downloads.</p>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=2400%2C1400&#038;ssl=1" alt="Five setup steps: install ffmpeg and Python, install Ollama and pull gpt-oss, create a virtual environment, download the Kokoro voice, and download the Instrument Sans font." class="wp-image-20681" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-setup-steps.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 3: the five setup steps and their download sizes</figcaption></figure>
<h2 id="step-1-install-ffmpeg-and-python-tools">Step 1. Install ffmpeg and Python tools</h2>
<pre class="wp-block-code"><code class="language-bash">sudo apt update
sudo apt install -y ffmpeg python3 python3-venv curl
</code></pre>
<p>Check that ffmpeg is installed:</p>
<pre class="wp-block-code"><code class="language-bash">ffmpeg -version | head -1
</code></pre>
<h2 id="step-2-install-ollama-and-download-an-open-llm">Step 2. Install Ollama and download an open LLM</h2>
<p><a href="https://ollama.com" rel="noopener">Ollama</a> runs open language models on your own machine. Install it with the official script:</p>
<pre class="wp-block-code"><code class="language-bash">curl -fsSL https://ollama.com/install.sh | sh
</code></pre>
<p>Download a model. This tutorial uses <code>gpt-oss</code> (20 billion parameters, about 13 GB):</p>
<pre class="wp-block-code"><code class="language-bash">ollama pull gpt-oss
</code></pre>
<p>Test it:</p>
<pre class="wp-block-code"><code class="language-bash">ollama run gpt-oss &quot;Say hello in five words&quot;
</code></pre>
<p>You should see a short reply. Press <code>Ctrl+D</code> to exit.</p>
<p><strong>Smaller computer?</strong> Try a model of about 3 billion parameters, such as <code>llama3.2:3b</code> or <code>qwen2.5:3b</code>, and pass its name with <code>--model</code> later. Small models are much faster but write plainer scripts, and they are more likely to return broken JSON. I tested only <code>gpt-oss</code>, so check the result when you try another model.</p>
<h2 id="step-3-create-the-project-folder-and-python-environment">Step 3. Create the project folder and Python environment</h2>
<pre class="wp-block-code"><code class="language-bash">mkdir -p ~/ai-video/fonts ~/ai-video/models
cd ~/ai-video
python3 -m venv venv
./venv/bin/pip install kokoro-onnx soundfile pillow
</code></pre>
<p>A virtual environment keeps every package inside this folder. It needs no <code>sudo</code> and it does not touch your system Python.</p>
<h2 id="step-4-download-the-voice-kokoro-text-to-speech">Step 4. Download the voice (Kokoro text-to-speech)</h2>
<p><a href="https://github.com/hexgrad/kokoro" rel="noopener">Kokoro</a> is a small open text-to-speech model (Apache 2.0 license) that sounds far more natural than older offline voices. The <code>kokoro-onnx</code> package runs it on the CPU. Download the model file (about 310 MB) and the voices file (about 27 MB):</p>
<pre class="wp-block-code"><code class="language-bash">cd ~/ai-video
R=https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0
curl -L -o models/kokoro-v1.0.onnx $R/kokoro-v1.0.onnx
curl -L -o models/voices-v1.0.bin  $R/voices-v1.0.bin
</code></pre>
<p>Test the voice:</p>
<pre class="wp-block-code"><code class="language-bash">./venv/bin/python - &lt;&lt;'EOF'
import soundfile as sf
from kokoro_onnx import Kokoro

tts = Kokoro(&quot;models/kokoro-v1.0.onnx&quot;, &quot;models/voices-v1.0.bin&quot;)
samples, rate = tts.create(&quot;Hello from my own computer.&quot;, voice=&quot;am_michael&quot;, speed=1.0, lang=&quot;en-us&quot;)
sf.write(&quot;test.wav&quot;, samples, rate)
EOF
ffplay -autoexit -nodisp test.wav
</code></pre>
<p><code>ffplay</code> comes with ffmpeg on most systems. If it is missing, open <code>test.wav</code> in any audio player.</p>
<p><strong>Choosing a voice.</strong> The script takes a <code>--voice</code> option. A few good English voices:</p>
<div style="overflow-x:auto">
<table>
<thead>
<tr>
<th>Voice</th>
<th>Style</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>am_michael</code></td>
<td>Male, American (the default in this tutorial)</td>
</tr>
<tr>
<td><code>af_heart</code></td>
<td>Female, American</td>
</tr>
<tr>
<td><code>bf_emma</code></td>
<td>Female, British</td>
</tr>
<tr>
<td><code>bm_george</code></td>
<td>Male, British</td>
</tr>
</tbody>
</table>
</div>
<p>Run <code>tts.get_voices()</code> in Python to list all of them. British voices sound best with <code>lang="en-gb"</code>.</p>
<h2 id="step-5-download-the-font">Step 5. Download the font</h2>
<p>The slides use <a href="https://fonts.google.com/specimen/Instrument+Sans" rel="noopener">Instrument Sans</a>, a free font under the SIL Open Font License:</p>
<pre class="wp-block-code"><code class="language-bash">cd ~/ai-video
curl -L -o fonts/InstrumentSans.ttf \
  &quot;https://github.com/google/fonts/raw/main/ofl/instrumentsans/InstrumentSans%5Bwdth%2Cwght%5D.ttf&quot;
</code></pre>
<p>This is a <em>variable</em> font, so one file provides Regular, Medium, SemiBold and Bold. To use another font, change the <code>FONT</code> path at the top of the script. If you use a static font file, remove the <code>set_variation_by_name</code> line in <code>font()</code>.</p>
<p>After steps 1 to 5, your folder looks like this:</p>
<pre class="wp-block-code"><code>~/ai-video/
├── fonts/InstrumentSans.ttf
├── models/kokoro-v1.0.onnx
├── models/voices-v1.0.bin
└── venv/
</code></pre>
<h2 id="how-the-local-llm-video-pipeline-works">How the local LLM video pipeline works</h2>
<p>The script runs five stages. Each stage hands a simple file to the next one.</p>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=2400%2C1400&#038;ssl=1" alt="The pipeline: brief.txt goes to the LLM, which writes scenes.json. For every scene, Kokoro makes a voice file and Pillow makes a slide image. ffmpeg then builds clips and joins them into final.mp4." class="wp-image-20682" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-pipeline.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 4: from brief.txt to final.mp4</figcaption></figure>
<ol>
<li><strong>Storyboard.</strong> The script asks the LLM for JSON: a list of scenes, each with a <code>headline</code>, up to four <code>bullets</code> and a <code>narration</code>.</li>
<li><strong>Voice.</strong> Kokoro reads each narration into a WAV file. The script measures the WAV length, because <strong>the audio length decides how long each scene lasts</strong>. This keeps picture and voice in sync with no manual timing.</li>
<li><strong>Slides.</strong> Pillow draws a slide for each scene. Long headlines are wrapped into two balanced lines.</li>
<li><strong>Clips.</strong> ffmpeg combines each slide and its audio into a short clip with a slow zoom and a fade in and out.</li>
<li><strong>Join.</strong> ffmpeg joins the clips into <code>final.mp4</code>.</li>
</ol>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=2400%2C1400&#038;ssl=1" alt="A timeline of six scenes of 11.4, 10.5, 13.0, 13.5, 13.0 and 13.1 seconds, each sized to match its voice-over audio." class="wp-image-20683" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-audio-sets-length.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 5: the voice-over sets the length of every scene</figcaption></figure>
<p>Three details are worth knowing:</p>
<ul>
<li><strong>Do not use Ollama&#8217;s <code>"format": "json"</code> option with reasoning models such as <code>gpt-oss</code>.</strong> It returned garbage in my tests. The script instead asks for JSON in the prompt, extracts the <code>{...}</code> block, checks it, and retries up to three times.</li>
<li><strong>Normalize the text.</strong> LLMs like typographic characters (non-breaking hyphens, em dashes, curly quotes) that fonts and voices handle badly. The <code>normalize()</code> function replaces them.</li>
<li><strong>Teach the voice your vocabulary.</strong> Text-to-speech models stumble on names such as &#8220;ffmpeg&#8221;. The <code>PRONUNCIATION</code> dictionary rewrites words for the voice only, so the slides still show the real spelling.</li>
</ul>
<h2 id="the-complete-python-script">The complete Python script</h2>
<p>Save this as <code>~/ai-video/make_video.py</code>:</p>
<pre class="wp-block-code"><code class="language-python">#!/usr/bin/env python3
&quot;&quot;&quot;make_video.py - turn a short brief into a narrated video, fully offline.

LLM (Ollama)  -&gt; writes the storyboard (headline, bullets, narration) as JSON
Kokoro TTS    -&gt; turns each narration into a natural-sounding voice-over
Pillow        -&gt; draws one slide per scene
ffmpeg        -&gt; animates the slides, mixes the audio, joins everything into an MP4

Usage:
    python make_video.py brief.txt --out my_video --model gpt-oss --scenes 6
&quot;&quot;&quot;
import argparse, json, re, subprocess, urllib.request
from pathlib import Path

import soundfile as sf
from kokoro_onnx import Kokoro
from PIL import Image, ImageDraw, ImageFont

W, H, FPS = 1920, 1080, 30
HERE = Path(__file__).parent
FONT = HERE / &quot;fonts&quot; / &quot;InstrumentSans.ttf&quot;       # variable font: Regular..Bold
KOKORO_MODEL = HERE / &quot;models&quot; / &quot;kokoro-v1.0.onnx&quot;
KOKORO_VOICES = HERE / &quot;models&quot; / &quot;voices-v1.0.bin&quot;

# Words the voice tends to mispronounce -&gt; how to spell them for the voice only.
PRONUNCIATION = {
    &quot;SmartTutorials.net&quot;: &quot;Smart Tutorials dot net&quot;,
    &quot;smarttutorials.net&quot;: &quot;smart tutorials dot net&quot;,
    &quot;ffmpeg&quot;: &quot;eff eff em peg&quot;,
    &quot;Ollama&quot;: &quot;oh-lama&quot;,
    &quot;LLM&quot;: &quot;L L M&quot;,
    &quot;LLMs&quot;: &quot;L L Ms&quot;,
    &quot;TTS&quot;: &quot;text to speech&quot;,
    &quot;MP4&quot;: &quot;M P 4&quot;,
    &quot;JSON&quot;: &quot;jay-son&quot;,
    &quot;RAG&quot;: &quot;rag&quot;,
}


# ---------- 1. The LLM writes the storyboard ----------
def ask_llm(brief, model, n_scenes):
    prompt = f&quot;&quot;&quot;You write storyboards for short narrated tutorial videos.
Brief:
{brief}

Return ONLY JSON with this shape:
{{&quot;scenes&quot;: [{{&quot;headline&quot;: &quot;max 8 words&quot;, &quot;bullets&quot;: [&quot;max 4 short bullets, max 7 words each&quot;], &quot;narration&quot;: &quot;1-2 spoken sentences, plain text, no emojis&quot;}}]}}
Rules: exactly {n_scenes} scenes. Scene 1 is the title card (empty bullets list). The last scene is a call to action.
Write narration the way a calm, friendly person would say it aloud: contractions, no hype.&quot;&quot;&quot;
    # NOTE: no &quot;format&quot;: &quot;json&quot; here - reasoning models such as gpt-oss break with it.
    body = json.dumps({&quot;model&quot;: model, &quot;prompt&quot;: prompt, &quot;stream&quot;: False,
                       &quot;options&quot;: {&quot;temperature&quot;: 0.6}}).encode()
    for attempt in range(1, 4):
        req = urllib.request.Request(&quot;http://localhost:11434/api/generate&quot;, body,
                                     {&quot;Content-Type&quot;: &quot;application/json&quot;})
        with urllib.request.urlopen(req, timeout=900) as r:
            text = json.load(r)[&quot;response&quot;]
        m = re.search(r&quot;\{.*\}&quot;, text, re.S)  # grab the JSON object even if the model adds chatter
        try:
            scenes = json.loads(m.group(0))[&quot;scenes&quot;]
            assert len(scenes) &gt;= 2 and all(&quot;narration&quot; in s and &quot;headline&quot; in s for s in scenes)
            return scenes
        except Exception as e:
            print(f&quot;  attempt {attempt}: could not parse the LLM answer ({e}); retrying&quot;)
    raise SystemExit(&quot;The LLM did not return valid JSON after 3 attempts&quot;)


def normalize(s):
    &quot;&quot;&quot;Replace typographic characters that fonts and voices handle badly.&quot;&quot;&quot;
    s = s.replace(&quot;‑&quot;, &quot;-&quot;).replace(&quot;—&quot;, &quot;, &quot;).replace(&quot;–&quot;, &quot;-&quot;)
    s = s.replace(&quot;’&quot;, &quot;'&quot;).replace(&quot;‘&quot;, &quot;'&quot;).replace(&quot;“&quot;, '&quot;').replace(&quot;”&quot;, '&quot;')
    return re.sub(r&quot;\s+&quot;, &quot; &quot;, s).strip()


def for_voice(s):
    s = normalize(s)
    for word, spoken in PRONUNCIATION.items():
        s = re.sub(rf&quot;\b{re.escape(word)}(?![\w])&quot;, spoken, s) if word[0].isalnum() else s.replace(word, spoken)
    return s


# ---------- 2. Slides ----------
def font(size, weight=&quot;Regular&quot;):
    f = ImageFont.truetype(str(FONT), size)
    f.set_variation_by_name(weight)
    return f


def background():
    im = Image.new(&quot;RGB&quot;, (W, H))
    px = im.load()
    for y in range(H):
        t = y / H
        c = (int(12 + 18 * t), int(14 + 10 * t), int(40 + 50 * t))
        for x in range(W):
            px[x, y] = c
    d = ImageDraw.Draw(im, &quot;RGBA&quot;)
    for cx, cy, r, col in [(260, 180, 340, (80, 120, 255, 40)), (1700, 900, 420, (140, 90, 255, 36))]:
        d.ellipse([cx - r, cy - r, cx + r, cy + r], fill=col)
    return im


def wrap(d, text, f, max_width, max_lines=2):
    &quot;&quot;&quot;Split text into at most max_lines lines, as evenly balanced as possible.&quot;&quot;&quot;
    words = text.split()
    if d.textlength(text, font=f) &lt;= max_width or max_lines == 1 or len(words) &lt; 2:
        return [text]
    best = None
    for i in range(1, len(words)):  # try every split point, keep the most balanced
        a, b = &quot; &quot;.join(words[:i]), &quot; &quot;.join(words[i:])
        widest = max(d.textlength(a, font=f), d.textlength(b, font=f))
        if best is None or widest &lt; best[0]:
            best = (widest, [a, b])
    return best[1]


def draw_scene(scene, index, total, path, brand):
    im = background()
    d = ImageDraw.Draw(im, &quot;RGBA&quot;)
    headline = normalize(scene[&quot;headline&quot;])
    bullets = [normalize(b) for b in (scene.get(&quot;bullets&quot;) or [])][:4]
    if not bullets:  # title / closing card: centred, wrapped to two lines
        f = font(120, &quot;Bold&quot;)
        lines = wrap(d, headline, f, W - 360)
        y = (H - len(lines) * 150) / 2 - 20
        for line in lines:
            d.text(((W - d.textlength(line, font=f)) / 2, y), line, font=f, fill=(255, 255, 255))
            y += 150
    else:
        f = font(92, &quot;Bold&quot;)
        lines = wrap(d, headline, f, W - 320)
        y = 130
        for line in lines:
            d.text((160, y), line, font=f, fill=(255, 255, 255))
            y += 112
        d.rectangle([160, y + 14, 460, y + 22], fill=(120, 160, 255, 255))
        y += 90
        fb = font(60, &quot;Medium&quot;)
        for b in bullets:
            d.ellipse([170, y + 20, 198, y + 48], fill=(120, 160, 255, 255))
            d.text((240, y), b, font=fb, fill=(235, 240, 255))
            y += 120
    if brand:
        d.text((130, H - 100), brand, font=font(34, &quot;Medium&quot;), fill=(160, 190, 255, 200))
    gap, r = 36, 9  # progress dots
    x0 = (W - (total - 1) * gap) / 2
    for i in range(total):
        col = (160, 190, 255, 255) if i == index else (160, 190, 255, 80)
        d.ellipse([x0 + i * gap - r, H - 70 - r, x0 + i * gap + r, H - 70 + r], fill=col)
    im.save(path)


# ---------- 3. Voice and video ----------
def synth(tts, text, path, voice, speed):
    samples, rate = tts.create(text, voice=voice, speed=speed, lang=&quot;en-us&quot;)
    sf.write(str(path), samples, rate)
    return len(samples) / rate


def make_clip(png, wav, dur, out):
    frames = int(dur * FPS)
    vf = (f&quot;zoompan=z='1+0.0002*on':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':d={frames}:s={W}x{H}:fps={FPS},&quot;
          f&quot;fade=t=in:st=0:d=0.4,fade=t=out:st={dur - 0.4:.2f}:d=0.4,format=yuv420p&quot;)
    subprocess.run([&quot;ffmpeg&quot;, &quot;-y&quot;, &quot;-loglevel&quot;, &quot;error&quot;, &quot;-loop&quot;, &quot;1&quot;, &quot;-i&quot;, str(png), &quot;-i&quot;, str(wav),
                    &quot;-t&quot;, f&quot;{dur:.2f}&quot;, &quot;-vf&quot;, vf,
                    &quot;-af&quot;, f&quot;adelay=400,apad,atrim=0:{dur:.2f},afade=t=out:st={dur - 0.4:.2f}:d=0.4&quot;,
                    &quot;-c:v&quot;, &quot;libx264&quot;, &quot;-preset&quot;, &quot;medium&quot;, &quot;-crf&quot;, &quot;18&quot;, &quot;-r&quot;, str(FPS),
                    &quot;-c:a&quot;, &quot;aac&quot;, &quot;-ar&quot;, &quot;44100&quot;, &quot;-b:a&quot;, &quot;192k&quot;, str(out)], check=True)


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument(&quot;brief&quot;, help=&quot;text file describing the video&quot;)
    ap.add_argument(&quot;--out&quot;, default=&quot;video&quot;, help=&quot;output folder&quot;)
    ap.add_argument(&quot;--model&quot;, default=&quot;gpt-oss&quot;, help=&quot;Ollama model that writes the storyboard&quot;)
    ap.add_argument(&quot;--scenes&quot;, type=int, default=5)
    ap.add_argument(&quot;--voice&quot;, default=&quot;am_michael&quot;, help=&quot;Kokoro voice, e.g. am_michael, af_heart, bf_emma&quot;)
    ap.add_argument(&quot;--speed&quot;, type=float, default=1.0, help=&quot;speaking speed, 0.8 slower .. 1.2 faster&quot;)
    ap.add_argument(&quot;--brand&quot;, default=&quot;SmartTutorials.net&quot;, help=&quot;small text at the bottom-left ('' to hide)&quot;)
    ap.add_argument(&quot;--reuse&quot;, action=&quot;store_true&quot;, help=&quot;reuse scenes.json instead of calling the LLM&quot;)
    a = ap.parse_args()

    out = Path(a.out)
    out.mkdir(exist_ok=True)
    sj = out / &quot;scenes.json&quot;
    if a.reuse and sj.exists():
        scenes = json.loads(sj.read_text())
    else:
        print(&quot;Asking the LLM for a storyboard ...&quot;)
        scenes = ask_llm(Path(a.brief).read_text(), a.model, a.scenes)
        sj.write_text(json.dumps(scenes, indent=2, ensure_ascii=False))
    print(json.dumps(scenes, indent=2, ensure_ascii=False))

    tts = Kokoro(str(KOKORO_MODEL), str(KOKORO_VOICES))
    clips = []
    for i, s in enumerate(scenes):
        png, wav, clip = out / f&quot;scene{i}.png&quot;, out / f&quot;voice{i}.wav&quot;, out / f&quot;clip{i}.mp4&quot;
        draw_scene(s, i, len(scenes), png, a.brand)
        dur = synth(tts, for_voice(s[&quot;narration&quot;]), wav, a.voice, a.speed) + 0.4 + (1.2 if i == len(scenes) - 1 else 0.6)
        make_clip(png, wav, dur, clip)
        clips.append(clip)
        print(f&quot;scene {i + 1}/{len(scenes)} done ({dur:.1f}s)&quot;)

    lst = out / &quot;list.txt&quot;
    lst.write_text(&quot;&quot;.join(f&quot;file '{c.name}'\n&quot; for c in clips))
    final = out / &quot;final.mp4&quot;
    subprocess.run([&quot;ffmpeg&quot;, &quot;-y&quot;, &quot;-loglevel&quot;, &quot;error&quot;, &quot;-f&quot;, &quot;concat&quot;, &quot;-safe&quot;, &quot;0&quot;, &quot;-i&quot;, str(lst),
                    &quot;-c&quot;, &quot;copy&quot;, &quot;-movflags&quot;, &quot;+faststart&quot;, str(final)], check=True)
    print(&quot;Wrote&quot;, final)


if __name__ == &quot;__main__&quot;:
    main()
</code></pre>
<h2 id="step-6-make-your-first-video">Step 6. Make your first video</h2>
<p>Write a brief. It is plain text, and the more concrete it is, the better the result:</p>
<pre class="wp-block-code"><code class="language-bash">cd ~/ai-video
cat &gt; brief.txt &lt;&lt;'EOF'
Video title: &quot;5 tips for faster Docker builds&quot; for SmartTutorials.net.
Audience: developers who already use Docker.
Cover: layer caching, multi-stage builds, .dockerignore, slim base images, BuildKit.
Closing: more tutorials on smarttutorials.net.
EOF
</code></pre>
<p>Run the script:</p>
<pre class="wp-block-code"><code class="language-bash">./venv/bin/python make_video.py brief.txt --out docker_tips --scenes 6
</code></pre>
<p>You will see the storyboard printed as JSON, then <code>scene 1/6 done</code>, and finally <code>Wrote docker_tips/final.mp4</code>. Open the file in any video player.</p>
<div style="overflow-x:auto">
<table>
<thead>
<tr>
<th>Option</th>
<th>Meaning</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>--scenes N</code></td>
<td>Number of scenes. The first is a title card and the last is a call to action.</td>
<td>5</td>
</tr>
<tr>
<td><code>--model NAME</code></td>
<td>Any model you pulled with <code>ollama pull</code></td>
<td><code>gpt-oss</code></td>
</tr>
<tr>
<td><code>--voice NAME</code></td>
<td>Kokoro voice</td>
<td><code>am_michael</code></td>
</tr>
<tr>
<td><code>--speed X</code></td>
<td>Speaking speed, from 0.8 (slower) to 1.2 (faster)</td>
<td>1.0</td>
</tr>
<tr>
<td><code>--brand TEXT</code></td>
<td>Small label at the bottom left. Use <code>''</code> to hide it.</td>
<td><code>SmartTutorials.net</code></td>
</tr>
<tr>
<td><code>--reuse</code></td>
<td>Skip the LLM and re-render from the saved <code>scenes.json</code></td>
<td>off</td>
</tr>
</tbody>
</table>
</div>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=2400%2C1400&#038;ssl=1" alt="Six frames from the finished video: a title card followed by five scenes with headlines and bullet points." class="wp-image-20685" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/07-result-frames.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 6: frames from the video this script made for this tutorial</figcaption></figure>
<h2 id="step-7-polish-the-video-with-the-edit-loop">Step 7. Polish the video with the edit loop</h2>
<p>The LLM gives you a good first draft. Treat it as a draft.</p>
<ol>
<li>Open <code>docker_tips/scenes.json</code> in a text editor.</li>
<li>Fix the wording: shorten bullets, correct facts, make the narration sound like something you would say aloud.</li>
<li>Render again without calling the LLM:</li>
</ol>
<pre class="wp-block-code"><code class="language-bash">./venv/bin/python make_video.py brief.txt --out docker_tips --reuse
</code></pre>
<p>Because the slow LLM step is skipped, a re-render takes under a minute. Repeat until you are happy.</p>
<figure class="wp-block-image size-full"><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=2400%2C1400&#038;ssl=1" alt="The edit loop: generate with the LLM, edit scenes.json by hand, re-render with the reuse option, and repeat until the video is right." class="wp-image-20684" width="2400" height="1400" loading="lazy" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?w=2400&amp;ssl=1 2400w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=300%2C175&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=1024%2C597&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=768%2C448&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=1536%2C896&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/06-edit-loop.png?resize=2048%2C1195&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /><figcaption>Figure 7: draft with the LLM, polish by hand</figcaption></figure>
<p><strong>Tips for narration that sounds human:</strong></p>
<ul>
<li>Use contractions: &#8220;you&#8217;ll&#8221;, &#8220;it&#8217;s&#8221;.</li>
<li>Keep sentences short, one idea each.</li>
<li>Spell out symbols and acronyms the way you say them, or add them to <code>PRONUNCIATION</code>.</li>
<li>Try <code>--speed 0.95</code> for a calmer pace.</li>
<li>Listen to a few voices before you commit to one.</li>
</ul>
<h2 id="troubleshooting">Troubleshooting</h2>
<div style="overflow-x:auto">
<table>
<thead>
<tr>
<th>Problem</th>
<th>Fix</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>Connection refused</code> on port 11434</td>
<td>Ollama is not running. Start it with <code>ollama serve</code>, or <code>sudo systemctl start ollama</code>.</td>
</tr>
<tr>
<td><code>The LLM did not return valid JSON after 3 attempts</code></td>
<td>Use a larger model or fewer scenes. Small models struggle with strict JSON.</td>
</tr>
<tr>
<td>First run is slow</td>
<td>The model loads into memory once. Later runs are faster while Ollama keeps it loaded.</td>
</tr>
<tr>
<td><code>OSError: cannot open resource</code> for the font</td>
<td>Check that <code>fonts/InstrumentSans.ttf</code> exists, or change <code>FONT</code> at the top of the script.</td>
</tr>
<tr>
<td><code>set_variation_by_name</code> error</td>
<td>Your font is not a variable font. Remove that line in <code>font()</code>.</td>
</tr>
<tr>
<td>The voice mispronounces a word</td>
<td>Add the word to <code>PRONUNCIATION</code>, or respell it in <code>scenes.json</code>, then run with <code>--reuse</code>.</td>
</tr>
<tr>
<td>Out of GPU memory</td>
<td>Ollama offloads to system RAM automatically, so it still works, only slower. Or use a smaller model.</td>
</tr>
<tr>
<td>Text is cut off at the screen edge</td>
<td>Shorten the headline or bullet. Headlines wrap to two lines, bullets do not wrap.</td>
</tr>
</tbody>
</table>
</div>
<h3 id="other-systems">Other systems</h3>
<p>The Python and ffmpeg parts are cross-platform. On macOS, install ffmpeg with Homebrew. On Windows, install it with winget. Install Ollama from <a href="https://ollama.com" rel="noopener">ollama.com</a>. I have not tested these systems, so expect small differences in the setup commands.</p>
<h2 id="make-it-yours">Make it yours</h2>
<ul>
<li><strong>Branding.</strong> Change the gradient colors in <code>background()</code> or paste your logo onto each slide with Pillow&#8217;s <code>Image.paste</code>.</li>
<li><strong>Another language.</strong> Kokoro includes voices for several languages. Choose a matching voice and <code>lang</code> code.</li>
<li><strong>Background music.</strong> Add a quiet, royalty-free track in the final ffmpeg step with the <code>amix</code> filter.</li>
<li><strong>Let the LLM design more.</strong> Add fields such as <code>accent_color</code> to the JSON and read them in <code>draw_scene</code>.</li>
<li><strong>Real footage.</strong> Replace the slide images with screen recordings and keep the same voice and timing logic.</li>
<li><strong>Subtitles.</strong> You already have each scene&#8217;s narration and duration, so an <code>.srt</code> file takes only a few lines.</li>
</ul>
<h2 id="frequently-asked-questions">Frequently asked questions</h2>
<h3 id="can-i-create-a-video-with-a-local-llm-without-a-gpu">Can I create a video with a local LLM without a GPU?</h3>
<p>Yes. Ollama can run models on the CPU, and Kokoro runs on the CPU too. Everything is slower without a GPU, so pick a smaller model if the storyboard step takes too long.</p>
<h3 id="is-this-really-free-and-offline">Is this really free and offline?</h3>
<p>After the one-time downloads, yes. Nothing is sent to a cloud service and no API key is needed. Ollama, ffmpeg, Pillow and Kokoro are open source projects, but check each license if you plan to use the videos commercially.</p>
<h3 id="which-llm-works-best">Which LLM works best?</h3>
<p>I tested <code>gpt-oss</code> (20B), which follows the JSON format well but is slow on a small GPU. Smaller models are faster but less reliable, so check their output before you rely on them.</p>
<h3 id="can-i-use-my-own-voice-or-a-different-language">Can I use my own voice or a different language?</h3>
<p>Kokoro ships with many voices and several languages, and you can switch with <code>--voice</code>. Using recordings of your own voice would mean replacing the text-to-speech step with your own WAV files. This tutorial does not cover that.</p>
<h3 id="can-it-generate-real-video-footage">Can it generate real video footage?</h3>
<p>No. It builds slide-style videos with motion and voice-over. To add real footage, replace the slide images with screen recordings and keep the same timing logic.</p>
<h2 id="summary">Summary</h2>
<p>You now have a complete offline video pipeline. An open LLM writes the script, Kokoro speaks it, Pillow draws it and ffmpeg assembles it, with no API keys, no subscription and no data leaving your machine.</p>
<p>The video at the top of this article was made with exactly this script. If you build something with it, tell me in the comments what you would like to see added next. For more hands-on guides, browse the <a href="https://smarttutorials.net/llm-engineering/">LLM Engineering</a> and <a href="https://smarttutorials.net/llms/">LLMs</a> sections of this site.</p>
<p><em>Build with AI. Ship agents.</em></p>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/create-narrated-video-local-llm/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20677</post-id>	</item>
		<item>
		<title>ARTEX: what the FBI’s warning about LLM-driven intrusions means for your apps</title>
		<link>https://smarttutorials.net/artex-fbi-flash-llm-driven-intrusions/</link>
					<comments>https://smarttutorials.net/artex-fbi-flash-llm-driven-intrusions/#respond</comments>
		
		<dc:creator/>
		<pubDate>Mon, 16 Nov 2026 07:57:43 +0000</pubDate>
				<category><![CDATA[AI Security]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20667</guid>

					<description><![CDATA[The FBI says an open-source, LLM-driven pentest framework is being used for real intrusions. Here is how it works and which controls matter.]]></description>
										<content:encoded><![CDATA[<h2 id="1-what-happened">1. What happened</h2>
<p>On 13 November 2026 the FBI published FLASH-20261113-001 about ARTEX, an open-source, LLM-driven penetration-testing framework. The FBI says attackers have used it since at least August 2026 to automate steps from reconnaissance to data exfiltration. It also reports that some intrusions went from initial targeting to privileged access in under three hours. Check Point Research had published its own analysis of criminal use on 5 November.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/01-timeline.png?ssl=1" alt="Timeline from release to FLASH" /></p>
<h2 id="2-why-it-matters-to-builders">2. Why it matters to builders</h2>
<p>The FBI says ARTEX is good at overlooked systems: partner portals, mobile backends, sales-support tools and legacy services. The flaws it lists are not new: unsigned SAML assertions, SSRF, SQL injection, missing API authentication, hardcoded admin passwords in JavaScript bundles. The change is speed and scale. The FBI says small groups can run several campaigns at once.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/02-surface.png?ssl=1" alt="Peripheral systems named by the FBI" /></p>
<h2 id="3-how-it-works">3. How it works</h2>
<p>ARTEX is a multi-agent platform written in Go. An operator describes a goal in natural language, and agents turn it into commands. It has no model of its own and calls external LLM providers. The FBI lists Claude, GPT, DeepSeek, GLM, Grok and Kimi. Check Point examined 10 misconfigured operator consoles and reports that most attacks ran autonomously after the goal was set. It also reports that Chinese models dominated, with the DeepSeek Flash family most common. In its account, guardrails triggered once, when an operator used an Anthropic model, and the operator then switched models.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/03-architecture.png?ssl=1" alt="How an ARTEX run is put together" /></p>
<h2 id="4-what-to-do">4. What to do</h2>
<p>The FBI recommendations, in short:</p>
<ol type="1">
<li><strong>Shrink exposure.</strong> Inventory every internet-facing app, including peripheral ones. Keep cloud admin, Kudu/SCM and other management interfaces on trusted networks.</li>
<li><strong>Tighten identity.</strong> Apply least privilege to application permissions and watch for credentials added to apps.</li>
<li><strong>Guard the app layer.</strong> Rate limits, server-side authorization, no verbose errors to anonymous users, and alerts on sequential record lookups.</li>
<li><strong>Hunt secrets.</strong> Scan repositories, images and pipelines for embedded secrets and rotate any you find.</li>
</ol>
<p>For detection, the FLASH lists outbound calls to LLM API hosts as an indicator. This one-liner is illustrative and untested; adapt it to your log format:</p>
<div class="sourceCode" id="cb1">
<pre class="sourceCode bash"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="co"># illustrative: count egress log lines per LLM API host named in the FLASH</span></span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">grep</span> <span class="at">-E</span> <span class="st">&#39;api\.anthropic\.com|api\.deepseek\.com|open\.bigmodel\.cn|api\.x\.ai&#39;</span> egress.log <span class="kw">|</span> <span class="fu">awk</span> <span class="st">&#39;{print $1}&#39;</span> <span class="kw">|</span> <span class="fu">sort</span> <span class="kw">|</span> <span class="fu">uniq</span> <span class="at">-c</span></span></code></pre>
</div>
<p>Many legitimate tools call these hosts, so treat a hit as a lead, not proof. The FBI itself says to vet indicators before acting.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/04-controls.png?ssl=1" alt="Controls mapped to entry points" /></p>
<h2 id="5-what-is-still-unknown-and-takeaways">5. What is still unknown, and takeaways</h2>
<p>The FLASH says the 1,600+ exposed consoles are a floor, not a total. The &#8220;under three hours&#8221; figure describes some intrusions, not a typical one, and the 2,250-tenant ConnectWise figure measures downstream access, not confirmed damage. We do not know how widely the forks are deployed.</p>
<p><img data-recalc-dims="1" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2026/11/05-known-unknown.png?ssl=1" alt="Established versus not established" /></p>
<p><strong>Takeaways (our opinion):</strong> attackers are getting a cheap labour multiplier, not a new exploit class, so basic hygiene on forgotten apps pays off. Assume anything internet-facing is probed continuously.</p>
<h2 id="sources">Sources</h2>
<ul>
<li>FBI, FLASH-20261113-001, &#8220;Threat Overview of ARTEX Autonomous Penetration Testing Framework&#8221;, 13 Nov 2026: <a href="https://www.ic3.gov/CSA/2026/261113.pdf">ic3.gov/CSA/2026/261113.pdf</a></li>
<li>Check Point Research, &#8220;Hacking on Autopilot: Inside ARTEX Cybercrime Campaigns&#8221;, 5 Nov 2026: <a href="https://research.checkpoint.com/2026/hacking-on-autopilot-inside-artex-cybercrime-campaigns/">research.checkpoint.com</a></li>
<li>Cyber Security News coverage of the FLASH, 14 Nov 2026: <a href="https://cybersecuritynews.com/fbi-reveals-hackers-artex-ai-usage">cybersecuritynews.com</a></li>
</ul>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/artex-fbi-flash-llm-driven-intrusions/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20667</post-id>	<enclosure length="541176" type="application/pdf" url="https://www.ic3.gov/CSA/2026/261113.pdf"/><itunes:explicit>no</itunes:explicit><itunes:subtitle>The FBI says an open-source, LLM-driven pentest framework is being used for real intrusions. Here is how it works and which controls matter.</itunes:subtitle><itunes:summary>The FBI says an open-source, LLM-driven pentest framework is being used for real intrusions. Here is how it works and which controls matter.</itunes:summary><itunes:keywords>AI Security</itunes:keywords></item>
		<item>
		<title>Step-by-Step Guide: Deploying a Laravel Application to AWS Lightsail Ubuntu Instance (EC2) Using GitHub Actions CI/CD</title>
		<link>https://smarttutorials.net/step-by-step-guide-deploying-a-laravel-application-to-aws-lightsail-ubuntu-instance-ec2-using-github-actions-ci-cd/</link>
					<comments>https://smarttutorials.net/step-by-step-guide-deploying-a-laravel-application-to-aws-lightsail-ubuntu-instance-ec2-using-github-actions-ci-cd/#respond</comments>
		
		<dc:creator><![CDATA[muni]]></dc:creator>
		<pubDate>Tue, 20 Jun 2023 08:12:59 +0000</pubDate>
				<category><![CDATA[AWS]]></category>
		<category><![CDATA[GitHub]]></category>
		<category><![CDATA[Laravel]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20547</guid>

					<description><![CDATA[In this blog post topic focuses on providing a comprehensive step-by-step guide to deploying a Laravel application to an AWS Lightsail Ubtuntu instance using Github Actions for continuous integration and continuous deployment (CI/CD). Technical Requirements AWS Lightsail Instance Github (your code must be github repo) Laravel App I am using following Github repo. For this [&#8230;]]]></description>
										<content:encoded><![CDATA[
<p class="wp-block-paragraph">In this blog post topic focuses on providing a comprehensive step-by-step guide to deploying a Laravel application to an AWS Lightsail Ubtuntu instance using Github Actions for continuous integration and continuous deployment (CI/CD).</p>



<div class="wp-block-image"><figure class="aligncenter size-full"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/Deploying-a-Laravel-Application-to-AWS-Lightsail-Ubuntu-Instance-EC2-Using-GitHub-Actions-CICD.png?ssl=1"><img data-recalc-dims="1" decoding="async" width="742" height="530" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/Deploying-a-Laravel-Application-to-AWS-Lightsail-Ubuntu-Instance-EC2-Using-GitHub-Actions-CICD.png?resize=742%2C530&#038;ssl=1" alt="Step-by-Step Guide: Deploying a Laravel Application to AWS Lightsail Ubuntu Instance (EC2) Using GitHub Actions CI/CD" class="wp-image-20563" title="Step-by-Step Guide: Deploying a Laravel Application to AWS Lightsail Ubuntu Instance (EC2) Using GitHub Actions CI/CD" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/Deploying-a-Laravel-Application-to-AWS-Lightsail-Ubuntu-Instance-EC2-Using-GitHub-Actions-CICD.png?w=742&amp;ssl=1 742w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/Deploying-a-Laravel-Application-to-AWS-Lightsail-Ubuntu-Instance-EC2-Using-GitHub-Actions-CICD.png?resize=300%2C214&amp;ssl=1 300w" sizes="(max-width: 742px) 100vw, 742px" /></a></figure></div>



<h2 class="wp-block-heading">Technical Requirements</h2>



<ol class="wp-block-list"><li>AWS Lightsail Instance</li><li>Github (your code must be github repo)</li><li>Laravel App</li></ol>



<blockquote class="wp-block-quote is-layout-flow wp-block-quote-is-layout-flow"><p>I am using following Github repo.</p></blockquote>



<figure class="wp-block-embed is-type-rich is-provider-embed wp-block-embed-embed"><div class="wp-block-embed__wrapper">
<div class="github-embed github-embed-repository github-logo-mark">    <p>        <a href="https://github.com/muni2explore/gen-quiz" target="_blank">			<strong>				Quiz Gen			</strong>		</a>		<br>        <a href="https://github.com/muni2explore/gen-quiz" target="_blank">https://github.com/muni2explore/gen-quiz</a><br>        <a href="https://github.com/muni2explore/gen-quiz/network" target="_blank">2</a> forks.<br>        <a href="https://github.com/muni2explore/gen-quiz/stargazers" target="_blank">0</a> stars.<br>        <a href="https://github.com/muni2explore/gen-quiz/issues" target="_blank">1</a> open issues.<br>        <details open>            <summary>Recent commits:</summary>            <ul class="github_commits">                                    <li class="github_commit">                        <a href="https://github.com/nxgeninventors/gen-quiz/commit/7f0d18fcb432bfe9bc37bf7190d8603aea36328b" target="_blank">Quiz start logic</a>, muni                    </li>                                    <li class="github_commit">                        <a href="https://github.com/nxgeninventors/gen-quiz/commit/509df0046ba7452da3a2e69e6ee93929166f3eab" target="_blank">Fix</a>, muni                    </li>                                    <li class="github_commit">                        <a href="https://github.com/nxgeninventors/gen-quiz/commit/ad8088324defbfa217226f5d8ab554affd7d2cba" target="_blank">removed laravel sqlite db</a>, muni                    </li>                                    <li class="github_commit">                        <a href="https://github.com/nxgeninventors/gen-quiz/commit/d7a9af4f72b66e3c4b3dfda64549bd3816bdc9da" target="_blank">removed laravel sqlite db</a>, muni                    </li>                                    <li class="github_commit">                        <a href="https://github.com/nxgeninventors/gen-quiz/commit/e5755c7668dc8f2a71474cea7e91e48dae8ec93f" target="_blank">Fixes</a>, muni                    </li>                            </ul>        </details>    </p></div>
</div></figure>



<p class="wp-block-paragraph">For this tutorial <strong>I am going assume you have already have Github repository for your Laravel application</strong>.</p>



<h2 class="wp-block-heading">Configuring AWS  Access Key &amp; Secret</h2>



<p class="wp-block-paragraph">To establish communication with AWS via command line or programmatically, we need <strong>Access Key &amp; Secret access</strong> key. </p>



<p class="wp-block-paragraph">First login into your AWS console using your username and password.  Then go to <strong>IAM -&gt; Users </strong>section.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?ssl=1"><img data-recalc-dims="1" decoding="async" width="1024" height="214" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list.jpg?resize=1024%2C214&#038;ssl=1" alt="" class="wp-image-20548" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?resize=1024%2C214&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?resize=300%2C63&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?resize=768%2C161&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?resize=1536%2C322&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-scaled.jpg?resize=2048%2C429&amp;ssl=1 2048w" sizes="(max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS IAM User List</figcaption></figure>



<p class="wp-block-paragraph">Next Click on <strong>Add users </strong>button on the top right to create user.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="304" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1.jpg?resize=1024%2C304&#038;ssl=1" alt="" class="wp-image-20549" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?resize=1024%2C304&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?resize=300%2C89&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?resize=768%2C228&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?resize=1536%2C456&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-user-step-1-scaled.jpg?resize=2048%2C609&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS Create User &#8211; Step 1</figcaption></figure>



<p class="wp-block-paragraph">Now enter user name you want create and click <strong>Next</strong> button to continue.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="429" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2.jpg?resize=1024%2C429&#038;ssl=1" alt="" class="wp-image-20551" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?resize=1024%2C429&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?resize=300%2C126&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?resize=768%2C322&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?resize=1536%2C644&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-user-set-permissions-setp-2-scaled.jpg?resize=2048%2C859&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>Set Permission to User </figcaption></figure>



<p class="wp-block-paragraph">Now don&#8217;t provide any permission and click on <strong>Next</strong> button to continue.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="512" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user.jpg?resize=1024%2C512&#038;ssl=1" alt="" class="wp-image-20552" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?resize=1024%2C512&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?resize=300%2C150&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?resize=768%2C384&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?resize=1536%2C768&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-review-create-user-scaled.jpg?resize=2048%2C1025&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS Review Create User</figcaption></figure>



<p class="wp-block-paragraph">Now click <strong>Create user </strong>button to create new user.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="221" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user.jpg?resize=1024%2C221&#038;ssl=1" alt="" class="wp-image-20553" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?resize=1024%2C221&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?resize=300%2C65&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?resize=768%2C166&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?resize=1536%2C331&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-iam-users-list-with-new-user-scaled.jpg?resize=2048%2C442&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS User list with New User</figcaption></figure>



<p class="wp-block-paragraph">Now click on newly created user &#8216;depoy-laravel-app&#8217; to create <strong>Access key &amp; Secret</strong>.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="602" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret.jpg?resize=1024%2C602&#038;ssl=1" alt="" class="wp-image-20554" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?resize=1024%2C602&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?resize=300%2C176&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?resize=768%2C452&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?resize=1536%2C903&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/create-aws-access-key-secret-scaled.jpg?resize=2048%2C1204&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>Create AWS Access Key &amp; Secret</figcaption></figure>



<p class="wp-block-paragraph">Now click <strong>Create access key </strong>button to create <strong>access key &amp; secret</strong>.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="671" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation.jpg?resize=1024%2C671&#038;ssl=1" alt="" class="wp-image-20555" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?resize=1024%2C671&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?resize=300%2C197&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?resize=768%2C503&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?resize=1536%2C1007&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-create-access-key-recommendation-scaled.jpg?resize=2048%2C1342&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS Create Access Key Recomendation</figcaption></figure>



<p class="wp-block-paragraph">Now check check the radio button &#8216;<em>I understand the above recommendation and want to proceed to create an access key</em>&#8216;. And click on &#8216;<strong>Next</strong>&#8216; continue.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="243" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key.jpg?resize=1024%2C243&#038;ssl=1" alt="" class="wp-image-20556" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?resize=1024%2C243&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?resize=300%2C71&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?resize=768%2C182&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?resize=1536%2C364&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/aws-add-tag-to-create-access-key-scaled.jpg?resize=2048%2C486&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>Set description tag</figcaption></figure>



<p class="wp-block-paragraph">Finally click &#8216;Create access key&#8217; button to create a key.</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="492" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key.jpg?resize=1024%2C492&#038;ssl=1" alt="" class="wp-image-20559" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?resize=1024%2C492&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?resize=300%2C144&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?resize=768%2C369&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?resize=1536%2C739&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/AWS-access-secret-key-scaled.jpg?resize=2048%2C985&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>AWS Retrieve Access key.<br><br>Now note down the <strong>Access key &amp; Secret access key</strong>. (Click on show link to get <meta charset="utf-8"><strong>Secret access key</strong>). Or Click on the <strong>Download .csv file</strong> to get download the access key and secret key in CSV file format.</figcaption></figure>



<h2 class="wp-block-heading">Configuring GitHub Secrets:</h2>



<p class="wp-block-paragraph">Now login into Github.com account and access your repository settings page to configure all the secrets that are required for CI &amp; CD deployment. I have added following secrets by clicking on &#8216;<strong>New repository secret</strong>&#8216; button. (AWS ACCESS KEY, ACCESS SECRET, PEM FILE, AWS HOSTNAME &amp; USERNAME).</p>



<figure class="wp-block-image size-large"><a href="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?ssl=1"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="730" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables.jpg?resize=1024%2C730&#038;ssl=1" alt="" class="wp-image-20560" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?resize=1024%2C730&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?resize=300%2C214&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?resize=768%2C547&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?resize=1536%2C1094&amp;ssl=1 1536w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2023/06/github-action-secret-variables-scaled.jpg?resize=2048%2C1459&amp;ssl=1 2048w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></a><figcaption>Github Action Secret Variables</figcaption></figure>



<h2 class="wp-block-heading">Defining the Deployment Workflow:</h2>



<p class="wp-block-paragraph">Now create &#8216;<strong>.github</strong>&#8216; folder in the project root directory, and add &#8216;<strong>workflows</strong>&#8216; folder in it. Now add <strong>deploy-aws.yml </strong>file in it.</p>



<pre class="wp-block-code"><code>├── .github
│&nbsp;&nbsp; └── workflows
│&nbsp;&nbsp;     └── deploy-aws.yml
├── .gitignore
├── README.md
├── app
```</code></pre>



<p class="wp-block-paragraph">Now following content to it.</p>



<pre class="wp-block-code"><code>name: Quiz

on:
  push:
    branches:
    - main

jobs:
  deploy:
    runs-on: ubuntu-latest

    steps:
    - name: Checkout
      uses: actions/checkout@v2

    - name: Install Build dependencies
      run: |
        sudo apt-get update
        sudo apt-get install -y git php composer
      
    - name: Set up Node.js 18.12.0
      uses: actions/setup-node@v2
      with:
        node-version: '18.12.0'
    
    - name: Configure AWS Credentials
      uses: aws-actions/configure-aws-credentials@v1
      with:
        aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
        aws-secret-access-key: ${{ secrets.AWS_ACCESS_SECRET_KEY }}
        aws-region: eu-west-2

    - name: Install Frontend dependencies
      run: |
        npm install
    
    - name: Build Frontend Code
      run: npm run build

    - name: Build Backend Code
      run: composer install --prefer-dist

    - name: Deploy Laravel code
      env:
          PRIVATE_KEY: ${{ secrets.AWS_PEM_KEY  }}
          HOSTNAME : ${{ secrets.HOSTNAME  }}
          USER_NAME : ${{ secrets.USER_NAME  }}
          ENV : ${{ secrets.ENV  }}
      run: |
        echo "$ENV" &gt; .env
        echo "$PRIVATE_KEY" &gt; private_key &amp;&amp; chmod 600 private_key
        rsync -r --exclude 'node_modules' --exclude 'storage' --exclude '.git/' --delete-after -e "ssh -o StrictHostKeyChecking=no -i private_key" . ${USER_NAME}@${HOSTNAME}:/var/www/nxgeninventors.com/quiz/

        ssh -o StrictHostKeyChecking=no -i private_key ${USER_NAME}@${HOSTNAME} '
            cd /var/www/nxgeninventors.com/simba/ &amp;&amp; 
            sudo chmod -R 777 storage &amp;&amp; 
            php artisan storage:link 
        '
        
        
```</code></pre>



<p class="wp-block-paragraph">When ever code pushed to <strong>main</strong> branch, it trigger job. </p>



<p class="wp-block-paragraph">Step1: Checkout codebase from main branch</p>



<p class="wp-block-paragraph">Step 2: Install build dependencies that are required for this project (git, php, composer). </p>



<p class="wp-block-paragraph"><meta charset="utf-8">Step 3: Setting up Node version 18.12.0. </p>



<p class="wp-block-paragraph"><meta charset="utf-8">Step 4: Configure AWS Credentials (Access key &amp; Secret). </p>



<p class="wp-block-paragraph"><meta charset="utf-8">Step 5: Install Frontend dependencies. </p>



<p class="wp-block-paragraph">Step 6: Build Frontend Code</p>



<p class="wp-block-paragraph"><meta charset="utf-8">Step 7: Finally Deploy Laravel build code to the server, and set appropriate permission.</p>
]]></content:encoded>
					
					<wfw:commentRss>https://smarttutorials.net/step-by-step-guide-deploying-a-laravel-application-to-aws-lightsail-ubuntu-instance-ec2-using-github-actions-ci-cd/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20547</post-id>	</item>
		<item>
		<title>Dynamic List Show More &amp; Less Feature Using VueJS</title>
		<link>https://smarttutorials.net/dynamic-list-show-more-less-feature-using-vuejs/</link>
		
		<dc:creator><![CDATA[muni]]></dc:creator>
		<pubDate>Tue, 04 Aug 2020 00:53:28 +0000</pubDate>
				<category><![CDATA[JAVASCRIPT]]></category>
		<category><![CDATA[VueJS]]></category>
		<category><![CDATA[javascript]]></category>
		<category><![CDATA[vuejs]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20266</guid>

					<description><![CDATA[We display the array of objects using v-for directive, where content of the each item is large. So by default we will display excerpt of the content with show more button. When user clicks on the show more button, we will display large content with show less button. let see how we are going to implement this for this dynamic list.]]></description>
										<content:encoded><![CDATA[
<p class="wp-block-paragraph">This is continuation of my previous tutorial on <a aria-label="undefined (opens in a new tab)" href="https://smarttutorials.net/add-show-more-less-feature-using-vuejs/" target="_blank" rel="noreferrer noopener nofollow">Add Show More &amp; Less feature using VueJS</a>. Before continuing this tutorial, please have a look at my previous tutorial on this <a href="https://smarttutorials.net/add-show-more-less-feature-using-vuejs/">Show More &amp; Less</a>.</p>



<p class="wp-block-paragraph">We display the array of objects using <strong>v-for</strong> directive, where content of the each item is large. So by default we will display <strong>excerpt</strong> of the content with <strong>show more button</strong>. When user clicks on the <strong>show more</strong> button, we will display <strong>large content</strong> with <strong>show less</strong> button. let see how we are going to implement this for this dynamic list.</p>



<div class="text-center"><a class="btn btn-default btn-success" title="Show More &amp; Less using VueJS Demo" href="//demo.smarttutorials.net/show-more-Less-feature-using-vuejs/dynamic.html" target="_blank" rel="noopener noreferrer">Dynamic List Show More &amp; Less using VueJS Demo</a></div>



<figure class="wp-block-image size-large text-center"><img data-recalc-dims="1" loading="lazy" decoding="async" width="700" height="300" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/Dynamic-List-Show-More-Less-Feature-Using-VueJS.jpg?resize=700%2C300&#038;ssl=1" alt="Dynamic List Show More &amp; Less Feature Using VueJS" class="wp-image-20271" title="Dynamic List Show More &amp; Less Feature Using VueJS" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/Dynamic-List-Show-More-Less-Feature-Using-VueJS.jpg?w=700&amp;ssl=1 700w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/Dynamic-List-Show-More-Less-Feature-Using-VueJS.jpg?resize=300%2C129&amp;ssl=1 300w" sizes="auto, (max-width: 700px) 100vw, 700px" /></figure>


<div class="embed-responsive embed-responsive-16by9" style="margin: 20px auto;"><iframe class="embed-responsive-item" src="https://www.youtube.com/embed/eixLgOnKSFk" allowfullscreen="allowfullscreen"></iframe></div>
<div class="embed-responsive embed-responsive-16by9" style="margin: 20px auto;"><iframe class="embed-responsive-item" src="https://www.youtube.com/embed/W7wqGVzn1aA" allowfullscreen="allowfullscreen"></iframe></div>
<pre><code class="language language-html">
&lt;script src="https://unpkg.com/vue"&gt;&lt;/script&gt;
&lt;div id="app"&gt;
    &lt;h1 class="title"&gt;{{title}}&lt;/h1&gt;

    &lt;div&gt;
        &lt;ul&gt;
            &lt;li :key="key" v-for="(list, key) in lists"&gt;
                &lt;!-- Excerpt section --&gt;
                &lt;div class="mb-1 gray-bg" v-show="!list.Flag"&gt;
                    &lt;p class="mb-1"&gt;{{list.about | summary }}&lt;/p&gt;
                    &lt;p class="btn" @click="toggler(list, true);"&gt;Show More&lt;/p&gt;
                &lt;/div&gt;
                &lt;!-- Excerpt section end --&gt;

                &lt;!-- Content section --&gt;
                &lt;div class="mb-1 gray-bg" v-show="list.Flag"&gt;
                    &lt;p class="mb-1" v-html="list.about"&gt;&lt;/p&gt;
                    &lt;p class="btn" @click="toggler(list, false);"&gt;Show Less&lt;/p&gt;
                &lt;/div&gt;
                &lt;!-- Content section end--&gt;
            &lt;/li&gt;
        &lt;/ul&gt;
    &lt;/div&gt;
&lt;/div&gt;
&lt;script&gt;
    var app = new Vue({
                data: function(){
                    return {
                        title: "Dynamic List Show More &amp; Less Feature Using VueJS",
                        lists: [
                            {
                                "about": "Velit adipisicing quis mollit consequat ullamco veniam ipsum in laborum excepteur veniam nostrud qui amet. Quis ipsum nostrud reprehenderit consectetur consectetur consequat id. Ipsum nostrud magna aliquip nisi ea nisi Lorem ut cillum nisi eiusmod tempor. Aute incididunt commodo ea deserunt in quis esse eiusmod voluptate nisi veniam anim.\r\n&lt;br/&gt;Esse eiusmod veniam sunt reprehenderit magna in. Eu officia sunt laborum qui irure ex ad excepteur ea duis quis esse sint occaecat. Laborum ut et dolor labore. Exercitation Lorem culpa quis sint sint exercitation elit ea aute culpa ex. Dolore Lorem consequat dolore consequat reprehenderit voluptate officia pariatur qui dolor ut Lorem labore quis. Sint proident id consequat cupidatat nostrud. Dolore sit labore reprehenderit sit cupidatat voluptate laboris incididunt.\r\n&lt;br/&gt;Qui amet consectetur anim proident dolore nisi dolore. Veniam dolore fugiat deserunt proident officia dolor in tempor ut nulla dolore elit ea labore. Ut anim esse do reprehenderit adipisicing. Et in Lorem incididunt nostrud et. Cillum quis enim nisi ad cillum.\r\n&lt;br/&gt;"
                            },
                            {
                                "about": "Officia veniam Lorem labore eu sint do anim pariatur cupidatat officia fugiat aliqua sunt culpa. Nulla aute voluptate aliquip ea Lorem. Anim laboris dolor velit culpa eu deserunt qui sunt eu in aute. Ut voluptate anim labore in eiusmod aliquip do ea id magna et do et.\r\n&lt;br/&gt;Excepteur sunt eiusmod cillum laboris aliqua elit commodo. Ut anim duis laboris pariatur laborum esse ad aute culpa consequat est occaecat eiusmod qui. Aute sunt laboris officia consectetur nostrud mollit dolore incididunt id. Qui duis elit deserunt culpa ut labore id esse. Laboris veniam duis commodo dolor sit ex id ut occaecat. Aliquip exercitation culpa veniam voluptate occaecat adipisicing ullamco voluptate culpa et dolor fugiat ut aliqua. Sunt id commodo id ut dolore magna non dolor cupidatat anim laboris nulla.\r\n&lt;br/&gt;Nulla aliqua laboris velit eu ex ullamco irure labore id et aliqua. Eiusmod aliqua minim incididunt adipisicing do cillum velit quis non ut voluptate sint velit culpa. Qui cillum tempor excepteur Lorem tempor occaecat laborum magna magna pariatur labore amet est. Eu nulla enim Lorem ex est adipisicing elit velit cupidatat amet do reprehenderit aliquip. Cupidatat magna excepteur laboris officia exercitation anim Lorem tempor. Occaecat ex pariatur aliqua enim.\r\n&lt;br/&gt;"
                            }
                            ]
                    }
                },
                filters: {
                    summary: function(text) {
                        return text.substring(0, 150)+' ...';
                    }
                },
                methods:{
                    toggler(obj, flag){
                        this.$set(obj, 'Flag', flag);
                    }
                }
            });
    app.$mount("#app");        
&lt;/script&gt;
</code></pre>
<p>I have added CDN link of Vue.js v2.6.11, next created VueJS app by instantiating Vue. Using v-for directive listed the array of Objects. Where each item will have two section.&nbsp;</p>
<ol>
<li>Section one &#8211; excerpt data with show more button</li>
<li>Section two &#8211; large data with show less button</li>
</ol>
<p>At a time either one of the section is visible by <strong>dynamic Flag attribute</strong> on each item. I made this <strong>dynamic Flag attribute </strong>is a reactive one using <strong>$set</strong> method. So whenever user clicks on either show more/less button, the toggler method triggered that will either true/false value to display more/less content based on the <strong>Flag value</strong>.&nbsp;</p>
<div class="text-center"><a class="btn btn-default btn-success" style="padding: 15px 50px;" title="Download show more &amp; less VueJS Script" href="//www.smarttutorials.net/subscribers.php?id=84" target="_blank" rel="noopener noreferrer"> Download show more &amp; less VueJS Script </a><p></p>
<p><a class="btn btn-default btn-danger non_premium_user" style="padding: 15px 50px;" rel="nofollow">Instant Download This Script </a></p>
</div>


<p class="wp-block-paragraph">By default <strong>less content</strong> is displayed using <strong>v-show</strong> directive, where <strong>v-show</strong> directive checks </p>


<pre><code class="language-html">v-show="!list.Flag"</code></pre>


<p class="wp-block-paragraph">Initially <strong>Flag property </strong>on <strong>list object is undefined</strong>. Show <strong>!list.Flag</strong> becomes <strong>true</strong>, so less content automatically visible by default.</p>



<p class="wp-block-paragraph">Please leave comment, If you guys have any doubts.</p>
]]></content:encoded>
					
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20266</post-id>	</item>
		<item>
		<title>Add Show More &amp; Less feature using VueJS</title>
		<link>https://smarttutorials.net/add-show-more-less-feature-using-vuejs/</link>
		
		<dc:creator><![CDATA[muni]]></dc:creator>
		<pubDate>Mon, 03 Aug 2020 04:51:28 +0000</pubDate>
				<category><![CDATA[JAVASCRIPT]]></category>
		<category><![CDATA[VueJS]]></category>
		<category><![CDATA[vuejs]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20256</guid>

					<description><![CDATA[I had splitted this tutorial onto two parts. Simple Add Show More &#38; Less feature using VueJS Dynamic List Show More &#38; Less Feature Using VueJS Show More &#38; Less using VueJS Demo Step 1: Create index.html file and add the following scripts in it. &#60;script src="https://unpkg.com/vue"&#62;&#60;/script&#62; &#60;div id="app"&#62; &#60;h1 class="title"&#62;{{title}}&#60;/h1&#62; &#60;div&#62; &#60;div class="mb-1 gray-bg" [&#8230;]]]></description>
										<content:encoded><![CDATA[
<p class="wp-block-paragraph">I had splitted this tutorial onto two parts.</p>



<ol class="wp-block-list"><li>Simple Add Show More &amp; Less feature using VueJS</li><li>Dynamic List Show More &amp; Less Feature Using VueJS</li></ol>



<figure class="wp-block-image size-large"><img data-recalc-dims="1" loading="lazy" decoding="async" width="700" height="300" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/show-more-less-feature-using-vuejs.jpg?resize=700%2C300&#038;ssl=1" alt="Show More &amp; Less feature using VueJS" class="wp-image-20263" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/show-more-less-feature-using-vuejs.jpg?w=700&amp;ssl=1 700w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/08/show-more-less-feature-using-vuejs.jpg?resize=300%2C129&amp;ssl=1 300w" sizes="auto, (max-width: 700px) 100vw, 700px" /></figure>


<div class="text-center"><a class="btn btn-default btn-success" title="Show More &amp; Less using VueJS Demo" href="https://demo.smarttutorials.net/show-more-Less-feature-using-vuejs/" target="_blank" rel="noopener noreferrer">Show More &amp; Less using VueJS Demo</a></div>


<p class="wp-block-paragraph"><div class="embed-responsive embed-responsive-16by9" style="margin: 20px auto;"><iframe class="embed-responsive-item" src="https://www.youtube.com/embed/eixLgOnKSFk" allowfullscreen="allowfullscreen"></iframe></div>
<div class="embed-responsive embed-responsive-16by9" style="margin: 20px auto;"><iframe class="embed-responsive-item" src="https://www.youtube.com/embed/W7wqGVzn1aA" allowfullscreen="allowfullscreen"></iframe></div></p>



<p class="wp-block-paragraph">Step 1:</p>


<p><!-- /wp:post-content --></p>
<p><!-- wp:paragraph --></p>
<p>Create index.html file and add the following scripts in it.</p>
<p><!-- /wp:paragraph --></p>
<pre><code class="language language-html">
&lt;script src="https://unpkg.com/vue"&gt;&lt;/script&gt;
&lt;div id="app"&gt;
    &lt;h1 class="title"&gt;{{title}}&lt;/h1&gt;
    &lt;div&gt;
        &lt;div class="mb-1 gray-bg" v-show="!showFlag"&gt;
            &lt;p class="mb-1"&gt;Lorem ipsum dolor sit amet consectetur adipisicing elit.&lt;/p&gt;
            &lt;p class="btn" @click="showFlag=true;"&gt;Show More&lt;/p&gt;
        &lt;/div&gt;

        &lt;div class="mb-1 gray-bg" v-show="showFlag"&gt;
            &lt;p class="mb-1"&gt;Velit adipisicing quis mollit consequat ullamco veniam ipsum in laborum excepteur veniam nostrud qui amet. Quis ipsum nostrud reprehenderit consectetur consectetur consequat id. Ipsum nostrud magna aliquip nisi ea nisi Lorem ut cillum nisi eiusmod tempor. Aute incididunt commodo ea deserunt in quis esse eiusmod voluptate nisi veniam anim.&lt;br/&gt;&lt;br/&gt;Esse eiusmod veniam sunt reprehenderit magna in. Eu officia sunt laborum qui irure ex ad excepteur ea duis quis esse sint occaecat. Laborum ut et dolor labore. Exercitation Lorem culpa quis sint sint exercitation elit ea aute culpa ex. Dolore Lorem consequat dolore consequat reprehenderit voluptate officia pariatur qui dolor ut Lorem labore quis. Sint proident id consequat cupidatat nostrud. Dolore sit labore reprehenderit sit cupidatat voluptate laboris incididunt.&lt;br/&gt; &lt;br/&gt;Qui amet consectetur anim proident dolore nisi dolore. Veniam dolore fugiat deserunt proident officia dolor in tempor ut nulla dolore elit ea labore. Ut anim esse do reprehenderit adipisicing. Et in Lorem incididunt nostrud et. Cillum quis enim nisi ad cillum.&lt;br/&gt;&lt;/p&gt;
            &lt;p class="btn" @click="showFlag=false;"&gt;Show Less&lt;/p&gt;
        &lt;/div&gt;
    &lt;/div&gt;
&lt;/div&gt;
&lt;script&gt;
    var app = new Vue({
                data: function(){
                    return {
                        title: "Simple Show More &amp; Less Feature Using VueJS",
                        showFlag: false,
                    }
                }
            });
    app.$mount("#app");        
&lt;/script&gt;
</code></pre>
<p><!-- wp:paragraph --></p>
<p>Where I declared <code><strong>showFlag</strong></code> variable, which will help us to track show more &amp; less status. By default <strong>less text</strong> and <strong>Show more button</strong> will show. When user clicks on Show more button <strong>showFlag</strong> set to <strong>true</strong>. </p>
<p><!-- /wp:paragraph --></p>
<p><!-- wp:paragraph --></p>
<p>Now using <strong>v-show </strong>directive, we will <strong>show more text section with show less button</strong>. Meanwhile show less text section with show more button will get hidden. When user clicks on show less button <strong>showFlag</strong> set to <strong>false</strong>. Now v-show directive will hide more text section &amp; show less text section.</p>
<p><!-- /wp:paragraph --></p>
<div class="text-center">
    <a class="btn btn-default btn-success" style="padding: 15px 50px;" title="Download show more &amp; less VueJS Script" href="//www.smarttutorials.net/subscribers.php?id=84" target="_blank" rel="noopener noreferrer"> Download show more &amp; less VueJS Script </a><p></p>
<p><a class="btn btn-default btn-danger non_premium_user" style="padding: 15px 50px;" rel="nofollow">Instant Download This Script </a></p>
</div>
<p><!-- wp:paragraph --></p>
<p>Please leave comment, If you guys have any doubts.</p>
<p><!-- /wp:paragraph --></p>]]></content:encoded>
					
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20256</post-id>	</item>
		<item>
		<title>How to create a unique wedding invitation online?</title>
		<link>https://smarttutorials.net/how-to-create-unique-wedding-invitation-online/</link>
		
		<dc:creator><![CDATA[muni]]></dc:creator>
		<pubDate>Thu, 16 Apr 2020 07:05:19 +0000</pubDate>
				<category><![CDATA[How Things Work]]></category>
		<guid isPermaLink="false">https://smarttutorials.net/?p=20208</guid>

					<description><![CDATA[If you are Jack &#38; spouse is Rose. How about having an online invitation like JackWedsRose.com? Wouldn&#8217;t you be interested in having a unique wedding invitation like that? Read more to find out how There are many services available online to create wedding invitations online, but creating something impressive takes time and effort. If you [&#8230;]]]></description>
										<content:encoded><![CDATA[
<p class="wp-block-paragraph">If you are Jack &amp; spouse is Rose. How about having an online invitation like <strong><a href="http://jackwedsrose.com/">JackWedsRose.com</a></strong>? Wouldn&#8217;t you be interested in having a unique wedding invitation like that? Read more to find out how</p>



<p class="wp-block-paragraph">There are many services available online to create wedding invitations online, but creating something impressive takes time and effort. </p>



<p class="wp-block-paragraph">If you have all the time in the world you can just craft one perfectly yourself, else you need assistance. </p>



<p class="wp-block-paragraph">Everyone sends an invitation to mobile devices nowadays. Mobile device has evolved so much in recent years, but do you think e-invitations evolved?</p>



<p class="wp-block-paragraph">All invitations you receive are usually an image or link in Whatsapp.  If it&#8217;s an image it contains details written in the text which are hard to read. <br>If its link, it&#8217;s is usually large to remember.</p>



<p class="wp-block-paragraph">How about having an invitation like <strong><a href="http://jackwedsrose.com">JackWedsRose.com</a></strong>?  Wouldn&#8217;t it be easy? </p>



<figure class="wp-block-image size-large"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1024" height="551" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/ShareImg_eweddingInvite.jpg?resize=1024%2C551&#038;ssl=1" alt="Social share invitation preview" class="wp-image-20211" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/ShareImg_eweddingInvite.jpg?resize=1024%2C551&amp;ssl=1 1024w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/ShareImg_eweddingInvite.jpg?resize=300%2C161&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/ShareImg_eweddingInvite.jpg?resize=768%2C413&amp;ssl=1 768w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/ShareImg_eweddingInvite.jpg?w=1060&amp;ssl=1 1060w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></figure>



<p class="wp-block-paragraph">Don&#8217;t you think it will be unique? </p>



<p class="wp-block-paragraph">But who has the time to do all the work involved?  Services like <a href="https://eweddinginvite.com">eWeddingInvite.com</a> come as a rescue for you who needs to do something unique.</p>



<p class="wp-block-paragraph">They collect only a few details to make a complete wedding website &amp; a unique online wedding invitation for you in minutes.</p>



<p class="wp-block-paragraph">Yes, it&#8217;s possible. </p>



<p class="wp-block-paragraph">We know people are so terrible at remembering the dates, that&#8217;s why they have smartphones. So let us send them <strong>smart invitations</strong></p>



<h2 class="wp-block-heading">How an invitation can be smart?</h2>



<p class="wp-block-paragraph">First, it can be smart enough to sit just in the device home screen without the need for any installation. </p>



<div class="wp-block-image"><figure class="aligncenter size-large"><img data-recalc-dims="1" loading="lazy" decoding="async" width="500" height="376" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Invitaion_added_to_home_screen.jpg?resize=500%2C376&#038;ssl=1" alt="Smart wedding invitation" class="wp-image-20213" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Invitaion_added_to_home_screen.jpg?w=500&amp;ssl=1 500w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Invitaion_added_to_home_screen.jpg?resize=300%2C226&amp;ssl=1 300w" sizes="auto, (max-width: 500px) 100vw, 500px" /></figure></div>



<p class="wp-block-paragraph">Now when your invitee opens it, it opens your invitation with a quick access menu at the bottom. </p>



<div class="wp-block-image"><figure class="aligncenter size-large is-resized"><img data-recalc-dims="1" loading="lazy" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Easy_for_your_guests_to_come_to_the_event.jpg?resize=393%2C499&#038;ssl=1" alt="Mobile Wedding Invitation" class="wp-image-20214" width="393" height="499" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Easy_for_your_guests_to_come_to_the_event.jpg?w=500&amp;ssl=1 500w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Easy_for_your_guests_to_come_to_the_event.jpg?resize=236%2C300&amp;ssl=1 236w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Easy_for_your_guests_to_come_to_the_event.jpg?resize=300%2C381&amp;ssl=1 300w" sizes="auto, (max-width: 393px) 100vw, 393px" /></figure></div>



<p class="wp-block-paragraph">It has <strong>Add to Calendar</strong> button, remember it&#8217;s a smartphone with built-in calendar and maps. </p>



<p class="wp-block-paragraph">He can just add the event to the calendar and their device takes care of reminding him of the event a day before the event. </p>



<p class="wp-block-paragraph">Now he gets a reminder about your event &amp; he decides to drive to your event venue, he has your invite saved on his home screen, he can just open it and click <strong>&#8220;Get Directions&#8221;</strong></p>



<p class="wp-block-paragraph">It will get him the driving directions to the venue in his maps application. </p>



<p class="wp-block-paragraph">Also your invitee can just RSVP to let you know that he isn&#8217;t coming. </p>



<p class="wp-block-paragraph">Don&#8217;t you think it&#8217;s smart? It saves you &amp; your invitees a lot of time. It&#8217;s convenience. </p>



<p class="wp-block-paragraph">Now imagine you sent a traditional printed invitation or an image that has the venue details. </p>



<p class="wp-block-paragraph">It&#8217;s a human tendency to forget the date &amp; even if remembered, he has to search for the venue or to give you a call for the directions. All these hassles are taken away when you send a smart invitation. </p>



<h2 class="wp-block-heading">How easy it is to create such a unique wedding invitation? </h2>



<figure class="wp-block-image size-large"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1010" height="447" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Required_details_eweddinginvite.png?resize=1010%2C447&#038;ssl=1" alt="Minimum details required to create online invitation" class="wp-image-20215" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Required_details_eweddinginvite.png?w=1010&amp;ssl=1 1010w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Required_details_eweddinginvite.png?resize=300%2C133&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Required_details_eweddinginvite.png?resize=768%2C340&amp;ssl=1 768w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></figure>



<p class="wp-block-paragraph">These are the minimum details that are required to build an awesome invitation for you. </p>



<p class="wp-block-paragraph">Now it&#8217;s time to do something even more. </p>



<p class="wp-block-paragraph">You see you just build a brand online with a unique name like <strong>JackWedsRose.com</strong>. Let&#8217;s use it to spread your love story.</p>



<h3 class="wp-block-heading"><strong>1. Attach Pre &amp; Post Wedding Photoshoots</strong></h3>



<p class="wp-block-paragraph">Attach pictures to your invite (wedding website now), so that it tells a story of your love to the world. After the wedding, it becomes a wedding picture gallery for every one of your guests. Update your pictures any number of times in a year. Upload up to 500 pictures from any device. It works even on a smart TV.</p>



<h3 class="wp-block-heading"><strong>2. Write your love story in words</strong></h3>



<p class="wp-block-paragraph">We believe you have a fantastic story to tell the world about your journey together till the wedding, express yourself in your own words. The world wants to hear.</p>



<figure class="wp-block-image size-large"><img data-recalc-dims="1" loading="lazy" decoding="async" width="1003" height="700" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Attach_Pictures_videos_story.png?resize=1003%2C700&#038;ssl=1" alt="Build your wedding brand by attaching pictures and videos" class="wp-image-20219" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Attach_Pictures_videos_story.png?w=1003&amp;ssl=1 1003w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Attach_Pictures_videos_story.png?resize=300%2C209&amp;ssl=1 300w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/Attach_Pictures_videos_story.png?resize=768%2C536&amp;ssl=1 768w" sizes="auto, (max-width: 1000px) 100vw, 1000px" /></figure>



<h3 class="wp-block-heading"><strong>3. Attach your favorite videos</strong></h3>



<p class="wp-block-paragraph">The adventure you did together recorded on your vacation? Attach the video to the invitation (or) attach any of your favorite video together (or) Just record a video from your phone camera &amp; speak to your guests. It plays to everyone from within invitation in full screen.</p>



<h3 class="wp-block-heading"><strong>4. Attach the YouTube live stream of the event.</strong></h3>



<p class="wp-block-paragraph">Not every one of the loved ones can attend the event in person. If you are one of the few people who host it online, just attach it to your invite.</p>



<h2 class="wp-block-heading">Get Invitation QR code. </h2>



<p class="wp-block-paragraph">It&#8217; time to make it even easier for people who see your invitation online. </p>



<div class="wp-block-image"><figure class="aligncenter size-large is-resized"><img data-recalc-dims="1" loading="lazy" decoding="async" src="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/JackWedsRose_QR_Code.png?resize=353%2C353&#038;ssl=1" alt="QR code for your invitation" class="wp-image-20217" width="353" height="353" srcset="https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/JackWedsRose_QR_Code.png?w=150&amp;ssl=1 150w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/JackWedsRose_QR_Code.png?resize=125%2C125&amp;ssl=1 125w, https://i0.wp.com/smarttutorials.net/wp-content/uploads/2020/04/JackWedsRose_QR_Code.png?resize=100%2C100&amp;ssl=1 100w" sizes="auto, (max-width: 353px) 100vw, 353px" /></figure></div>



<p class="wp-block-paragraph">Scanning this QR code on mobile makes your name to display on the mobile screen such as JackWedsRose.com </p>



<p class="wp-block-paragraph">Did we say that the invitation works in all devices that have a browser? It even works on a smart TV. </p>



<h2 class="wp-block-heading"><a rel="noreferrer noopener" aria-label="Create Invitation Now  (opens in a new tab)" href="https://eweddinginvite.com" target="_blank">Create Invitation Now </a>→<a rel="noreferrer noopener" aria-label="Create Invitation Now  (opens in a new tab)" href="https://eweddinginvite.com" target="_blank"> </a></h2>



<p class="wp-block-paragraph">It&#8217;s free, You don&#8217;t need to give your email/phone to use our services ever. You can just choose to be anonymous.</p>



<p class="wp-block-paragraph">You&#8217;ll get an&nbsp;<strong>invite key</strong>&nbsp;once your invitation is made which can be used to login (or) <strong>A unique link i</strong>s assigned to your account which<strong> can be bookmarked to your device home screen for easy access.</strong></p>
]]></content:encoded>
					
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">20208</post-id>	</item>
	</channel>
</rss>