Troubleshooting and FAQ

Troubleshooting And Faq is the focus of this documentation page. Common issues (404 assets, API errors, rate limits) and frequently asked questions. Follow the sections below to configure the feature and use it in your WordPress workflow.

Solutions to common issues and frequently asked questions about SmartyPress AI Engine.

Common Issues

API Key Not Working

• Verify the key is correct (no extra spaces)
• Check your provider account has credits/balance
• Open the provider card in Settings and click Save Provider Settings — the plugin tests the connection automatically
• Check if your region requires a proxy (OpenAI)

“Provider Not Found” Error

This means no API key is configured for the selected provider, or the provider is unavailable (error: Provider not found or not configured).

• Go to Settings and add a key for at least one provider
• Make sure the provider is selected as Default Provider

Rate Limit Errors (429)

You are sending too many requests. Solutions:

• Wait a few seconds and try again
• Switch to a different provider temporarily
• For bulk generation, retry failed items from the job controls; some providers (for example OpenRouter) also retry rate-limited requests automatically

Permalink Notice

If you see a notice about permalinks, go to Settings → Permalinks and select any structure other than “Plain”. Save changes.

Debug Logging

To troubleshoot API issues:

1. Go to SmartyPress AI → Settings.
2. Enable Enable Debug Logging under Debug Settings.
3. Optionally enable Also log successful requests for full request/response logging.
4. Reproduce the issue.
5. Open logs via the View API Logs link in Debug Settings, or use Logs in the SmartyPress AI sidebar navigation (#/logs).

Logs include: timestamp, provider, model, request data, response, and any errors. They are automatically deleted after 7 days.

Frequently Asked Questions

Is SmartyPress AI Engine free?

Yes, completely free and open source. You only pay for API usage to your chosen AI provider.

How much does content generation cost?

• Title: ~$0.001–$0.01
• Full article (500–1000 words): ~$0.02–$0.10
• DeepSeek is 10–50x cheaper than OpenAI

What languages are supported?

AI models support all major languages. Specify the language in Settings or per-generation. Plugin interface is available in English and Russian.

Can I use it with WooCommerce?

Yes. Enable Products under the Enabled Post Types setting. Works with product descriptions, titles, and short descriptions.

Is my data safe?

Yes. Data is sent to AI providers only when you click Generate. No background requests, no tracking, no analytics. API keys stored in your WordPress database. All communication uses HTTPS.

What happens when I uninstall?

All plugin settings and API keys are deleted. Generated content (posts, pages, images) is kept — it is your content.

Can I limit who can use AI features?

Yes, the plugin respects WordPress capabilities:

• edit_posts — required for Magic Wand and Content Generation
• publish_posts — required for Bulk Generation
• upload_files — required for Image ALT Generator
• manage_options — required for Settings

How does SEO Optimization work?

The SEO Optimization module reads failing SEO tests from Rank Math (or uses the built-in analyzer), then generates targeted AI fixes for each issue — keyword placement, density, readability, content length, and meta fields. You review the proposed changes in a diff view and apply them with one click. Go to SmartyPress AI → Components to enable the module, then open any post in Gutenberg and use Fix SEO Errors from the SmartyPress AI Writer menu, or the Fix SEO errors with AI / Fix errors button injected into the Rank Math or Yoast SEO sidebar panel.

Can I generate ALT text for images in bulk?

Yes. The Image ALT Generator module supports bulk processing of your entire Media Library. First, index your library, then select images (or filter by “Missing ALT”), and start a bulk generation job. The module uses AI vision to analyze each image and generates ALT text, captions, titles, and descriptions. You can also enable auto-generation for newly uploaded images. See the Image ALT Generator documentation for full details.

What is OpenRouter and why should I use it?

OpenRouter is an AI model aggregator that gives you access to 200+ models from dozens of providers (Meta Llama, Mistral, Google Gemini, Anthropic, and more) through a single API key. It is useful when you want to try different models without managing multiple provider accounts, need access to specialized models (e.g., web search, vision), or want to find the cheapest model for a specific task. In SmartyPress, configure your OpenRouter API key in Settings and select which text and image models to enable.

Why don’t I see YandexGPT or GigaChat in Settings?

Yandex and GigaChat providers are only visible when your WordPress site locale is set to ru_RU (Russian). These providers are designed for the Russian market. To enable them, go to Settings → General → Site Language and select “Русский”. After saving, the Yandex and GigaChat provider cards will appear in SmartyPress AI Settings.

Troubleshooting And Faq Workflow Checklist

The troubleshooting and faq workflow should be treated as a repeatable process, not a one-time setting. Start by confirming that the SmartyPress AI Engine module related to this page is enabled, then check the default provider, model, language, and post type settings before you run the feature on production content. This keeps generated output predictable and makes it easier to compare results between OpenAI, DeepSeek, OpenRouter, Yandex GPT, and GigaChat. Use this checklist whenever you document, test, or train another editor on Troubleshooting and FAQ. It helps keep the setup aligned with WordPress permissions, Rank Math SEO fields, and the editorial workflow used by your site. If a result looks different from what you expected, repeat the same checklist with a smaller prompt and a lower temperature before changing global settings.

1. Confirm that the required SmartyPress AI module is enabled in the Components screen.
2. Open Settings, open a provider card under AI Providers, enter a valid API key, and click Save Provider Settings (the plugin tests the connection automatically).
3. Choose the model that fits the task: fast models for drafts, premium models for final marketing copy, and web-search models for research.
4. Review the output language, temperature, max tokens, and prompt variables before generating content.
5. Save the result as a draft first, then review headings, links, facts, and SEO fields before publishing.

Recommended Settings

For most troubleshooting and faq tasks, start with a balanced model such as GPT-4o Mini, GPT-4o, DeepSeek V4 Flash, or a carefully selected OpenRouter model. Keep temperature around 0.5 to 0.8 for documentation and tutorials, because these pages need clarity more than experimentation. Increase temperature only when you need more creative headlines, introductions, or alternative wording. Use a clear default language and keep prompt variables consistent across articles. For documentation pages, a neutral or professional writing tone usually works best. If the generated result is too short, increase the number of sections or paragraphs per section rather than asking the model to “write more” after the fact. Structured settings create more stable output and make Troubleshooting and FAQ easier to reproduce later.