Contents
AI FAQ Generator — Plugixa FAQ
Generate FAQs automatically from a topic, a URL, or a PDF/document. Uses OpenAI or Google Gemini behind the scenes.
Setup
1 · Get an API key
Pick a provider:
- OpenAI — sign up at platform.openai.com, generate an API key.
- Google Gemini — get a key at aistudio.google.com.
2 · Configure the plugin
Go to Plugixa FAQ → Settings → AI Generator.
| Field | Notes |
|---|---|
| Enable AI Generator | Master toggle. |
| Provider | openai or google. |
| API key | Encrypted at rest. Never displayed after save. |
| Model | See Models. |
| Temperature | 0.0 (deterministic) to 1.0 (creative). 0.7 is a good default. |
| Max tokens | Response length cap. 2000 is typical. |
| Default language | Target language for generated content (e.g., “English”, “French”). |
3 · Test the connection
Click Test connection. The plugin makes a minimal request and reports success, API error, or rate-limit.
Models
OpenAI
| Model | Cost | Speed | Quality | Recommended use |
|---|---|---|---|---|
gpt-4o-mini |
$ | Fast | Good | Default — bulk generation |
gpt-4o |
$$ | Fast | Excellent | Flagship content |
gpt-4-turbo |
$$ | Medium | Excellent | Legacy — prefer 4o |
gpt-4 |
$$$ | Slow | Excellent | Rarely needed |
gpt-3.5-turbo |
$ | Fast | OK | Low-budget draft |
o1 / o3 |
$$$$ | Slow | Reasoning | Deep analysis — overkill for FAQs |
Models are fetched dynamically from OpenAI, so new releases appear automatically.
Google Gemini
| Model | Cost | Speed | Quality | Notes |
|---|---|---|---|---|
gemini-1.5-flash |
$ | Fast | Good | Default |
gemini-1.5-pro |
$$ | Medium | Excellent | Long-context |
gemini-pro |
$ | Fast | Good | Legacy |
Four ways to generate
From a topic
Enter a topic (e.g., “shipping policy”) and a count, then click Generate. The AI produces N question/answer pairs. Optional: provide context or a tone guide.
Topic: "Shipping to Europe"
Count: 8
Tone: Friendly, professional
Target audience: E-commerce customers
From a URL
Paste a URL. The plugin:
- Fetches the page (via
class-url-scraper.php). - Strips HTML and boilerplate, extracting the main content.
- Sends the content to the AI with instructions to generate FAQs.
Best for turning an existing blog post, documentation page, or product description into FAQs.
From a PDF or document
Upload a PDF, DOCX, or TXT. The plugin:
- Parses text from the document (via
class-document-parser.php+ PDF Parser library). - Extracts key content.
- Generates FAQs.
Common use: turning a product manual into a structured FAQ section.
File size limit: 20 MB (configurable via plugixa_faq_ai_max_file_size filter).
Category generation
Generate a full category of FAQs from a single prompt:
- Click Generate category.
- Name the category (e.g., “Returns”).
- Specify the count and optional context.
- Review and import.
Review and import
After generation, the FAQs appear in a preview table:
For each row:
- Regenerate title — rewrite just the question.
- Regenerate content — rewrite just the answer.
- Edit inline — click to edit either field.
- Reject — remove from the batch.
Click Import to save the remaining rows as draft FAQs.
Multilingual generation
If Multilingual is active, the Target language field appears. The plugin generates in the specified language and sets language_code on the imported FAQs.
For translation of existing FAQs: open an FAQ → Translate with AI → pick target language. The plugin asks the AI to translate (not paraphrase), then creates a new translation linked to the source via translation_group.
REST API
All endpoints require Pro license + manage_options:
| Method | Endpoint | Description |
|---|---|---|
POST |
/wp-json/plugixa-faq/v1/ai-generator/generate-faq |
Single Q&A from a prompt. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/generate-faqs |
Batch. Body: { topic, count, language?, tone?, context? }. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/generate-from-url |
Body: { url, count, language? }. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/generate-from-file |
Multipart with the uploaded file. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/generate-category |
Category-level generation. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/regenerate-title |
Rewrite a single question. |
POST |
/wp-json/plugixa-faq/v1/ai-generator/regenerate-content |
Rewrite a single answer. |
Hooks
| Hook | Type | Description |
|---|---|---|
plugixa_faq_before_ai_generate |
action | Before a generation request. Args: topic, provider, count. |
plugixa_faq_after_ai_generate |
action | After a successful generation. Args: faqs, topic, provider. |
plugixa_faq_ai_generated_faq |
filter | Modify a single generated item. |
plugixa_faq_ai_generated_faqs |
filter | Modify the whole batch. |
plugixa_faq_ai_provider_config |
filter | Override provider settings at runtime (e.g., per-category temperature). |
Cost estimation
Rough costs per batch of 10 FAQs with gpt-4o-mini at default settings:
- ~5,000 input tokens (topic + instructions)
- ~2,500 output tokens (10 Q&A pairs)
- Cost: ~$0.003 USD
The URL / PDF flows add input tokens proportional to document length.
Troubleshooting
“API error 401”
API key is wrong or revoked. Regenerate in the provider dashboard and re-save.
“API error 429”
Rate-limited. Wait, or switch to a higher-tier plan with the provider.
Generated FAQs are generic
- Raise the specificity of your topic (“Shipping to EU countries” → “Shipping to France: customs and taxes”).
- Provide a Context paragraph with brand voice, specific product details, etc.
- Lower temperature to 0.5 for less variation, or raise to 0.9 for more.
URL scraping returned nothing
Some sites block scrapers. Try saving the page as PDF and uploading that instead.
Related
- FAQ Management
- Categories
- AI settings — provider, keys, models, temperature
- Multilingual
- Import / Export — bulk import from external sources