AI Chatbot 🤖

The chatbot selects tools based on the user’s query. It analyzes the question and automatically picks the right search method. The AI understands user intent and applies relevant filters while searching your website content. For example, asking “show me services for marketing” makes the AI identify services related to marketing and pull relevant pages or posts.

🔍 Tool Selection Logic:

1. Search Products (Included in Pro)
– For products to BUY/SHOP (if WooCommerce active)
– Examples: “wireless headphones under $100”, “on-sale laptops”
– Searches: E-commerce products

2. Search Universal Content (Included in Pro)
– For general website content
– Searches: Blog posts, pages, documentation, policies, guides

3. Follow-up questions
– Answers from conversation context
– The chatbot remembers previous search results

Additional tool:

4. Product Details (Included in Pro)
AI asked about specific listing can call “get product details” tool to extract following data from the listing:
a. Product name and description
b. Price (regular + sale)
c. SKU
d. Categories
e. Attributes (color, size, etc.)
f. Stock status

What filters AI can apply when searching?

For Products (search_products):
– price_min / price_max – Price range
– in_stock – Only available products
– on_sale – Only discounted products
– category – Product category filter
– rating – Minimum rating (1-5)

With OpenAI’s $5 credit balance (that’s minimal amount), you can expect approximately following amount of conversations before needing to add more credits.

~ 3000 with GPT-5 Mini
~ 9000 with GPT-4.1 Nano
~ 3000 with GPT-4.1 Mini
~ 600 with GPT-4.1

Note: These numbers are approximate.

The real reason ChatGPT feels instant is streaming – words appear as generated. We use GPT via API and script needs to wait for the complete response. Also keep in mind that searching/fetching listing data needs to be processed in the background – that adds latency aswell.

Unfortunately no, at least not yet. What you can do is simply copy content from PDF and create a page/blog post with its content then add it to training data.

Pros

✅ Price! Free or one-time $39 vs enterprise solutions like Chatbot.com ($600+/year)
✅ Runs directly on your WordPress website
✅ You control your OpenAI API costs

Limitations

MySQL database which WordPress uses, lacks native vector search – all similarity calculations run in PHP so search speed depends on your server CPU and number of items.

✅ Best for: Up to 5,000 data training items (with description ~500 words each)
⚠️ Not ideal for: Sites with 5,000+ items, very high traffic, or hundreds of long-form pages/articles (3,000+ words each)

Recommendation: Perfect for small-to-medium directory or e-commerce sites. For enterprise needs (10,000+ items, instant search), use enterprise solution with dedicated vector database. 🙂