Author Archive

Follow this checklist:

1. ✅  Make sure your your listings have AI embeddings generated
2. ✅ Make sure your listings have keyword-rich descriptions!
3. ✅ Try “Query Expansion”  feature
4. ✅ Lower  “Minimum Match Percentage” setting
5. ✅ Clear cache in AI Chat & Search → Developer & Debug Options → Clear Cache. Maybe you searched for listing using keyword X then results got cached and you don’t see

AI search understands meaning, so it finds relevant results even when the exact words aren’t in your listings. That’s why it can match “romantic dinner spot” with fine dining restaurants or “dog grooming” with pet salons.

But it’s not magic — it works from the text in your listings. If a listing has almost no description, or uses very unusual wording, the AI may miss it. Also, in rare cases, it might return a result that feels related but isn’t exactly what you meant.

In short: it’s far better than keyword search, but like any search, it depends on good, descriptive content.

This setting determines how closely a listing must match the search query to appear in
results.

Setting Range: 0-100 (Default: 65)
Impact on Search Results:
– Lower Values (40-60): More results, some may be less relevant
– Medium Values (65-75): Balanced relevance and quantity (recommended)
– Higher Values (80-95): Fewer but highly relevant results

Example:
– Query: “Italian restaurant”
– 50% threshold: Returns pizza places, pasta shops, Mediterranean food
– 80% threshold: Only returns specifically Italian restaurants

Query expansion uses AI to understand and broaden search terms for better results.

Example:
– Original query: “coffee shop”
– Expanded query might include: “café”, “espresso bar”, “coffee house”

Trade-offs:
– ✅ Enabled: Better coverage, finds more results but not necessary always relevant (depends on minimal match settings)
– ❌ Disabled: Faster processing, more literal searches

After installing plugin, adding Open AI api key and clicking “Start Training” the plugin sends structured listing data to OpenAI’s / Gemini embeddings model to create vector embeddings: listing name, category, location,  amenities, features, description, FAQ, pricing/menu, user reviews (positive only, rating ≥3.0)

When this happens:
– Manual regeneration via admin panel
– Daily cron job (listeo_ai_update_embeddings) for changed listings
– When a listing is created/updated (if auto-update enabled)

What happens when user is searching?
– Listings data is not sent again when user searches for something
– User’s search query text is sent to OpenAI to generate an embedding vector
– This vector is compared locally against stored embeddings (no additional API calls)

On average, importing 100 businesses costs $2-4 in Google API fees. This includes:
✅ Business details (name, address, phone, website)
✅ Ratings and reviews
✅ Photos (if enabled)

The exact cost depends on which search method and fields you choose to import.

Google returns a maximum of 60 results per search query and plugin limit importing more than 20 listings at once for safety (lower quality hosting mail fail to import 20+ listings per batch).
For example, to import 120 listings:

1. Run first import: “Restaurants in Manhattan” (up to 20 results)
2. Run second import: “Restaurants in Brooklyn” (up to 20 results)
3. Run third import: “Restaurants in Queens” (up to 20 results)

The plugin automatically prevents duplicate imports by checking the Google Place ID.

Each variation will return different results.

Google Places API has built-in limitations:

• Maximum 20 listings per page
• Maximum 3 pages per search (60 listings total)
• No way to access results beyond the first 60

This is a hard limit set by Google, not the plugin. Even if your search query matches 500 restaurants, Google will only return the first 60. To import more listings, you must use different, more specific search queries (by neighborhood, cuisine type, or business category).

Example: Searching “restaurants in New York” might match thousands of places, but Google only returns 60. Instead, search “Italian restaurants in Manhattan” then “Chinese restaurants in Brooklyn” to access different sets of results.

Google returns the same results in the same order for each search. If you’ve already imported some listings, the plugin must:

1. Search through results you’ve already imported
2. Skip duplicates automatically
3. Continue searching until it finds enough new listings

Google’s API behavior:

Always returns results in the same order for the same query
No way to say “skip the first 40 results” or “give me results 41-60”
No offset parameter – only pagetoken for next 20

Example:
Search: “Coffee shops in London”
– Page 1: Results 1-20 (always the same)
– Page 2: Results 21-40 (always the same)
– Page 3: Results 41-60 (always the same)
– Max 60 results total

Second import run:
– Page 1: Same results 1-20 (duplicate check)
– Page 2: Same results 21-40 (duplicate check)
– Page 3: Same results 41-60 (finally, potential new ones)

Outcome: only couple of listings added due to existing duplicates but made 60 API calls 

Downloading photos:
⚠️ Violate Google’s Terms of Service
✅ No ongoing costs

Displaying from Google:
✅ Compliant with Terms of Service
❌ Costs ~$0.05 per photo per page view
❌ Can get expensive quickly (100 listings = $15/day at 100 views each)

The Places API shows up to 5 recent reviews per location. These are cached for 48 hours to comply with Google’s API Terms and to reduce usage costs. Once the cache expires, fresh reviews are fetched and displayed automatically when a user visits the listing page.