AIProperty Phuket

Live Phuket, Thailand real-estate catalogue: ~5,800 homes for sale and ~7,800 long-term rentals across 15 zones, plus development projects.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

Search Properties: Structured search of Phuket properties for sale with hard filters. Full parity with the website catalog filter. district, property_type, view, ownership and completion accept a sing
Semantic Search: Semantic search over the catalog + Voyage knowledge base (~17k chunks). Listings are searched DIRECTLY against the vector index here (no rate limit, full completeness + pagination, mu
Get Property: Full details for a single listing by its id (e.g. from search results). Returns the listing's attributes plus fazwaz_id, fazwaz_url (canonical source link) and the public site url. Price

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Live Phuket, Thailand real-estate catalogue: ~5,800 homes for sale and ~7,800 long-term rentals across 15 zones, plus development projects. Structured and semantic search, per-listing detail, and an enumerable district/filter vocabulary so models query the real option space instead of guessing.

Список инструментов сервера (5)

Технические названия из tools/list. Нужны только разработчикам.

search_properties	Structured search of Phuket properties for sale with hard filters. Full parity with the website catalog filter. district, property_type, view, ownership and completion accept a single value, a comma-string, OR an array, and (district/type) are normalized: zone names map to slugs ("Rawai"->rawai), type synonyms collapse to the catalog vocab ("Villas"->Villa). Multi-value = OR. Args: query: Free-text match on title / project / location / id. district: Zone(s) — "rawai", "Nai Harn", ["rawai","nai-harn"], "rawai,kata". property_type: Villa, House, Townhouse, Condo, Apartment, Penthouse (arrays/ synonyms/plurals/any case ok). bedrooms: "1,2" or "4+" or ["2","3"] (Studio = "0"). min_price / max_price: Price bounds in THB. min_area / max_area: Floor-area bounds in sqm. min_price_per_sqm / max_price_per_sqm: ฿/sqm bounds (THB). min_floor / max_floor: Floor-level bounds. min_beach / max_beach: Distance-to-beach bounds in KM (e.g. max_beach=1 = within 1 km of a beach). listing_age: Freshness window — "2w", "2m", "6m", "1y", or "old" (>1y). view: e.g. "Sea View","Pool View","Mountain View" (single/comma/array). ownership: "Foreign Ownership","Thai Ownership","Company","Leasehold" (single/comma/array). furnished: "Furnished", "Partly Furnished" or "Unfurnished". completion: "Off Plan","Completed","Under Construction","Assignment" (array ok). investment_profile: "str" (short-term rental), "ltr" (long-term), "luxury". sort: newest \| price_asc \| price_desc \| area_asc \| area_desc \| sqm_asc \| sqm_desc. page: 1-based page index. Iterate up to `pages` to enumerate ALL matches. limit: Page size (max 100). Returns {total, page, pages, applied_filters, results[], warnings?, diagnostics?}. Each result has fazwaz_id, fazwaz_url, public url, and price in THB.
semantic_search	Semantic search over the catalog + Voyage knowledge base (~17k chunks). Listings are searched DIRECTLY against the vector index here (no rate limit, full completeness + pagination, multi-zone OR). Knowledge sources (projects/developers/guides/districts) are answered via the RAG endpoint. Two modes (both paginate): - mode="rerank" (default): Voyage rerank-2 over the nearest candidates → best-by-meaning ordering. Best for "show me the most relevant few". - mode="filter": COMPLETENESS — every hard-filter match, ranked by similarity, no rerank trim, with `min_score` + `page`/`top_k` paging. For a guaranteed-exhaustive list also consider `search_properties`. district / property_type accept a value, comma-string or array and are normalized (incl. multi-zone OR), exactly like search_properties. Args: query: Natural-language query (EN or RU). sources: Defaults to ["listings"]. Add "projects","developers","guides", "districts" to also pull knowledge chunks (answered via RAG). Use "sales_kb" for the internal sales playbook — funnel stages, reply scripts, objection handling and the buying-procedure (for drafting client replies / consulting on next steps). mode: "rerank" \| "filter". top_k: Page size. page: 1-based page. min_score: 0..1 similarity cutoff. district/property_type/bedrooms/min_price/max_price: hard filters. Returns {query, mode, total, page, pages, applied_filters, results[], knowledge?[], notes?[]}. Listing results carry fazwaz_id, fazwaz_url, public url; prices in THB.
get_property	Full details for a single listing by its id (e.g. from search results). Returns the listing's attributes plus fazwaz_id, fazwaz_url (canonical source link) and the public site url. Prices are in THB. Returns {error:"not_found"} if the id does not exist.
list_districts_and_filters	Reference data for building searches: districts (with listing counts) and the set of valid filter values (property types, bedrooms, views, ownership, price bounds). Call this first when unsure which filter values are valid.
search_by_project	All units of one development (condo/villa project), with optional filters. Resolve by `project_id` (exact) or `project_name` (e.g. "Nai Harn Beach Condominium", "The Deck Patong"). Matches BOTH the project FK and the free-text project field, so text-only-linked units are not missed. If a name is ambiguous, returns candidate projects to pick from. Args: project_name: Development name (fuzzy, case-insensitive). project_id: FazWaz project id (from a prior candidates list / list tools). bedrooms: "2", "4+" or ["2","3"]. min_price / max_price: THB bounds. page / limit: Pagination (limit max 100). Iterate up to `pages` for all. Returns {project_id, project, total, page, pages, results[]} or {error:"ambiguous_project", candidates[...]} / {error:"not_found"}.