Malinica

List every active listing category as a flat catalog. Each entry has a numeric id, a dot-separated path encoding its place in the hierarchy (for example vozila.automobili is a child of vozila), and a human-readable title in Serbian. Call this first to translate what a user is looking for into a category id, then call get_category to learn which attributes that category supports.

Takes no parameters.

Describe one category and the attributes listings in it can be filtered by. Each attribute has a name (the key to use when filtering), a label, and a type giving the JSON value a filter must supply: string, number, boolean or date (ISO 8601). An attribute may also carry options, which are the only accepted values for it; value_type with min and max, bounding what numbers are accepted; or a picklist_path, whose accepted values are not listed here and must be fetched with get_picklist_values. A picklist_depends_on names another attribute whose value narrows this one.

Fetch one published listing by id, including its full description, price, location, category and stored attribute values. Attribute keys match the names reported by get_category for that listing's category, and attributes holds the raw stored values. Under the same key, attribute_labels gives that attribute's display label, plus a value label where the value comes from a fixed set such as a picklist or enum — use the labels when describing the listing to a user, and the raw values when filtering. Only public listings can be fetched.

Find Serbian locations by name and return their numeric ids, which is how listings are filtered by place. Matching is fuzzy and tolerates missing diacritics. Results carry a level (COUNTRY, MUNICIPALITY, CITY, CITY_MUNICIPALITY, SETTLEMENT, NEIGHBOURHOOD) and a path showing where the place sits in the hierarchy; use both to pick between same-named places, and prefer asking the user rather than guessing when several look plausible.

List the accepted values for an attribute whose get_category entry carries a picklist_path. These value sets are hierarchical and too large to inline, so they are fetched one level at a time. A picklist_path may contain a placeholder in braces naming another attribute, as in 'vehicles.car.{make}'; replace the placeholder with that attribute's chosen value before calling, so picking make 'toyota' means requesting 'vehicles.car.toyota' to get the models for it.

Search published listings by free text, category and location. Every argument is optional but at least one must be given; supplying several narrows the result the way a user ticking filters would. category_id and location_id are hierarchical and match the whole subtree beneath them, so the category 'Mobilni telefoni i oprema' also returns listings filed under its child categories, and Beograd also returns listings in Novi Beograd, Zemun and every other place under it. Filter at the broadest level the user actually meant, and only narrow when they named a specific place or category. Get ids from get_categories and search_locations. q is an ordinary keyword search, not semantic or vector search: it matches words the listing actually contains, so synonyms and paraphrases will not find anything. It matches broadly across titles, descriptions, attribute values and the listing's category and location names, but ranks titles and descriptions highest. Prefer q for what an item is, and the id filters for where it is and what it is filed under — 'stan Beograd' works, but a location_id for Beograd works better. Only the first few best matches are returned and there is no way to page past them. If the result looks too broad, narrow the search and call again rather than asking for more.