Cubi Estate · Schema
AgentSimilarRequest
CompanyReal EstateProperty SearchArtificial IntelligenceMCPListingsEurope
Properties
| Name | Type | Description |
|---|---|---|
| chat_id | integer | Chat id of the requesting user. |
| seed_id | object | Listing id of the seed (direct). |
| token | object | Carousel token (resolves seed via (token, index)). |
| index | object | Index into carousel cache. |
| mode | string | |
| other_city | object | Required for mode='cross_city' — target city. |
| limit | integer | Max candidates to return. |
| lang | object | |
| channel | object | |
| telegram_chat_id | object | |
| whatsapp_chat_id | object | |
| embedding_source | object | Per-request override for the pgvector NN embedding source. 'pca' = listing_concept_pca.embedding (50d, mig 078). 'search_doc' = listing_search_doc.embedding_v (384d, legacy). 'hybrid' = union of both |
| structural_pool | object | Per-request override for the structural-proximity pool (SIMILARITY_STRUCTURAL_POOL). True forces it on, False off; None (default) follows the env flag. in_city only — ignored for cross_city. Lets you |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/cubi-estate/json-schema/cubi-estate-agent-similar-request-schema.json",
"title": "AgentSimilarRequest",
"x-generated": "2026-11-04",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/cubi-estate-openapi.yml#/components/schemas/AgentSimilarRequest",
"properties": {
"chat_id": {
"type": "integer",
"title": "Chat Id",
"description": "Chat id of the requesting user."
},
"seed_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Seed Id",
"description": "Listing id of the seed (direct)."
},
"token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Token",
"description": "Carousel token (resolves seed via (token, index))."
},
"index": {
"anyOf": [
{
"type": "integer",
"maximum": 49.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Index",
"description": "Index into carousel cache."
},
"mode": {
"type": "string",
"enum": [
"in_city",
"cross_city"
],
"title": "Mode",
"default": "in_city"
},
"other_city": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Other City",
"description": "Required for mode='cross_city' — target city."
},
"limit": {
"type": "integer",
"maximum": 10.0,
"minimum": 1.0,
"title": "Limit",
"description": "Max candidates to return.",
"default": 5
},
"lang": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Lang",
"default": "en"
},
"channel": {
"anyOf": [
{
"type": "string",
"enum": [
"telegram",
"whatsapp"
]
},
{
"type": "null"
}
],
"title": "Channel",
"default": "telegram"
},
"telegram_chat_id": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Telegram Chat Id"
},
"whatsapp_chat_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Whatsapp Chat Id"
},
"embedding_source": {
"anyOf": [
{
"type": "string",
"enum": [
"pca",
"search_doc",
"hybrid"
]
},
{
"type": "null"
}
],
"title": "Embedding Source",
"description": "Per-request override for the pgvector NN embedding source. 'pca' = listing_concept_pca.embedding (50d, mig 078). 'search_doc' = listing_search_doc.embedding_v (384d, legacy). 'hybrid' = union of both pools (deduped by listing_id, max embed_sim wins on collision). None (default) follows SIMILARITY_USE_PCA_EMBEDDINGS env. Useful for in-request A/B without dyno restart."
},
"structural_pool": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Structural Pool",
"description": "Per-request override for the structural-proximity pool (SIMILARITY_STRUCTURAL_POOL). True forces it on, False off; None (default) follows the env flag. in_city only — ignored for cross_city. Lets you A/B the structural branch against real chats without an app-wide config flip."
}
},
"type": "object",
"required": [
"chat_id"
]
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/cubi-estate-agent-similar-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.