{ "openapi": "3.0.1", "info": { "title": "Malaysia Open Data Studio — Gov Data Joins", "description": "Value layer on Malaysia's official open data API (data.gov.my): cross-dataset joins (population x income x CPI by state), CSV/JSON/XLSX delivery, webhooks, AI-ready output with CC BY 4.0 attribution.", "version": "0.3", "x-build-id": "t1YiMrg2CAhbUHoxy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/subimpact~my-open-data-studio/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-subimpact-my-open-data-studio", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/subimpact~my-open-data-studio/runs": { "post": { "operationId": "runs-sync-subimpact-my-open-data-studio", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/subimpact~my-open-data-studio/run-sync": { "post": { "operationId": "run-sync-subimpact-my-open-data-studio", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "preset": { "title": "Preset bundle", "enum": [ "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8", "B9", "B10", "B11", "custom" ], "type": "string", "description": "Join bundle. B1 = Economy by State. B2 = Demography by State. B3 = Labour Market & Mobility. B4 = Prices & Inflation. B5 = Health & Pandemic. B6 = Public Transport Ridership. B7 = Education by State. B8 = Tourism & Arrivals. B9 = Agriculture & Commodities. B10 = Public Safety. B11 = Healthcare Capacity. custom = bring your own dataset ids.", "default": "B1" }, "customDatasets": { "title": "Custom join — dataset IDs", "type": "array", "description": "For preset=custom: list of data.gov.my catalogue ids to join (2-6). Leave empty to use a preset.", "items": { "type": "string" } }, "customKey": { "title": "Custom join — key columns", "type": "array", "description": "For preset=custom: key parts to join on. Use 'year' (extracted from the date field) or raw field names like state, district. All datasets must share these keys.", "default": [ "state", "year" ], "items": { "type": "string" } }, "customJoinType": { "title": "Custom join — join type", "enum": [ "inner", "left" ], "type": "string", "description": "inner keeps only keys present in every dataset; left keeps all keys from the first dataset.", "default": "inner" }, "customParams": { "title": "Custom join — API filters (JSON)", "type": "string", "description": "For preset=custom: JSON object of extra API params applied to every dataset, e.g. {\"filter\": \"overall@division\"}." }, "customAgg": { "title": "Custom join — aggregation", "enum": [ "none", "sum", "mean" ], "type": "string", "description": "none = keep raw rows (last value per key). sum = aggregate numeric values per key. mean = average numeric values per key.", "default": "none" }, "format": { "title": "Output format", "enum": [ "json", "csv", "xlsx" ], "type": "string", "description": "File format delivered to the key-value store (dataset records are always JSON).", "default": "json" }, "webhookUrl": { "title": "Webhook URL (optional)", "type": "string", "description": "POST the result file to this URL after the run (3 retries with backoff). Leave empty to skip." }, "aiReady": { "title": "AI-ready package", "type": "boolean", "description": "Also emit JSON Schema + data dictionary + sample rows for LLM/RAG ingestion.", "default": true }, "includeAttribution": { "title": "Include CC BY 4.0 attribution", "type": "boolean", "description": "Attach source/licence metadata sidecar to every output.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }