{ "openapi": "3.0.1", "info": { "title": "Dataset Query Engine", "description": "Use natural language queries to retrieve results from an Apify dataset. \nThis Actor provides a query engine that loads a dataset, executes SQL queries, and synthesizes results.", "version": "0.1", "x-build-id": "qm3cbIBHHSzcajZD4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jiri.spilka~dataset-query-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jiri.spilka-dataset-query-engine", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jiri.spilka~dataset-query-engine/runs": { "post": { "operationId": "runs-sync-jiri.spilka-dataset-query-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jiri.spilka~dataset-query-engine/run-sync": { "post": { "operationId": "run-sync-jiri.spilka-dataset-query-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "query", "datasetId" ], "properties": { "query": { "title": "Text or SQL query", "type": "string", "description": "Provide a query to specify the data to be retrieved from a dataset. The query can be in natural language or SQL format. For SQL, use the table name 'dataset'.\n\nExamples (when your dataset contains data scraped from Google Maps):\n- Find restaurant names with reviews above 4 and with at least 100 reviews.\n- SELECT title, totalScore, reviewsCount FROM dataset;" }, "datasetId": { "title": "Dataset ID", "type": "string", "description": "Dataset ID to retrieve data from." }, "modelName": { "title": "OpenAI model (OpenAI is the only supported provider now)", "enum": [ "gpt-4o-mini", "gpt-4o", "o3-mini" ], "type": "string", "description": "Specify the LLM for SQL generation and query synthesis. Currently supports OpenAI models with varying capabilities and performance characteristics.", "default": "gpt-4o-mini" }, "refreshDataset": { "title": "Refresh dataset", "type": "boolean", "description": "In standby mode, the dataset is loaded once and reused to optimize performance. This parameter allows reloading the dataset to ensure updated data is available.", "default": false }, "limit": { "title": "Limit number of dataset items used for query", "type": "integer", "description": "Maximum number of items to return. By default, there is no limit." }, "offset": { "title": "Number of items to skip from the start", "type": "integer", "description": "Number of items that should be skipped at the start. The default value is 0.", "default": 0 }, "useAgent": { "title": "Use AI Agent", "type": "boolean", "description": "When enabled, an AI Agent is used over a deterministic workflow. When to use an AI Agent? The agent can solve a broader range of tasks but can also be less reliable.", "default": true }, "debugMode": { "title": "Enable debug mode", "type": "boolean", "description": "When enabled, Actor will log additional debug messages from the Agent, including detailed reasoning steps.\n", "default": false } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }