{ "openapi": "3.0.1", "info": { "title": "Export Dataset to Parquet - Typed Schema for DuckDB & BigQuery", "description": "Apify exports JSON, CSV and Excel but not Parquet. Pick any dataset and get typed Parquet files (inferred schema, flattened nested fields, detected timestamps) in the key-value store, optionally pushed to S3, R2 or Google Cloud Storage. Ready for DuckDB, BigQuery, Athena.", "version": "1.0", "x-build-id": "Ah1W5twmBTqhqWPT8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~dataset-to-parquet/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-dataset-to-parquet", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~dataset-to-parquet/runs": { "post": { "operationId": "runs-sync-that_red_bird-dataset-to-parquet", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~dataset-to-parquet/run-sync": { "post": { "operationId": "run-sync-that_red_bird-dataset-to-parquet", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasets": { "title": "Dataset(s) to convert", "type": "array", "description": "Pick the dataset of any Actor run. Use the picker rather than typing an ID: it gives this Actor permission to read your dataset. Several datasets are appended into one Parquet schema. Leave empty to use the pasted rows below, or the built-in demo." }, "rows": { "title": "Rows (JSON)", "type": "array", "description": "Optional. Paste rows as JSON objects, e.g. {\"id\":1,\"name\":\"Ann\",\"tags\":[\"a\"]}. Nested objects are flattened by default.", "default": [] }, "rowsCsv": { "title": "Rows (CSV or JSON text)", "type": "string", "description": "Optional. Paste a CSV (first row = column names; numbers and true/false are detected) or a JSON array.", "default": "" }, "fileName": { "title": "Output file name", "type": "string", "description": "Base name of the Parquet file in the key-value store (.parquet is added). With several files the name gets -part-0001, -part-0002 and so on.", "default": "dataset" }, "nestedFields": { "title": "Nested objects", "enum": [ "flatten", "json" ], "type": "string", "description": "flatten turns {\"a\":{\"b\":1}} into a column a_b (best for BigQuery, Athena, DuckDB). json keeps each top-level nested object as one JSON column. Arrays are always kept as JSON columns.", "default": "flatten" }, "inferDates": { "title": "Detect timestamps", "type": "boolean", "description": "Columns where every value is an ISO 8601 date or date-time (2026-05-01, 2026-05-01T10:00:00Z) become TIMESTAMP columns. Date-times without a time zone are read as UTC.", "default": true }, "sanitizeColumnNames": { "title": "Warehouse-safe column names", "type": "boolean", "description": "Replace characters other than letters, digits and underscore with an underscore (BigQuery and Athena require this) and make names unique. Turn off to keep the original names.", "default": true }, "rowsPerFile": { "title": "Rows per file", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "Maximum rows in one Parquet file. Bigger datasets are split into several files with the same schema; each file is billed per started 1,000 rows.", "default": 250000 }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 20000000, "type": "integer", "description": "Safety limit on the number of rows converted in one run.", "default": 1000000 }, "s3Bucket": { "title": "S3 bucket (optional)", "type": "string", "description": "Also upload each Parquet file to this Amazon S3 bucket (or any S3-compatible service such as Cloudflare R2, MinIO or Backblaze B2). Needs the access key fields below. The files are always kept in the key-value store too.", "default": "" }, "s3Region": { "title": "S3 region", "type": "string", "description": "AWS region of the bucket, for example us-east-1 or eu-west-1. For R2 use auto.", "default": "us-east-1" }, "s3KeyPrefix": { "title": "S3 key prefix", "type": "string", "description": "Optional folder inside the bucket, for example scrapes/2026-10/.", "default": "" }, "s3AccessKeyId": { "title": "S3 access key ID", "type": "string", "description": "Access key ID of an IAM user that may PutObject into the bucket. Use a key limited to this bucket." }, "s3SecretAccessKey": { "title": "S3 secret access key", "type": "string", "description": "Secret access key that belongs to the access key ID. Stored encrypted by Apify." }, "s3SessionToken": { "title": "S3 session token", "type": "string", "description": "Only for temporary credentials (AWS STS). Leave empty otherwise." }, "s3Endpoint": { "title": "S3-compatible endpoint", "type": "string", "description": "Only for non-AWS services, for example https://.r2.cloudflarestorage.com or https://s3.us-west-004.backblazeb2.com. Leave empty for Amazon S3.", "default": "" }, "gcsBucket": { "title": "Google Cloud Storage bucket (optional)", "type": "string", "description": "Also upload each Parquet file to this Google Cloud Storage bucket. Needs the service-account JSON below.", "default": "" }, "gcsKeyPrefix": { "title": "GCS object prefix", "type": "string", "description": "Optional folder inside the bucket, for example scrapes/2026-10/.", "default": "" }, "gcsServiceAccountJson": { "title": "GCS service-account JSON", "type": "string", "description": "Paste the full JSON key of a service account with Storage Object Creator access to the bucket. Stored encrypted by Apify." } } }, "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 } } } } } } } } } }