AI Data Formatter & Schema Converter
Pricing
from $40.00 / 1,000 small data formattings
Transform messy CSV or JSON data into a validated custom schema with clean JSON and Excel-ready CSV outputs.
You can access the AI Data Formatter & Schema Converter programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "ppGF84cWLr20mE09s" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pearlescent_idiom~ai-data-formatter-schema-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pearlescent_idiom-ai-data-formatter-schema-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/pearlescent_idiom~ai-data-formatter-schema-converter/runs": { "post": { "operationId": "runs-sync-pearlescent_idiom-ai-data-formatter-schema-converter", "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/pearlescent_idiom~ai-data-formatter-schema-converter/run-sync": { "post": { "operationId": "run-sync-pearlescent_idiom-ai-data-formatter-schema-converter", "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": [ "targetSchema" ], "properties": { "records": { "title": "Source records", "maxItems": 500, "type": "array", "description": "Paste a JSON array of objects. Field names and value formats can be inconsistent.", "items": { "type": "object" }, "default": [ { "Customer ID": "C-001", "Full Name": " Ada Yilmaz ", "Mail": "ADA@EXAMPLE.COM", "Spent": "1,250.50", "Newsletter": "yes" }, { "id": "C-001", "name": "Ada Yilmaz", "email": "ada@example.com", "total": 1250.5, "subscribed": true }, { "customer_no": "C-002", "customer": "Mert Kaya", "email_address": "mert@example.com", "amount": "850", "newsletter": "no" } ] }, "files": { "title": "Or upload CSV or JSON files", "maxItems": 5, "type": "array", "description": "Upload up to five UTF-8 CSV or JSON files.", "items": { "type": "string" } }, "dataText": { "title": "Or paste CSV/JSON text", "maxLength": 500000, "type": "string", "description": "Automatic detection supports standard JSON arrays/objects and comma-separated CSV." }, "inputFormat": { "title": "Pasted/uploaded data format", "enum": [ "auto", "json", "csv" ], "type": "string", "description": "Use automatic detection unless the source has an unusual extension or structure.", "default": "auto" }, "targetSchema": { "title": "Target JSON Schema", "type": "object", "description": "Define one output object. Missing required non-null values are reported as failed records instead of invented.", "default": { "type": "object", "properties": { "customer_id": { "type": "string" }, "full_name": { "type": "string" }, "email": { "type": [ "string", "null" ] }, "total_spent": { "type": [ "number", "null" ] }, "subscribed": { "type": [ "boolean", "null" ] } }, "required": [ "customer_id", "full_name", "email", "total_spent", "subscribed" ], "additionalProperties": false } }, "instructions": { "title": "Transformation instructions", "maxLength": 4000, "type": "string", "description": "Optional field mappings, locale rules, date formats, units, or naming conventions.", "default": "Normalize email addresses to lowercase and trim surrounding whitespace." }, "removeDuplicates": { "title": "Remove duplicate records", "type": "boolean", "description": "Keep the first matching formatted record and report how many duplicates were found.", "default": true }, "deduplicateBy": { "title": "Duplicate field paths", "maxItems": 10, "type": "array", "description": "Optional target fields such as email or customer_id. Leave empty to compare the complete formatted record.", "items": { "type": "string" }, "default": [ "email" ] }, "retryCount": { "title": "Validation retries", "minimum": 0, "maximum": 4, "type": "integer", "description": "Number of model correction attempts for invalid output.", "default": 2 }, "continueOnError": { "title": "Continue after a failed batch", "type": "boolean", "description": "Save failed rows with an error message and continue processing later batches.", "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI Data Formatter & Schema Converter from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: