{ "openapi": "3.0.1", "info": { "title": "ai-data-cleaner-classifier", "description": "Clean, normalize, deduplicate, and classify JSON, CSV, or Apify datasets using rules or OpenAI models. Built for automation pipelines, data preparation, and AI workflows. Supports dataset chaining, cost controls, and safe fallbacks.", "version": "0.0", "x-build-id": "EjJLHFQYPWUtBc1Mv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/keratogenous_surgeon~dataset-ai-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-keratogenous_surgeon-dataset-ai-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/keratogenous_surgeon~dataset-ai-cleaner/runs": { "post": { "operationId": "runs-sync-keratogenous_surgeon-dataset-ai-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/keratogenous_surgeon~dataset-ai-cleaner/run-sync": { "post": { "operationId": "run-sync-keratogenous_surgeon-dataset-ai-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "data": { "title": "Inline JSON Data", "type": "array", "description": "Array of objects provided directly in input (for small datasets).", "items": { "type": "object" } }, "sourceDatasetId": { "title": "Source Dataset ID", "type": "string", "description": "Apify Dataset ID to load input data from. Use this for large datasets or chaining Actors." }, "sourceKeyValueStoreKey": { "title": "Source Key-Value Store Key", "type": "string", "description": "Key in the default Key-Value Store containing a CSV or JSON file." }, "deduplicate": { "title": "Enable Deduplication", "type": "boolean", "description": "Remove duplicate records based on content hash.", "default": true }, "classificationLabels": { "title": "Classification Labels", "type": "array", "description": "List of labels/categories to classify each record into (e.g., 'spam', 'valid', 'lead', 'customer').", "items": { "type": "string" }, "default": [ "valid", "invalid", "needs_review" ] }, "normalizeFields": { "title": "Fields to Normalize", "type": "array", "description": "Field names to normalize (e.g., 'email', 'phone', 'name', 'company', 'url').", "items": { "type": "string" }, "default": [ "email", "phone", "name" ] }, "language": { "title": "Language", "type": "string", "description": "Language code for text processing (e.g., 'en', 'es', 'de').", "default": "en" }, "strictValidation": { "title": "Strict Validation", "type": "boolean", "description": "If enabled, records failing validation will be excluded from output.", "default": false }, "outputInvalidRecords": { "title": "Output Invalid Records", "type": "boolean", "description": "Include invalid/failed records in output with error details.", "default": true }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key for AI-powered classification. If not provided, rule-based classification is used." }, "aiModel": { "title": "AI Model", "enum": [ "gpt-4o-mini", "gpt-4o", "gpt-4-turbo", "gpt-3.5-turbo" ], "type": "string", "description": "OpenAI model to use for classification.", "default": "gpt-4o-mini" }, "classificationPrompt": { "title": "Custom Classification Prompt", "type": "string", "description": "Optional custom prompt for AI classification. Use {record} and {labels} placeholders." }, "enrichWithAI": { "title": "Enrich with AI", "type": "boolean", "description": "Use AI to extract additional insights and enrich each record.", "default": false }, "maxTokensPerRecord": { "title": "Max Tokens Per Record", "minimum": 50, "maximum": 1000, "type": "integer", "description": "Maximum tokens to use per record for AI processing (controls cost).", "default": 150 } } }, "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 } } } } } } } } } }