{ "openapi": "3.0.1", "info": { "title": "AI Dataset Cleaner & Schema Normalizer", "description": "Clean, normalize, deduplicate and validate Apify datasets or JSON. Infer schemas, fix inconsistent fields, flatten nested data and prepare reliable datasets for AI agents, RAG, CRM, analytics, APIs and databases.", "version": "0.0", "x-build-id": "DniBqnlmevtSrdqvk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/komelf~ai-dataset-cleaner-schema-normalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-komelf-ai-dataset-cleaner-schema-normalizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/komelf~ai-dataset-cleaner-schema-normalizer/runs": { "post": { "operationId": "runs-sync-komelf-ai-dataset-cleaner-schema-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/komelf~ai-dataset-cleaner-schema-normalizer/run-sync": { "post": { "operationId": "run-sync-komelf-ai-dataset-cleaner-schema-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "source_mode": { "title": "Source mode", "enum": [ "inline", "dataset" ], "type": "string", "description": "Inline is ready to try. Dataset mode reads an existing Apify dataset without modifying it.", "default": "inline" }, "source_dataset_id": { "title": "Source dataset id", "type": "string", "description": "Used only in dataset mode. Select a dataset you can read; READ permission only." }, "source_dataset": { "title": "Source dataset ID or name", "type": "string", "description": "Plain-text alternative for Published Tasks. Use the source dataset ID or name; ignored when the picker field is filled with the same value." }, "inline_records": { "title": "Inline records", "type": "array", "description": "An array of JSON objects for tests and small workflows, up to 1,000 records." }, "max_records": { "title": "Max records", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum source rows to examine, including duplicates and rejected rows. Hard ceiling 100,000.", "default": 1000 }, "preset": { "title": "Preset", "enum": [ "smart_clean", "minimal", "strict_normalization", "custom" ], "type": "string", "description": "Named presets control all advanced cleaning options. Choose Custom to edit advanced options.", "default": "smart_clean" }, "trim_strings": { "title": "Trim strings", "type": "boolean", "description": "Trim surrounding whitespace recursively, including strings inside arrays.", "default": true }, "normalize_nulls": { "title": "Normalize nulls", "type": "boolean", "description": "Convert configured placeholder strings to null; zero and false remain values.", "default": true }, "null_placeholders": { "title": "Null placeholders", "type": "array", "description": "Case-insensitive exact matches after optional trimming. Does not infer missing keys.", "default": [ "", "n/a", "na", "null", "none", "-", "unknown" ] }, "remove_null_fields": { "title": "Remove null fields", "type": "boolean", "description": "Remove explicit null object fields recursively. Null array elements remain in place.", "default": false }, "field_name_style": { "title": "Field name style", "enum": [ "preserve", "snake_case", "camelCase" ], "type": "string", "description": "Normalize keys recursively. Collisions receive deterministic suffixes without overwriting values.", "default": "snake_case" }, "rename_map": { "title": "Rename map", "type": "object", "description": "Exact original key to new key mapping, applied recursively before field naming.", "default": {} }, "include_fields": { "title": "Include fields", "type": "array", "description": "Keep only these final top-level names after flattening. Empty list keeps every field.", "default": [] }, "exclude_fields": { "title": "Exclude fields", "type": "array", "description": "Remove these final top-level names; exclusion takes priority over inclusion.", "default": [] }, "flatten": { "title": "Flatten", "type": "boolean", "description": "Flatten nested nonempty objects. Arrays remain arrays and empty objects are preserved.", "default": true }, "flatten_separator": { "title": "Flatten separator", "type": "string", "description": "Join nested field names with 1–4 characters. Collision suffixes use underscore.", "default": "_" }, "flatten_depth": { "title": "Flatten depth", "minimum": 1, "maximum": 8, "type": "integer", "description": "Maximum object edges flattened (1–8). Deeper objects remain nested.", "default": 8 }, "infer_types": { "title": "Infer types", "type": "boolean", "description": "Conservative integers, decimals, booleans and ISO date recognition. Preserve leading zeros, large IDs and ambiguous dates.", "default": true }, "normalize_email": { "title": "Normalize email", "type": "boolean", "description": "Preserve local-part case and lowercase domain. Invalid values remain present.", "default": true }, "lowercase_email_local": { "title": "Lowercase email local", "type": "boolean", "description": "Also lowercase email local parts; opt in only when appropriate for your data.", "default": false }, "normalize_url": { "title": "Normalize url", "type": "boolean", "description": "Normalize HTTP(S) scheme, host and default port; preserve query/fragment and never fetch URLs.", "default": true }, "normalize_phone": { "title": "Normalize phone", "type": "boolean", "description": "Remove separators only from phone-like fields with 7–15 digits; never infer a country.", "default": true }, "dedupe_mode": { "title": "Dedupe mode", "enum": [ "none", "exact", "normalized", "key", "fuzzy" ], "type": "string", "description": "First occurrence wins. Normalized comparisons casefold strings without changing output. Fuzzy is opt in and bounded.", "default": "normalized" }, "dedupe_keys": { "title": "Dedupe keys", "type": "array", "description": "Composite final top-level field names. Missing, null or empty key components keep the record distinct.", "default": [] }, "fuzzy_field": { "title": "Fuzzy field", "type": "string", "description": "One final top-level string field, required for fuzzy mode. Values over 256 characters are skipped.", "default": "" }, "fuzzy_threshold": { "title": "Fuzzy threshold", "minimum": 0.000001, "maximum": 1, "type": "number", "description": "Similarity from >0 to 1, within two-character prefix blocks. Can cause false matches.", "default": 0.92 }, "fuzzy_max_candidates": { "title": "Fuzzy max candidates", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum 10,000 candidates. Oversized known datasets skip fuzzy matching; exact dedupe continues.", "default": 10000 }, "infer_schema": { "title": "Infer schema", "type": "boolean", "description": "Infer JSON Schema over all retained cleaned rows before dedupe. Metadata is excluded.", "default": true }, "required_threshold": { "title": "Required threshold", "minimum": 0.000001, "maximum": 1, "type": "number", "description": "Presence fraction needed to mark fields required, using the full observed population.", "default": 0.95 }, "provided_schema": { "title": "Provided schema", "type": "object", "description": "Optional draft 2020-12 schema. References, regex and combinators are rejected for bounded offline validation. Formats are annotations.", "default": {} }, "schema_invalid_behavior": { "title": "Schema invalid behavior", "enum": [ "retain", "reject" ], "type": "string", "description": "Retain and report minimizes data loss. Reject removes invalid rows from output and billing.", "default": "retain" }, "include_cleaning_metadata": { "title": "Include cleaning metadata", "type": "boolean", "description": "Append source index and consistency score. Collision suffixes preserve user fields.", "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 } } } } } } } } } }