{ "openapi": "3.0.1", "info": { "title": "AI Training Data Validator - Clean LLM Datasets Automatically", "description": "Prepare production-ready training data for ChatGPT, Claude, Llama, and open-source LLMs. Remove duplicates, toxicity, PII, and low-quality samples automatically.", "version": "2.0", "x-build-id": "KoYPwOQWk9ZbSKoUb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~ai-training-data-validator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-ai-training-data-validator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~ai-training-data-validator/runs": { "post": { "operationId": "runs-sync-solutionssmart-ai-training-data-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~ai-training-data-validator/run-sync": { "post": { "operationId": "run-sync-solutionssmart-ai-training-data-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "datasetUrl" ], "properties": { "datasetUrl": { "title": "Dataset URL", "type": "string", "description": "Dataset URL or local path to a CSV, JSON, JSONL, or Parquet file. For local testing, you can point to examples/sample_training_data.jsonl." }, "dataType": { "title": "Data type", "enum": [ "text", "code", "conversation", "mixed" ], "type": "string", "description": "Choose the training data shape you want to clean.", "default": "mixed" }, "llmTarget": { "title": "LLM target", "enum": [ "chatgpt", "claude", "llama", "mistral", "custom" ], "type": "string", "description": "Target model family for the cleaned output.", "default": "custom" }, "removeDuplicates": { "title": "Remove duplicates", "type": "boolean", "description": "Remove exact and near-duplicate samples.", "default": true }, "removeToxicity": { "title": "Remove toxicity", "type": "boolean", "description": "Filter toxic or unsafe samples.", "default": true }, "removePII": { "title": "Remove PII", "type": "boolean", "description": "Mask emails, phones, SSNs, addresses, and other sensitive data.", "default": true }, "fixEncoding": { "title": "Fix encoding", "type": "boolean", "description": "Clean common encoding artifacts and malformed characters.", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "jsonl", "csv", "huggingface", "openai-finetuning" ], "type": "string", "description": "Serialization format for the cleaned dataset export.", "default": "jsonl" }, "maxTokensPerSample": { "title": "Max tokens per sample", "minimum": 32, "type": "integer", "description": "Truncate very long samples to this approximate token budget.", "default": 2048 }, "similarityThreshold": { "title": "Similarity threshold", "pattern": "^(0[\\.,][5-9]\\d?|0[\\.,]9\\d?)$", "type": "string", "description": "Near-duplicate threshold for MinHash-LSH matching. Enter a value from 0.5 to 0.99, for example 0.85 or 0,85.", "default": "0.85" }, "analysisConcurrency": { "title": "Analysis concurrency", "minimum": 1, "maximum": 128, "type": "integer", "description": "Maximum number of samples analyzed concurrently per batch. Useful when later enabling external moderation or PII services.", "default": 16 }, "enableLiveView": { "title": "Enable live view", "type": "boolean", "description": "Continuously write LIVE_VIEW.json and live_report.html during long runs.", "default": true }, "completionWebhookUrl": { "title": "Completion webhook URL", "type": "string", "description": "Optional webhook URL to receive a JSON summary when the run finishes. Works with n8n, Make, OpenClaw, and custom webhooks." }, "completionWebhookToken": { "title": "Completion webhook token", "type": "string", "description": "Optional bearer token sent as Authorization: Bearer when posting the completion webhook." }, "completionWebhookHeadersJson": { "title": "Completion webhook headers JSON", "type": "string", "description": "Optional JSON object with extra HTTP headers for the completion webhook, for example {\"x-api-key\":\"secret\"}." } } }, "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 } } } } } } } } } }