{ "openapi": "3.0.1", "info": { "title": "Ai Training Data Curator", "description": "Crawl websites and curate high-quality training data for LLM fine-tuning. Automatic deduplication, quality scoring, and language detection. Export to JSONL, Parquet, or CSV formats ready for OpenAI, Claude, or Llama training.", "version": "1.1", "x-build-id": "5uAj1uayEGy3AmThH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/omarchydev~ai-training-data-curator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-omarchydev-ai-training-data-curator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/omarchydev~ai-training-data-curator/runs": { "post": { "operationId": "runs-sync-omarchydev-ai-training-data-curator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/omarchydev~ai-training-data-curator/run-sync": { "post": { "operationId": "run-sync-omarchydev-ai-training-data-curator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "start_urls": { "title": "Start URLs", "type": "array", "description": "URLs to start crawling from. Leave empty if using BYOD mode.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "documents": { "title": "Documents (BYOD)", "type": "array", "description": "Your own documents to process. Provide text strings or objects with 'text' field. Use this instead of Start URLs for BYOD mode." }, "byod_text_field": { "title": "Text Field Name (BYOD)", "type": "string", "description": "Field name containing text in BYOD documents (default: 'text')", "default": "text" }, "max_byod_documents": { "title": "Max BYOD Documents", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum documents to process in BYOD mode (prevents memory issues)", "default": 500 }, "crawl_mode": { "title": "Crawl Mode", "enum": [ "single_page", "same_domain", "same_subdomain", "all_links" ], "type": "string", "description": "How extensively to crawl: single_page, same_domain, same_subdomain, all_links", "default": "same_domain" }, "max_pages": { "title": "Maximum Pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl", "default": 100 }, "max_depth": { "title": "Maximum Depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum link depth from start URLs", "default": 3 }, "content_selectors": { "title": "Content Selectors", "type": "array", "description": "CSS selectors for main content elements (e.g., article, main, .content)", "items": { "type": "string" } }, "exclude_selectors": { "title": "Exclude Selectors", "type": "array", "description": "CSS selectors for elements to exclude (e.g., nav, footer, .sidebar)", "items": { "type": "string" } }, "min_word_count": { "title": "Minimum Word Count", "minimum": 10, "maximum": 10000, "type": "integer", "description": "Minimum words per document", "default": 100 }, "max_word_count": { "title": "Maximum Word Count", "minimum": 100, "maximum": 500000, "type": "integer", "description": "Maximum words per document (longer documents will be truncated)", "default": 50000 }, "deduplicate": { "title": "Enable Deduplication", "type": "boolean", "description": "Remove near-duplicate documents using fuzzy matching", "default": true }, "dedup_threshold_percent": { "title": "Deduplication Threshold (%)", "minimum": 50, "maximum": 100, "type": "integer", "description": "Similarity threshold for deduplication (50-100%, higher = stricter)", "default": 85 }, "quality_filter": { "title": "Enable Quality Filter", "type": "boolean", "description": "Filter out low-quality documents based on quality score", "default": true }, "min_quality_score_percent": { "title": "Minimum Quality Score (%)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Minimum quality score to include document (0-100%)", "default": 50 }, "language_filter": { "title": "Language Filter", "type": "array", "description": "Language codes to include (e.g., en, es, fr). Empty = all languages", "items": { "type": "string" } }, "chunk_documents": { "title": "Chunk Documents", "type": "boolean", "description": "Split documents into smaller chunks for training", "default": false }, "chunk_size": { "title": "Chunk Size", "minimum": 64, "maximum": 8192, "type": "integer", "description": "Target tokens per chunk when chunking is enabled", "default": 512 }, "chunk_overlap": { "title": "Chunk Overlap", "minimum": 0, "maximum": 512, "type": "integer", "description": "Overlap tokens between consecutive chunks", "default": 64 }, "output_format": { "title": "Output Format", "enum": [ "jsonl", "json", "csv" ], "type": "string", "description": "Format for output data", "default": "jsonl" }, "text_field_name": { "title": "Text Field Name", "type": "string", "description": "Field name for text content in output", "default": "text" }, "include_metadata": { "title": "Include Metadata", "type": "boolean", "description": "Include document metadata (title, author, URL, etc.)", "default": true }, "include_raw_html": { "title": "Include Raw HTML", "type": "boolean", "description": "Include raw HTML in output (increases data size)", "default": false }, "remove_urls": { "title": "Remove URLs from Text", "type": "boolean", "description": "Remove URLs from extracted text", "default": false }, "remove_emails": { "title": "Remove Emails from Text", "type": "boolean", "description": "Remove email addresses from extracted text (recommended for privacy)", "default": true }, "normalize_whitespace": { "title": "Normalize Whitespace", "type": "boolean", "description": "Normalize whitespace and remove excessive blank lines", "default": true }, "use_proxies": { "title": "Use Proxies", "type": "boolean", "description": "Use Apify proxy for requests", "default": false }, "max_concurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum concurrent page requests", "default": 10 }, "request_delay_ms": { "title": "Request Delay (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Delay between requests in milliseconds", "default": 500 } } }, "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 } } } } } } } } } }