{ "openapi": "3.0.1", "info": { "title": "AI Dataset Converter - Website to Training Data", "description": "Crawl websites and convert content into AI-ready formats: RAG chunks, fine-tuning JSONL, Q&A pairs, clean Markdown. Token-aware chunking, quality scoring, deduplication. No external LLM API needed.", "version": "1.0", "x-build-id": "JCdi7bWCVJOC3Vluv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/boztek-ltd~ai-dataset-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-boztek-ltd-ai-dataset-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/boztek-ltd~ai-dataset-converter/runs": { "post": { "operationId": "runs-sync-boztek-ltd-ai-dataset-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/boztek-ltd~ai-dataset-converter/run-sync": { "post": { "operationId": "run-sync-boztek-ltd-ai-dataset-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Initial URLs to crawl. Sub-pages are automatically discovered and crawled based on depth and limit settings.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages to crawl", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum number of pages to crawl. Set to 0 for unlimited.", "default": 100 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many link hops from a start URL the crawler will follow. 0 = only start URLs.", "default": 5 }, "crawlerType": { "title": "Crawler type", "enum": [ "cheerio", "adaptive", "playwright" ], "type": "string", "description": "Crawler engine. Cheerio (default) is fast and cheap; switch to Playwright or Adaptive only for JavaScript-heavy single-page apps.", "default": "cheerio" }, "includeGlobs": { "title": "Include URL patterns", "type": "array", "description": "Only URLs matching these glob patterns will be crawled. Leave empty to crawl all discovered URLs.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeGlobs": { "title": "Exclude URL patterns", "type": "array", "description": "URLs matching these glob patterns will be skipped.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "outputFormat": { "title": "Output format", "enum": [ "rag-chunks", "fine-tuning-jsonl", "qa-pairs", "markdown", "all" ], "type": "string", "description": "Primary output format. Choose 'All formats' to produce all four into separate named datasets.", "default": "rag-chunks" }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 64, "maximum": 8192, "type": "integer", "description": "Target token count per chunk (cl100k_base / GPT-4 compatible). Applies to RAG and fine-tuning formats.", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2048, "type": "integer", "description": "Token overlap between consecutive chunks. Helps preserve context across boundaries.", "default": 50 }, "extractQAPairs": { "title": "Extract Q&A pairs", "type": "boolean", "description": "Automatically extract question-answer pairs from FAQ pages and heading+paragraph structures.", "default": true }, "language": { "title": "Content language filter", "type": "string", "description": "ISO 639-1 code (e.g. 'en', 'tr', 'de'). Only pages in this language are included. Leave empty to allow all.", "default": "" }, "minContentLength": { "title": "Minimum content length (characters)", "minimum": 0, "type": "integer", "description": "Pages with cleaned content shorter than this are skipped.", "default": 100 }, "minQualityScore": { "title": "Minimum quality score (0.0-1.0)", "minimum": 0, "maximum": 1, "type": "number", "description": "Pages scoring below this heuristic threshold are excluded from output.", "default": 0.3 }, "removeDuplicates": { "title": "Remove duplicate content", "type": "boolean", "description": "Detect and skip near-duplicate pages using content fingerprinting.", "default": true }, "removeBoilerplate": { "title": "Remove boilerplate", "type": "boolean", "description": "Strip navigation, footers, cookie banners, and other non-content elements.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Residential proxy recommended for geo-aware sites.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of pages processed in parallel. Browser crawler: 1-5; HTTP crawler: 10-50.", "default": 10 } } }, "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 } } } } } } } } } }