{ "openapi": "3.0.1", "info": { "title": "RAG-Ready Web Scraper & Smart Chunker for AI Knowledge Bases", "description": "RAG-ready web scraper that collects, cleans, deduplicates, filters, and chunks web content into structured datasets for AI pipelines. Generates high-quality knowledge-base data optimized for LLMs, embeddings, and vector databases", "version": "0.1", "x-build-id": "8ZHh7H8POmLMZr6rB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/adinfosys-labs~rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-adinfosys-labs-rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/adinfosys-labs~rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases/runs": { "post": { "operationId": "runs-sync-adinfosys-labs-rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/adinfosys-labs~rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases/run-sync": { "post": { "operationId": "run-sync-adinfosys-labs-rag-ready-web-scraper-smart-chunker-for-ai-knowledge-bases", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrlsText": { "title": "Start URLs (one per line)", "type": "string", "description": "Enter URLs to fetch. One per line. Lines starting with # are ignored. If sourceDatasetId is provided, this field is ignored.", "default": "" }, "sourceDatasetId": { "title": "Source dataset ID", "type": "string", "description": "Optional: datasetId containing raw documents (fields like url/title/text/html). If provided, Actor ingests from dataset instead of crawling.", "default": "" }, "maxPages": { "title": "Max pages", "type": "integer", "description": "Maximum number of pages to process (either from startUrlsText or sourceDatasetId).", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "type": "integer", "description": "Parallel fetches when using startUrlsText (keep conservative to avoid rate limits).", "default": 5 }, "userAgent": { "title": "User agent", "type": "string", "description": "User-Agent header used for HTTP requests.", "default": "Mozilla/5.0 (compatible; RAGReadyCollector/0.1; +https://apify.com/)" }, "topicKeywordsText": { "title": "Topic keywords (one per line)", "type": "string", "description": "Keywords used for relevance scoring. One keyword per line. Leave empty to disable keyword scoring.", "default": "" }, "noiseControlJson": { "title": "Noise control (JSON)", "type": "string", "description": "Optional JSON object for filtering/dedupe/quality scoring. Leave empty to use defaults.", "default": "" }, "chunkingJson": { "title": "Chunking (JSON)", "type": "string", "description": "Optional JSON object for chunking settings. Leave empty to use defaults.", "default": "" }, "outputJson": { "title": "Output options (JSON)", "type": "string", "description": "Optional JSON object for output options (e.g., writeRunReport). Leave empty to use defaults.", "default": "" }, "debug": { "title": "Debug logging", "type": "boolean", "description": "Enable extra logs for troubleshooting.", "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 } } }, "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 } } } } } } } } } }