{ "openapi": "3.0.1", "info": { "title": "AI Website to Clean Markdown & RAG Chunks Scraper", "description": "Convert any bloated webpage or JS-heavy SPA into clean Markdown, JSON, and RAG-ready chunks. Slash LLM token costs by up to 90%.", "version": "1.0", "x-build-id": "poU7lmftIlAhX9qZ2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/narwal~ai-website-to-markdown-rag-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-narwal-ai-website-to-markdown-rag-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/narwal~ai-website-to-markdown-rag-scraper/runs": { "post": { "operationId": "runs-sync-narwal-ai-website-to-markdown-rag-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/narwal~ai-website-to-markdown-rag-scraper/run-sync": { "post": { "operationId": "run-sync-narwal-ai-website-to-markdown-rag-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "List of URLs to extract clean Markdown/JSON from.", "default": [ { "url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "scrapingMode": { "title": "Scraping Engine Mode", "enum": [ "auto", "fast_http", "playwright_browser" ], "type": "string", "description": "'auto' uses ultra-fast HTTP first and falls back to Playwright only if JS rendering is required. Saves Compute Units!", "default": "auto" }, "outputFormat": { "title": "Output Format", "enum": [ "markdown", "json", "both" ], "type": "string", "description": "Choose the output structure for the extracted content.", "default": "markdown" }, "includeLinks": { "title": "Preserve Hyperlinks", "type": "boolean", "description": "Keep hyperlinks inside the extracted Markdown/text.", "default": true }, "includeImages": { "title": "Include Image Links", "type": "boolean", "description": "Include Markdown image references in the output.", "default": false }, "includeTables": { "title": "Extract HTML Tables", "type": "boolean", "description": "Convert HTML tables into clean Markdown tables.", "default": true }, "enableChunking": { "title": "Enable RAG Auto-Chunking", "type": "boolean", "description": "Split the clean text into smaller overlapping chunks ready for Vector Databases (Pinecone, Qdrant, Weaviate).", "default": true }, "chunkSize": { "title": "Chunk Size (Characters)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Maximum character length per RAG chunk (~4 chars = 1 token).", "default": 1500 }, "chunkOverlap": { "title": "Chunk Overlap (Characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Character overlap between consecutive chunks to preserve context.", "default": 200 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "Number of pages to process in parallel.", "default": 5 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure Apify Proxy to avoid IP blocks.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }