{ "openapi": "3.0.1", "info": { "title": "Website to RAG Chunks: Markdown, Tokens & Incremental Crawl", "description": "Turn any website, docs site, PDF or DOCX into clean, heading-aware RAG chunks with exact token counts. Incremental mode only returns new or changed pages. Pay per page, not per chunk.", "version": "1.0", "x-build-id": "aHCl3LOeRL3PDaaHc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nacenempresas~rag-website-chunks/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nacenempresas-rag-website-chunks", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nacenempresas~rag-website-chunks/runs": { "post": { "operationId": "runs-sync-nacenempresas-rag-website-chunks", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nacenempresas~rag-website-chunks/run-sync": { "post": { "operationId": "run-sync-nacenempresas-rag-website-chunks", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites, docs sites, sitemaps or direct links to PDF/DOCX/TXT/MD/llms.txt files. Pages under the same path are discovered automatically via links and the sitemap.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "Maximum number of pages/documents returned (and charged) in this run. The crawl also stops at your run's spending limit.", "default": 100 }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 32, "maximum": 8192, "type": "integer", "description": "Maximum tokens per chunk. No chunk ever exceeds this limit: text is split by section, then paragraph, then sentence.", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2048, "type": "integer", "description": "Tokens repeated between consecutive chunks of the same section (max half of chunk size).", "default": 64 }, "tokenizer": { "title": "Tokenizer", "enum": [ "cl100k_base", "o200k_base", "approximate" ], "type": "string", "description": "cl100k_base (GPT-4, GPT-3.5, text-embedding-3), o200k_base (GPT-4o and newer) or a fast approximation.", "default": "cl100k_base" }, "output": { "title": "Output", "enum": [ "chunks", "pages", "both" ], "type": "string", "description": "chunks: one row per chunk (ready for a vector database). pages: one row per page with full Markdown. both: both row types with a `type` field.", "default": "chunks" }, "incremental": { "title": "Incremental mode (only new or changed pages)", "type": "boolean", "description": "Remembers a fingerprint of every page between runs. Unchanged pages are skipped and not charged. Ideal for scheduled runs that keep a vector index fresh.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Optional name of the key-value store that keeps incremental state. Leave empty to derive it from the start URLs." }, "useSitemap": { "title": "Use sitemap", "type": "boolean", "description": "Discover pages from robots.txt sitemaps and /sitemap.xml, including pages that are not linked.", "default": true }, "stayWithinPath": { "title": "Stay within start URL path", "type": "boolean", "description": "Only crawl URLs under the start URL's folder (e.g. /docs/). Disable to crawl the whole domain.", "default": true }, "includeGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Only crawl URLs matching these patterns, e.g. https://example.com/docs/**", "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Never crawl URLs matching these patterns, e.g. **/changelog/**", "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "maxDepth": { "title": "Max link depth", "minimum": 0, "type": "integer", "description": "How many link hops from the start URL to follow.", "default": 20 }, "includeFiles": { "title": "Linked documents to convert", "type": "array", "description": "Linked files that are downloaded and chunked too.", "items": { "type": "string", "enum": [ "PDF", "DOCX", "TXT", "MD" ] }, "default": [ "PDF", "DOCX", "TXT", "MD" ] }, "jsFallback": { "title": "JavaScript rendering", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto: fast HTTP first, headless browser only for pages that come back (almost) empty. always: render every page. never: HTTP only.", "default": "auto" }, "removeBoilerplate": { "title": "Remove repeated boilerplate", "type": "boolean", "description": "Drop menus, footers and cookie notices that repeat across pages, plus duplicate chunks and near-duplicate pages.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by the site's robots.txt.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel HTTP requests.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Use a proxy for sites that block datacenter IPs.", "default": { "useApifyProxy": 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 }, "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 } } } } } } } } } }