{ "openapi": "3.0.1", "info": { "title": "Website to RAG Chunks — RAG crawler, token-sized, cited", "description": "Crawl a docs site, help center or blog and get embedding-ready chunks: main content as Markdown, split at headings to a token size you choose, each with its heading path, a citation URL to its section, a token count and a content hash. Plain HTTP. Built and maintained by an AI agent.", "version": "0.1", "x-build-id": "jpLKvphz9x0ReibzY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webprobe-tools~website-to-rag-chunks/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webprobe-tools-website-to-rag-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/webprobe-tools~website-to-rag-chunks/runs": { "post": { "operationId": "runs-sync-webprobe-tools-website-to-rag-chunks", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/webprobe-tools~website-to-rag-chunks/run-sync": { "post": { "operationId": "run-sync-webprobe-tools-website-to-rag-chunks", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Where to start: a site (https://docs.example.com), a section (https://example.com/docs/), or a sitemap (.xml or .xml.gz). A bare domain is read as https://. Only pages at or under each start URL's folder are crawled unless scope is \"domain\".", "default": [ { "url": "https://crawlee.dev/python/docs/quick-start" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after chunking this many pages. This bounds the run's cost.", "default": 20 }, "chunkTokens": { "title": "Chunk size (tokens)", "minimum": 64, "maximum": 8000, "type": "integer", "description": "Largest chunk, in OpenAI o200k_base tokens, heading line included. 256–1024 suits most embedding models.", "default": 512 }, "chunkOverlapTokens": { "title": "Overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Repeat up to this many tokens of whole paragraphs from the end of the previous chunk of the same section. 0 turns overlap off.", "default": 50 }, "headingContext": { "title": "Start each chunk with its heading path", "type": "boolean", "description": "Prefix every chunk with a line such as [Quick start > Installation], so a retriever can tell apart chunks from same-named sections.", "default": true }, "scope": { "title": "Scope", "enum": [ "path", "domain" ], "type": "string", "description": "path: only URLs at or under each start URL's folder. domain: the whole host.", "default": "path" }, "includeGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Crawl only URLs matching one of these, e.g. https://example.com/docs/**. Empty: everything in scope.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Never crawl URLs matching one of these, e.g. **/changelog/**.", "default": [ "**/changelog**", "**/docs/0.*/**", "**/docs/next/**" ], "items": { "type": "string" } }, "useSitemaps": { "title": "Use the site's sitemaps", "type": "boolean", "description": "Read the sitemaps robots.txt names (or /sitemap.xml); their in-scope URLs are crawled after the linked pages, so pages no link reaches are found too.", "default": true }, "dedupe": { "title": "Drop duplicates", "type": "boolean", "description": "Skip a page whose content matches one already chunked (it is not charged), and drop a chunk identical to one already output.", "default": true }, "keepLinks": { "title": "Keep link URLs in the text", "type": "boolean", "description": "Keep Markdown links as [text](url). Off: only the link text stays, which saves tokens.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs the site's robots.txt disallows.", "default": true }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages are fetched at once.", "default": 5 }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "A page that does not answer in time is skipped and not charged.", "default": 20 } } }, "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 } } } } } } } } } }