{ "openapi": "3.0.1", "info": { "title": "Docs2rag", "description": "Crawl public docs and convert them into AI-ready RAG datasets. Docs2RAG strips navigation noise, preserves code blocks & tables, and exports clean Markdown and structured chunks ready for vector DBs like Pinecone, Qdrant, & Chroma with zero API keys required.", "version": "0.0", "x-build-id": "Cv3w5hAildRY5Q8rP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thebyteguy~docs2rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thebyteguy-docs2rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thebyteguy~docs2rag/runs": { "post": { "operationId": "runs-sync-thebyteguy-docs2rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thebyteguy~docs2rag/run-sync": { "post": { "operationId": "run-sync-thebyteguy-docs2rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One or more documentation entry point URLs to begin crawling.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl and extract. Default is 100.", "default": 100 }, "maxDepth": { "title": "Max Depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum link crawl depth from the start URLs. Default is 10.", "default": 10 }, "includeUrlPatterns": { "title": "Include URL Patterns", "type": "array", "description": "Optional list of regex or glob patterns. Only URLs matching at least one pattern will be crawled.", "default": [] }, "excludeUrlPatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Optional list of regex or glob patterns. Matching URLs will be skipped.", "default": [] }, "sameDomainOnly": { "title": "Same Domain Only", "type": "boolean", "description": "If true, only links on the same host domain as the start URL will be crawled.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Whether to fetch and respect the target site's robots.txt rules.", "default": true }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of concurrent requests. Keep safe to avoid overloading target servers.", "default": 5 }, "requestTimeoutSecs": { "title": "Request Timeout (Seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum timeout in seconds for each HTTP request.", "default": 30 }, "removeSelectors": { "title": "Remove Selectors (CSS)", "type": "array", "description": "Custom CSS selectors for elements to remove from the page prior to extraction (e.g., banner, cookie popups).", "default": [] }, "contentSelectors": { "title": "Content Selectors (CSS)", "type": "array", "description": "Custom CSS selectors to locate the main documentation body. If provided, the first match is extracted.", "default": [] }, "chunkSize": { "title": "Chunk Size", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Target size for each text chunk (in characters, or tokens if token-aware chunking). Default is 1200.", "default": 1200 }, "chunkOverlap": { "title": "Chunk Overlap", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Overlap between consecutive chunks (in characters, or tokens). Default is 200.", "default": 200 }, "minContentLength": { "title": "Min Content Length", "minimum": 10, "maximum": 5000, "type": "integer", "description": "Minimum character count for extracted page content to be kept. Prevents saving empty or stub pages.", "default": 100 }, "includeCode": { "title": "Include Code Blocks", "type": "boolean", "description": "Whether to preserve code blocks and syntax-highlighted snippets in Markdown and chunks.", "default": true }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Whether to preserve image markdown syntax with alt text and URLs.", "default": false }, "outputFormats": { "title": "Output Formats", "type": "array", "description": "Supported output formats to produce: MARKDOWN, JSON, JSONL.", "default": [ "MARKDOWN", "JSON", "JSONL" ] }, "deduplicateContent": { "title": "Deduplicate Content", "type": "boolean", "description": "Avoid processing duplicate pages with identical content hashes.", "default": true }, "crawlSitemap": { "title": "Crawl Sitemap", "type": "boolean", "description": "Automatically discover documentation URLs via /sitemap.xml if available.", "default": true }, "generatePageSummaries": { "title": "Generate Page Summaries", "type": "boolean", "description": "Optional extractive page summary generation (does not require external API keys).", "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 }, "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 } } } } } } } } } }