{ "openapi": "3.0.1", "info": { "title": "Docs-to-RAG Crawler", "description": "Crawl documentation sites (ReadTheDocs, GitBook, Docusaurus, Mintlify) and output chunked markdown ready for RAG/vector DB ingestion. Splits by heading hierarchy, strips nav/sidebar chrome.", "version": "0.1", "x-build-id": "4fs5EVZ619zSXfyp2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~docs-rag-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-docs-rag-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~docs-rag-crawler/runs": { "post": { "operationId": "runs-sync-automation-lab-docs-rag-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~docs-rag-crawler/run-sync": { "post": { "operationId": "run-sync-automation-lab-docs-rag-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "📄 Documentation URL", "pattern": "^https?://", "type": "string", "description": "Enter the root URL of the documentation site to crawl (e.g. https://docs.example.com). The crawler will follow internal links and collect all documentation pages." }, "maxPages": { "title": "📦 Max pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Set the maximum number of documentation pages to crawl. Lower values = faster, cheaper runs. Start small to preview results.", "default": 100 }, "includeCodeBlocks": { "title": "💻 Include code blocks", "type": "boolean", "description": "Keep code blocks (```...```) in output chunks. Disable to produce text-only chunks for embedding models that perform poorly on code.", "default": true }, "chunkMode": { "title": "✂️ Chunk mode", "enum": [ "heading", "page" ], "type": "string", "description": "Choose how pages are split into chunks. 'heading' splits on H2/H3 boundaries (recommended for most docs). 'page' outputs one chunk per full page.", "default": "heading" }, "maxChunkWords": { "title": "📏 Max chunk size (words)", "minimum": 50, "maximum": 2000, "type": "integer", "description": "Maximum number of words per chunk. Chunks longer than this are split further at paragraph boundaries. ~250 words ≈ 330 tokens (GPT-4 tokenizer).", "default": 300 }, "linkSelector": { "title": "🔗 Link selector (CSS)", "type": "string", "description": "CSS selector to find navigation links. Leave empty for auto-detection (recommended). Override only if the site uses unusual nav structure.", "default": "" }, "excludePatterns": { "title": "🚫 Exclude URL patterns", "type": "array", "description": "List URL patterns to skip (glob-style). For example: '*/changelog/*', '*/blog/*', '*/release-notes/*'.", "default": [], "items": { "type": "string" } }, "waitForSelector": { "title": "⏳ Wait for selector (JS sites)", "type": "string", "description": "If the docs site needs JavaScript rendering, enter a CSS selector to wait for (e.g. '.markdown-body'). Leave empty for pure HTML sites (uses faster Cheerio mode).", "default": "" } } }, "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 } } } } } } } } } }