{ "openapi": "3.0.1", "info": { "title": "Docs-to-RAG Optimizer", "description": "Convert public developer documentation into clean Markdown, semantic RAG chunks, token counts, duplicate hashes, JSONL exports, and quality warnings for AI assistants.", "version": "0.1", "x-build-id": "ceR4NC1byF0zmjUFg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vamsi-krishna~docs-to-rag-optimizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vamsi-krishna-docs-to-rag-optimizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vamsi-krishna~docs-to-rag-optimizer/runs": { "post": { "operationId": "runs-sync-vamsi-krishna-docs-to-rag-optimizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vamsi-krishna~docs-to-rag-optimizer/run-sync": { "post": { "operationId": "run-sync-vamsi-krishna-docs-to-rag-optimizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 public documentation URLs to crawl and convert into Markdown, JSONL, and RAG chunks.", "default": [ { "url": "https://docusaurus.io/docs" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional XML sitemap URLs to seed additional pages.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "Maximum number of pages to successfully process (stored + charged).", "default": 100 }, "maxDepth": { "title": "Max depth", "minimum": 0, "type": "integer", "description": "Maximum crawl depth from the start URLs.", "default": 5 }, "includePatterns": { "title": "Include patterns (regex)", "type": "array", "description": "Only crawl URLs matching at least one regex. If empty, include all (subject to other filters).", "items": { "type": "string" }, "default": [] }, "excludePatterns": { "title": "Exclude patterns (regex)", "type": "array", "description": "Skip URLs matching any regex.", "items": { "type": "string" }, "default": [] }, "crawlOnlyDocs": { "title": "Crawl only docs pages", "type": "boolean", "description": "Skip obvious non-docs pages (blog, pricing, login, etc.).", "default": true }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Output formats to produce.", "items": { "type": "string", "enum": [ "json", "markdown" ] }, "default": [ "json", "markdown" ] }, "removeSelectors": { "title": "Remove selectors", "type": "array", "description": "CSS selectors to remove before extraction/markdown conversion.", "items": { "type": "string" }, "default": [] }, "keepSelectors": { "title": "Keep selectors", "type": "array", "description": "If provided, restrict extraction to these selectors.", "items": { "type": "string" }, "default": [] }, "preserveCodeBlocks": { "title": "Preserve code blocks", "type": "boolean", "description": "Preserve fenced code blocks in the generated Markdown and extract code blocks into JSON.", "default": true }, "preserveTables": { "title": "Preserve tables", "type": "boolean", "description": "Convert HTML tables into GitHub-Flavored Markdown tables and include table HTML in JSON.", "default": true }, "preserveLinks": { "title": "Preserve links", "type": "boolean", "description": "Keep links in Markdown and include normalized links in JSON.", "default": true }, "chunkingEnabled": { "title": "Chunking enabled", "type": "boolean", "description": "Generate chunk-level records suitable for RAG ingestion.", "default": true }, "chunkStrategy": { "title": "Chunk strategy", "enum": [ "header-aware" ], "type": "string", "description": "Chunking strategy used to split pages into semantic chunks.", "default": "header-aware" }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 50, "type": "integer", "description": "Target maximum tokens per chunk (approximate).", "default": 800 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "type": "integer", "description": "Approximate overlap between consecutive chunks to improve retrieval continuity.", "default": 100 }, "deduplicateContent": { "title": "Deduplicate content", "type": "boolean", "description": "Detect exact-duplicate pages by content hash and mark them via duplicateOf.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Respect robots.txt disallow rules when crawling.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum concurrent page requests.", "default": 5 } } }, "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 } } } } } } } } } }