{ "openapi": "3.0.1", "info": { "title": "RAG Web Crawler: Clean Markdown + Token-Sized Chunks", "description": "Turn any website into embeddings-ready chunks for RAG and vector databases. Structure-aware token-sized chunking, clean LLM-ready markdown, per-chunk citations and metadata, dedup, and junk filtering. Pay per result, no surprise compute bills.", "version": "1.1", "x-build-id": "cqhSZTFeSPfHr8CBl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/commonelements~rag-ready-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-commonelements-rag-ready-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/commonelements~rag-ready-crawler/runs": { "post": { "operationId": "runs-sync-commonelements-rag-ready-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/commonelements~rag-ready-crawler/run-sync": { "post": { "operationId": "run-sync-commonelements-rag-ready-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more seed URLs to crawl.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlScope": { "title": "Crawl scope", "enum": [ "same-domain", "same-subdomain", "same-path", "start-urls-only" ], "type": "string", "description": "Which links to follow.", "default": "same-subdomain" }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Link hops from a start URL. 0 = only the start URLs.", "default": 3 }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Only crawl URLs matching these glob patterns, e.g. https://x.com/docs/**", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Skip URLs matching these globs, e.g. **/tag/**, **?print=1", "default": [], "items": { "type": "string" } }, "maxPages": { "title": "Max pages (hard cap)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard ceiling on pages crawled. Protects against runaway crawls and runaway bills.", "default": 200 }, "renderJs": { "title": "Render JavaScript", "type": "boolean", "description": "Use a headless browser for JS-heavy/SPA sites. Off = fast static HTTP crawl (recommended default).", "default": false }, "outputFormat": { "title": "Output format", "enum": [ "chunks-jsonl", "markdown", "langchain", "jsonl-bulk" ], "type": "string", "description": "RAG chunks = one record per chunk (recommended). Markdown = one record per page. LangChain = {page_content, metadata} Document JSON per chunk. JSONL bulk = flat one-record-per-chunk for bulk import.", "default": "chunks-jsonl" }, "enableChunking": { "title": "Enable chunking", "type": "boolean", "description": "Split each page into token-sized retrieval units. Forced ON when output format is RAG chunks.", "default": true }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 64, "maximum": 4096, "type": "integer", "description": "Target token budget per chunk (sized for your embedding model).", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 1024, "type": "integer", "description": "Token overlap between adjacent chunks (typically 10-20% of chunk size).", "default": 75 }, "dedupNearDuplicates": { "title": "Collapse near-duplicate chunks", "type": "boolean", "description": "Drop exact + near-duplicate chunks (shared boilerplate, syndicated content) via content hash + SimHash.", "default": true }, "filterJunkChunks": { "title": "Filter junk chunks", "type": "boolean", "description": "Drop near-empty, nav-residue, and low-information chunks.", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy configuration for the crawl. Apify Proxy recommended for large or rate-limited sites.", "default": { "useApifyProxy": true } }, "incremental": { "title": "Incremental sync (only new/changed pages)", "type": "boolean", "description": "When ON, pages whose content is unchanged since the last run are crawled but NOT re-emitted (not billed). Requires the actor to persist state in a named key-value store (see 'State store name').", "default": false }, "forceFullCrawl": { "title": "Force full crawl (ignore prior state)", "type": "boolean", "description": "Override: emit every page this run even if incremental is ON, then overwrite the saved state. Use after changing chunking settings or to rebuild a stale index.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store that persists per-URL content hashes between runs. Defaults to a deterministic name derived from the start URLs so scheduled re-runs of the same task share state automatically. Set explicitly to share state across tasks/schedules.", "default": "" }, "emitDeletions": { "title": "Emit tombstones for deleted pages", "type": "boolean", "description": "When incremental is ON, emit a deletion record for each URL seen last run but missing this run, so downstream vector stores can purge stale vectors. Tombstones are NOT billed.", "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 } } }, "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 } } } } } } } } } }