{ "openapi": "3.0.1", "info": { "title": "Website & Docs to Markdown + RAG Chunks", "description": "Turn websites & docs into clean Markdown plus token-bounded, embeddings-ready RAG chunks (heading lineage + sha256) ready for Pinecone, Weaviate, Qdrant or pgvector. Optional no-hallucination field extraction and AEO mode (FAQ, answer-first, llms.txt, citations). Robots honored; ownership required.", "version": "0.1", "x-build-id": "lLlA5xyj3J3kacix8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/awesome_highboy~aeo-rag-ready-content-structurer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-awesome_highboy-aeo-rag-ready-content-structurer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/awesome_highboy~aeo-rag-ready-content-structurer/runs": { "post": { "operationId": "runs-sync-awesome_highboy-aeo-rag-ready-content-structurer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/awesome_highboy~aeo-rag-ready-content-structurer/run-sync": { "post": { "operationId": "run-sync-awesome_highboy-aeo-rag-ready-content-structurer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "source", "ownership_attestation" ], "properties": { "source": { "title": "Source", "type": "object", "description": "The permissioned URLs to ingest: a URL list OR a sitemap you own / are authorized to crawl." }, "ownership_attestation": { "title": "Ownership / authorization attestation (REQUIRED — must be true)", "type": "boolean", "description": "You attest that you OWN or are AUTHORIZED to ingest every URL/sitemap above. The run is REJECTED before any fetch with zero events billed if this is not true (M5 Gate A / AC-OwnershipGate). This is the legality keystone (no third-party ToS violation, no anti-bot arms race).", "default": false }, "render": { "title": "Render mode", "enum": [ "http", "browser" ], "type": "string", "description": "http (default; got-scraping, cheapest) or browser (Playwright/Chromium for JS-heavy pages — higher per-page compute).", "default": "http" }, "outputMode": { "title": "Output mode", "enum": [ "rag", "aeo" ], "type": "string", "description": "rag (default — per-chunk Markdown + embeddings-ready JSON) or aeo (Answer-Engine assets: FAQ pairs / answer-first blocks / llms.txt / citation-structured). Same ownership/robots/paid-plan/QA gates apply to both.", "default": "rag" }, "chunking": { "title": "Chunking", "type": "object", "description": "strategy: semantic|fixed; maxTokens: int 128-2048 (default 512); overlapTokens: int (default 64). No emitted chunk exceeds maxTokens (AC-ChunkBound)." }, "extractSchema": { "title": "Structured extraction schema (optional)", "type": "object", "description": "Optional per-page extraction. fields: [{name, type, instruction}]. Values are NEVER hallucinated - a field with no answer returns null. field_extracted is charged only per (page x field) pair returning a non-null value." }, "aeo": { "title": "AEO asset options (used only when outputMode=aeo)", "type": "object", "description": "assets: which AEO record kinds to emit — any of ['faq_pair','answer_block','llms_txt','citation_block']. AEO answers obey the no-hallucination contract (an absent answer is OMITTED, never invented)." }, "model": { "title": "Extraction model", "enum": [ "haiku", "sonnet" ], "type": "string", "description": "haiku (default; claude-haiku-4-5, cheapest) or sonnet (claude-sonnet-4-6, higher-fidelity extraction). All Claude calls route via M2 -> M7 LiteLLM gateway (the ONLY Anthropic egress); never raw Anthropic. Opus is VERIFY-only at build time and is NOT a runtime option.", "default": "haiku" }, "respectRobotsTxt": { "title": "Respect robots.txt (forced true — cannot be disabled)", "type": "boolean", "description": "robots.txt is ALWAYS honored. Disallowed URLs are listed in robots_skipped_urls and emit 0 chunks (0 charge). This cannot be set false via the API (M5 Gate C / AC-Robots); the value is forced true regardless of input (EU AI Act machine-readable opt-out compliance).", "default": true }, "language": { "title": "Language hint (ISO code, optional)", "type": "string", "description": "Optional ISO language-code hint (e.g. 'en')." } } }, "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 } } } } } } } } } }