{ "openapi": "3.0.1", "info": { "title": "Document to Markdown - PDF, Word, Excel, PowerPoint to Text", "description": "Convert PDF, DOCX, XLSX, PPTX, HTML and CSV files from URLs into clean Markdown or plain text for AI, RAG and LLM pipelines. Tables kept, pages split, pay per document.", "version": "1.0", "x-build-id": "wrqWziLO79tu67rcS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/adaptive_arbor_rtz~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-adaptive_arbor_rtz-document-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/adaptive_arbor_rtz~document-to-markdown/runs": { "post": { "operationId": "runs-sync-adaptive_arbor_rtz-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/adaptive_arbor_rtz~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-adaptive_arbor_rtz-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Links to documents, one per line. Supported: PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx), HTML pages, CSV, TXT, Markdown and JSON, plus scanned PDFs and images (PNG, JPEG, WebP, TIFF) via OCR. The file type is detected from the content, so links without a file extension work too.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "markdown keeps headings, lists and tables (best for AI/LLM and RAG pipelines). text is plain text without formatting.", "default": "markdown" }, "includePages": { "title": "Split into pages", "type": "boolean", "description": "Also return a 'pages' array with one entry per PDF page, slide or spreadsheet sheet. Useful for citations and chunking.", "default": false }, "ocr": { "title": "OCR (scanned PDFs and images)", "enum": [ "auto", "always", "off" ], "type": "string", "description": "auto = recognise text only on PDF pages without a text layer (scanned pages) and in image files (PNG, JPEG, WebP, TIFF, GIF, BMP). always = OCR every PDF page. off = never. OCR is charged per recognised page.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Language(s) of the scanned text, e.g. 'eng', 'deu', 'fra', 'isl', or several like 'eng+deu'. English names such as 'German' work too. Default English.", "default": "eng" }, "maxOcrPages": { "title": "Max OCR pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop OCR after this many pages per document, to cap cost on long scans.", "default": 50 }, "maxPages": { "title": "Max pages or slides", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after this many PDF pages or slides per document.", "default": 1000 }, "maxRowsPerSheet": { "title": "Max rows per sheet", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many rows per Excel sheet or CSV file.", "default": 5000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip larger files (not charged).", "default": 50 }, "timeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Give up on a download after this many seconds (not charged).", "default": 120 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many documents to process at the same time.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Use a proxy if a server blocks data-centre downloads.", "default": { "useApifyProxy": 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 } } } } } } } } } }