{ "openapi": "3.0.1", "info": { "title": "Document to Markdown & Text: PDF, OCR, Word, PowerPoint", "description": "Convert PDFs, scans, images, DOCX, PPTX, XLSX and HTML to clean Markdown and text for LLMs and RAG. Tables become Markdown tables; scanned pages are read with Tesseract OCR (24 languages). $0.004 per document, $0.002 per OCR page or image; failed files free.", "version": "0.1", "x-build-id": "eOJSYGQ95BKutnOBS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webstack-labs~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webstack-labs-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/webstack-labs~document-to-markdown/runs": { "post": { "operationId": "runs-sync-webstack-labs-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/webstack-labs~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-webstack-labs-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", "properties": { "fileUrls": { "title": "File links", "type": "array", "description": "Direct links to the files to convert: PDF (text or scanned), PNG, JPEG, TIFF, WebP, BMP, GIF, DOCX, PPTX, XLSX, HTML, CSV, TXT or Markdown. One row per file. Leave empty to convert a free 2-page sample PDF and see the output.", "items": { "type": "string" } }, "ocr": { "title": "OCR", "enum": [ "auto", "always", "never" ], "type": "string", "description": "When to read pages with OCR (Tesseract). auto (default): only PDF pages with no usable text layer (scans) and images. always: every PDF page, for PDFs with a broken text layer. never: no OCR (images then fail, free).", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the text for OCR, 1 to 4 codes (Tesseract or ISO): eng, deu, fra, spa, ita, por, nld, pol, rus, ukr, tur, jpn, chi_sim, chi_tra, kor, ara, hin, vie, ind, swe, dan, nor, fin, ces (or en, de, ja, zh ...). Default: eng.", "default": [ "eng" ], "items": { "type": "string" } }, "pageRange": { "title": "Pages", "type": "string", "description": "Pages (or slides) to convert, for example \"1-5, 8, 12-\". Empty (default): all pages, up to maxPagesPerFile." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop after this many pages or slides of one file (the row is then marked truncated). Default 200.", "default": 200 }, "extractTables": { "title": "Tables as Markdown", "type": "boolean", "description": "Detect tables on PDF text pages and return them as Markdown tables (Word, PowerPoint, Excel, HTML and CSV tables are always kept). Default true.", "default": true }, "includePages": { "title": "Per-page text", "type": "boolean", "description": "Add a pages list to each row: page number, text, whether OCR was used and its confidence. Default true.", "default": true }, "includePlainText": { "title": "Plain text", "type": "boolean", "description": "Add the plain text (without Markdown) to each row in the text field. Default true. The Markdown is always returned, in the row and as a .md file.", "default": true }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution at which scanned PDF pages are rendered for OCR. Higher reads small print better but is slower. Default 200.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (free row with an error). Default 100.", "default": 100 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Check each site's robots.txt before downloading. Turn off only for files you own or may download. Default true.", "default": true } } }, "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 } } } } } } } } } }