{ "openapi": "3.0.1", "info": { "title": "Document to Markdown (PDF, Word, PowerPoint, Excel) + OCR", "description": "Convert PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX), EPUB, HTML and images to clean Markdown from URLs, with OCR for scanned PDFs, tables, page selection and RAG chunks. Built on Microsoft MarkItDown, made for LLMs and AI agents.", "version": "1.0", "x-build-id": "WV1yakw9uRFcOqgDT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fast_data_asap~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fast_data_asap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fast_data_asap~document-to-markdown/runs": { "post": { "operationId": "runs-sync-fast_data_asap-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fast_data_asap~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-fast_data_asap-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documentUrls" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Public links to the files you want as Markdown: PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX/XLS), EPUB, HTML, CSV, JSON, TXT, or images (PNG, JPG, TIFF, WebP) for OCR. Google Drive, Google Docs, Dropbox and GitHub share links are converted to direct downloads automatically. Max 50 MB per file.", "items": { "type": "string" } }, "pages": { "title": "Pages", "type": "string", "description": "Optional. Which pages to convert, e.g. \"1-5\", \"1,3,7-9\" or \"10-\" (page 10 to the end). Applies to PDF pages, PowerPoint slides, Excel sheets and multi-page TIFFs. Leave empty for all pages. You only pay for the pages you select." }, "ocr": { "title": "OCR (scanned PDFs and images)", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto: OCR only PDF pages that have (almost) no text layer, plus images. always: OCR every PDF page (for PDFs with a broken text layer). never: no OCR, text layer only.", "default": "auto" }, "outputChunks": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Optional. Also split the Markdown into paragraph-aware chunks of up to this many characters, each with the page range it came from. Ready for embeddings and vector databases. 0 = off.", "default": 0 }, "includePageBreaks": { "title": "Mark page breaks", "type": "boolean", "description": "Insert invisible Markdown comments like (or , ) before every page, so an LLM can cite page numbers.", "default": true }, "maxConcurrency": { "title": "Max parallel documents", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents are downloaded and converted at the same time.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Downloads go out directly by default. Use a proxy only if a server refuses direct 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 } } } } } } } } } }