{ "openapi": "3.0.1", "info": { "title": "Document to Markdown – PDF, Word, PowerPoint, Excel + OCR", "description": "Convert PDF, DOCX, PPTX, XLSX, HTML, EPUB and images to clean Markdown or plain text for LLMs and RAG. Tables kept, scanned pages read with OCR in 100+ languages, optional RAG chunks with page numbers.", "version": "1.0", "x-build-id": "N8noQJog3REndVZb6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kris_fili~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kris_fili-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kris_fili~document-to-markdown/runs": { "post": { "operationId": "runs-sync-kris_fili-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kris_fili~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-kris_fili-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Document URLs", "type": "array", "description": "Direct links to files: PDF, DOCX, PPTX, XLSX, XLS, CSV, HTML, EPUB, TXT, MD, JSON, XML, MSG, IPYNB or images (PNG, JPEG, TIFF, WebP). Google Drive, Google Docs, Dropbox and GitHub share links are converted to downloads automatically (files must be shared as 'anyone with the link').", "items": { "type": "string" } }, "files": { "title": "…or upload files", "type": "array", "description": "Upload documents from your computer (stored in your Apify key-value store)." }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps headings, lists and tables (best for LLMs). Text removes the Markdown syntax.", "default": "markdown" }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "0 = one result per document. Above 0 = split each document into chunks of at most this many characters (about 4 characters per token) – one dataset item per chunk with page numbers and heading path, ready for a vector database. Paragraphs and tables are kept together when possible.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many characters from the end of a chunk are repeated at the start of the next one (only with chunking).", "default": 150 }, "ocr": { "title": "OCR (scanned pages and images)", "enum": [ "auto", "always", "off" ], "type": "string", "description": "Auto: OCR only pages without a text layer (scans, photos). Always: OCR every PDF page (for PDFs with a broken text layer). Off: never OCR.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Language(s) of scanned text, joined with +, e.g. eng, deu, fra, spa, pol, eng+deu, chi_sim, jpn. Two-letter codes work too (en, de, pl). 100+ languages supported.", "default": "eng" }, "ocrPageSegmentation": { "title": "OCR layout mode", "enum": [ "auto", "single-column", "single-block", "sparse" ], "type": "string", "description": "Auto works for most documents. Use single column for receipts and narrow text, sparse for forms, signs and screenshots with scattered text.", "default": "auto" }, "pageRange": { "title": "Pages (PDF)", "type": "string", "description": "Convert only these PDF pages, e.g. 1-5,8,10- (empty = all pages)." }, "maxPages": { "title": "Maximum pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit per document (PDF pages, image frames).", "default": 500 }, "pageMarkers": { "title": "Page markers", "type": "boolean", "description": "Insert (or ) comments between pages in the Markdown.", "default": false }, "removeHeadersFooters": { "title": "Remove repeated headers, footers and page numbers (PDF)", "type": "boolean", "description": "Lines repeated at the top or bottom of most pages (running titles, page numbers) are removed – cleaner text for LLMs.", "default": true }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save every document as a .md file in the run's key-value store (link in 'markdownUrl').", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs (used for all PDFs in this run)." }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Bigger files are skipped with an error (no charge).", "default": 100 }, "maxFiles": { "title": "Maximum files", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many files.", "default": 1000 }, "maxConcurrency": { "title": "Files processed in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "For many small files raise it (and the run memory). OCR uses all CPU cores of the run anyway.", "default": 2 } } }, "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 } } } } } } } } } }