{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text Extractor: DOCX, PPTX, Excel + OCR", "description": "Convert PDF, Word, PowerPoint, Excel, CSV, HTML and image files to clean Markdown or text for LLMs and RAG: headings, tables, reading order, page markers and chunks. Scanned pages are OCR'd locally with Tesseract. Pay per page; blank and failed pages are free.", "version": "1.0", "x-build-id": "oP8kpSZ06acyDLaix" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pewterdesk~documents-to-ai-ready-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pewterdesk-documents-to-ai-ready-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pewterdesk~documents-to-ai-ready-markdown/runs": { "post": { "operationId": "runs-sync-pewterdesk-documents-to-ai-ready-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pewterdesk~documents-to-ai-ready-markdown/run-sync": { "post": { "operationId": "run-sync-pewterdesk-documents-to-ai-ready-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "files": { "title": "Upload files", "type": "array", "description": "Upload your documents (PDF, DOCX, PPTX, XLSX, CSV, HTML, TXT/MD, PNG/JPG/TIFF/WEBP). Only process files you own or have the right to use." }, "fileUrls": { "title": "File URLs", "type": "array", "description": "Direct links to your files. Google Drive / Docs, Dropbox and GitHub share links are converted to download links automatically (the file must be shared as 'anyone with the link').", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps structure that LLMs use well; plain text strips formatting.", "default": "markdown" }, "chunkSize": { "title": "Chunk size (characters, 0 = no chunking)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Split each document into RAG-ready chunks on paragraph/table boundaries, with page ranges. ~4 characters ≈ 1 token, so 2000 ≈ 500 tokens.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Trailing paragraphs repeated at the start of the next chunk (at most half the chunk size).", "default": 200 }, "outputMode": { "title": "Dataset rows", "enum": [ "document", "chunks" ], "type": "string", "description": "'One row per chunk' needs a chunk size above 0. Billing is the same either way.", "default": "document" }, "includePages": { "title": "Include per-page output", "type": "boolean", "description": "Adds a 'pages' array with Markdown, method (text/ocr) and OCR confidence for every page/slide/sheet.", "default": false }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto uses the PDF's text layer when it's good and falls back to local Tesseract OCR for scanned, image-only or broken-encoding pages. Images are always OCR'd.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages in your scanned documents. Picking only the ones you need is faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish" ] }, "default": [ "eng" ] }, "extractTables": { "title": "Detect tables", "type": "boolean", "description": "Render ruled PDF tables as Markdown tables in reading position.", "default": true }, "pageRange": { "title": "Page range (PDF)", "type": "string", "description": "Optional, e.g. '1-5, 8, 20-'. Pages outside the range are skipped and not billed." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Safety cap per file (0 = unlimited).", "default": 500 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Only if your PDFs are password-protected." }, "includeSpeakerNotes": { "title": "Include PowerPoint speaker notes", "type": "boolean", "description": "Appends slide speaker notes as a quote under each slide.", "default": true }, "htmlMainContentOnly": { "title": "HTML: main content only", "type": "boolean", "description": "Drops navigation, footers, sidebars, scripts and forms from HTML files.", "default": true }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (not charged).", "default": 100 }, "maxConcurrency": { "title": "Files processed in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "Raise together with memory (each 1 GB ≈ one parallel OCR job).", "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 } } } } } } } } } }