{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text Extractor: Word, HTML, OCR for RAG", "description": "Convert PDF, Word, PowerPoint, Excel, web pages and images to clean, LLM-ready Markdown. Paste links or upload files, click Start. Headings, lists and tables kept, optional OCR for scans, RAG chunks. No start fee.", "version": "0.1", "x-build-id": "adydxLjX9SPaLYUXp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/alpine-data~docs-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-alpine-data-docs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/alpine-data~docs-to-markdown/runs": { "post": { "operationId": "runs-sync-alpine-data-docs-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/alpine-data~docs-to-markdown/run-sync": { "post": { "operationId": "run-sync-alpine-data-docs-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "1. Links to your documents (PDF, Word, PowerPoint, Excel, web page or image)", "type": "array", "description": "One link per line (commas also work, https:// is optional). Direct file links, Google Drive / Dropbox / GitHub share links and normal web pages all work. Supported: PDF, DOCX, PPTX, XLSX, HTML, TXT/MD/CSV/JSON, PNG/JPG/TIFF/WebP (images need OCR). Leave empty and upload files below instead. If you leave links, files and dataset empty, a small paid example runs instead: 1 sample PDF (15 pages), measured charge $0.0095.", "items": { "type": "string" } }, "files": { "title": "…or upload files from your computer", "type": "array", "description": "Upload one or more files (PDF, DOCX, PPTX, XLSX, HTML, images). They are stored in your own Apify storage and converted like links." }, "useOcr": { "title": "2. Read scanned pages and images (OCR)", "type": "boolean", "description": "Off = fast and cheap: text is read from the file itself. On = pages without a text layer (scans, photos, images) are read with OCR (Tesseract) and charged as OCR pages. Pages that already have text are never OCR'd twice.", "default": false }, "ocrLanguages": { "title": "3. Language of the scanned text", "type": "array", "description": "Only used when OCR is on. Pick one or more languages (each extra language makes OCR a little slower).", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "tur", "swe", "dan", "nor", "fin", "ron", "hun", "hrv", "slv", "slk" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Turkish", "Swedish", "Danish", "Norwegian", "Finnish", "Romanian", "Hungarian", "Croatian", "Slovenian", "Slovak" ] }, "default": [ "eng" ] }, "outputFormat": { "title": "What do you want back?", "enum": [ "document", "chunks", "pages" ], "type": "string", "description": "Document = one row per file with the full Markdown. RAG chunks = one row per chunk (with heading path), ready for a vector database. Pages = one row per page/slide.", "default": "document" }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 100, "maximum": 8000, "type": "integer", "description": "Only for RAG chunks. Approximate tokens per chunk (1 token ≈ 4 characters). Chunks split at headings and paragraphs.", "default": 800 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Only for RAG chunks. How much text is repeated between neighbouring chunks.", "default": 80 }, "keepLinks": { "title": "Keep hyperlinks", "type": "boolean", "description": "Off = link text only (cleaner for AI). On = keep [text](url) links in the Markdown.", "default": false }, "webPageMainContentOnly": { "title": "Web pages: main content only", "type": "boolean", "description": "On = drop menus, cookie banners, footers and sidebars from web pages. Off = convert the whole page.", "default": true }, "includeSlideNotes": { "title": "PowerPoint: include speaker notes", "type": "boolean", "description": "Add each slide's speaker notes below the slide text.", "default": true }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save every document as a .md file (plus ALL_DOCUMENTS.md) in the run's key-value store, with a download link in each row.", "default": true }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop converting a document after this many pages (for Word, Excel and web pages: 3,000 characters = 1 page). You only pay for converted pages.", "default": 300 }, "maxDocuments": { "title": "Max documents per run", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Only the first N links/files are processed.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped (not charged). Big scanned PDFs need more memory: see README.", "default": 50 }, "datasetId": { "title": "Read links from a dataset", "type": "string", "description": "Pick a dataset (e.g. from a crawler run). Every row's link field is converted, together with the links above." }, "datasetUrlField": { "title": "Link field in that dataset", "type": "string", "description": "Name of the column holding the file link, e.g. url, fileUrl, pdfUrl.", "default": "url" }, "ocrForceAllPages": { "title": "OCR every page (even pages with text)", "type": "boolean", "description": "Only for broken PDFs whose text layer is garbage. Every page is then charged as an OCR page.", "default": false }, "detectTables": { "title": "Detect tables in PDFs", "type": "boolean", "description": "Turn tables into Markdown tables. Switch off if a PDF's layout gets mangled.", "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 } } } } } } } } } }