{ "openapi": "3.0.1", "info": { "title": "Document to Markdown for AI & RAG", "description": "Convert PDF, Word, PowerPoint, Excel, CSV, HTML and TXT files into clean Markdown or plain text for LLMs and RAG. Keeps headings, lists and tables, splits into token-sized chunks with page and heading metadata, and OCRs scanned PDFs.", "version": "1.0", "x-build-id": "XP4CnTuywfXqFNtZL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/egra_van~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-egra_van-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/egra_van~document-to-markdown/runs": { "post": { "operationId": "runs-sync-egra_van-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/egra_van~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-egra_van-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Links to PDF, DOCX, PPTX, XLSX, CSV, TSV, HTML, TXT or Markdown files. Google Drive, Google Docs/Sheets/Slides, Dropbox, OneDrive/SharePoint, Box and GitHub share links are converted to direct downloads automatically (files must be shared as 'Anyone with the link').", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyValueStoreKeys": { "title": "…or files in a key-value store", "type": "array", "description": "Keys of files uploaded to an Apify key-value store. Use 'storeIdOrName/key', or just 'key' together with the store below (default: this run's store).", "items": { "type": "string" } }, "keyValueStoreId": { "title": "Key-value store ID or name", "type": "string", "description": "Store that holds the keys above." }, "datasetId": { "title": "…or dataset with URLs", "type": "string", "description": "Apify dataset (e.g. output of a crawler) whose items contain document URLs." }, "datasetUrlField": { "title": "Dataset URL field", "type": "string", "description": "Field of the dataset items that holds the URL.", "default": "url" }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "Output format.", "default": "markdown" }, "chunking": { "title": "Chunking", "enum": [ "none", "heading", "fixed" ], "type": "string", "description": "How to split documents into dataset items for embeddings / vector databases.", "default": "none" }, "chunkSize": { "title": "Chunk size", "minimum": 50, "maximum": 100000, "type": "integer", "description": "Maximum chunk size, in the unit below. Typical for embeddings: 300–1000 tokens.", "default": 800 }, "chunkSizeUnit": { "title": "Chunk size unit", "enum": [ "tokens", "characters" ], "type": "string", "description": "Chunk size unit.", "default": "tokens" }, "chunkOverlap": { "title": "Chunk overlap", "minimum": 0, "maximum": 50000, "type": "integer", "description": "How much text from the end of a chunk is repeated at the start of the next one (same unit). Max half of the chunk size.", "default": 100 }, "includePageNumbers": { "title": "Insert page markers", "type": "boolean", "description": "Adds (Markdown) or [Page N] (text) at every page/slide boundary. Page ranges are always in each item's metadata.", "default": false }, "includeSpeakerNotes": { "title": "Include PowerPoint speaker notes", "type": "boolean", "description": "Include PowerPoint speaker notes.", "default": true }, "ocr": { "title": "OCR scanned pages", "type": "boolean", "description": "Read image-only (scanned) PDF pages and image files (PNG, JPG, TIFF, WebP) with OCR. Only pages without a text layer are OCR'd, and only those are charged as OCR pages.", "default": false }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages present in the scanned documents. Fewer languages = faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "ron", "rus" ], "enumTitles": [ "English", "Romanian", "Russian" ] }, "default": [ "eng" ] }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Process only the first N pages/slides of each document (0 = all). For formats without pages the text is cut at N × 3,000 characters.", "default": 0 }, "maxDocuments": { "title": "Max documents", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Max documents.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Max file size (MB).", "default": 100 } } }, "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 } } } } } } } } } }