{ "openapi": "3.0.1", "info": { "title": "Document to Markdown — PDF, Word, PowerPoint, Excel, OCR", "description": "Convert PDF, DOCX, PPTX, XLSX, HTML, CSV, EPUB and images to clean Markdown for LLMs and RAG. Scanned pages are read with OCR. $2 per 1,000 pages.", "version": "0.0", "x-build-id": "AVpRkmex0Twm0p5MJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saliga~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saliga-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/saliga~document-to-markdown/runs": { "post": { "operationId": "runs-sync-saliga-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/saliga~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-saliga-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": [ "urls" ], "properties": { "urls": { "title": "File URLs", "type": "array", "description": "Links to the files to convert: PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, TXT, MD, EPUB or an image (PNG, JPEG, TIFF, WebP). One result per file. The type is detected from the file itself.", "items": { "type": "string" } }, "extractTables": { "title": "Tables as Markdown tables", "type": "boolean", "description": "Detect tables in PDFs, with or without lines between cells, and output them as Markdown tables in place, with the caption above. Turn off to get their text as plain paragraphs.", "default": true }, "ocr": { "title": "OCR (scanned pages)", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto: read a PDF page with OCR only when it has no text layer but has an image (scans, photos). Always: OCR every PDF page. Never: text layer only. Images are always read with OCR.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "type": "string", "description": "Language of the scanned text. Combine with +, for example eng+deu. Available: eng, deu, fra, spa, ita, por, nld, tur, pol, swe.", "default": "eng" }, "maxPages": { "title": "Max pages per file", "minimum": 0, "type": "integer", "description": "Stop after this many pages of each PDF or image file (0 = all pages). Useful to cap the cost of very long documents.", "default": 0 }, "splitByPage": { "title": "One result per page", "type": "boolean", "description": "For PDFs and images, output one dataset item per page instead of one per file. Handy for chunking in RAG pipelines.", "default": false }, "pageMarkers": { "title": "Page markers", "type": "boolean", "description": "Insert before each PDF page so you can cite page numbers.", "default": true }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Also return the Markdown split into chunks of about this many characters (0 = off). Paragraphs and tables are not cut unless they are larger than a chunk; big tables are split between rows with the header repeated. Try 1500.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters of the previous chunk repeated at the start of the next one, cut at a word boundary (at most half the chunk size).", "default": 200 }, "requestHeaders": { "title": "Request headers", "type": "object", "description": "Extra HTTP headers for downloading, for example {\"Authorization\": \"Bearer …\"} for files behind a token. Sent only to the host of each URL, never to a redirect on another host. They are stored with the run input, so prefer short-lived tokens or pre-signed URLs." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Files larger than this are skipped with an error.", "default": 100 }, "maxConcurrency": { "title": "Files at a time", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files are downloaded and converted in parallel.", "default": 3 } } }, "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 } } } } } } } } } }