{ "openapi": "3.0.1", "info": { "title": "Document to Markdown Converter for AI", "description": "Convert PDF, DOCX, PPTX, XLSX, EPUB, HTML and images (with OCR) from public URLs into clean Markdown and structured JSON for AI agents and RAG.", "version": "1.0", "x-build-id": "8lbzInUQYKsz23fuy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jetlaunch~document-to-markdown-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jetlaunch-document-to-markdown-converter", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jetlaunch~document-to-markdown-converter/runs": { "post": { "operationId": "runs-sync-jetlaunch-document-to-markdown-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jetlaunch~document-to-markdown-converter/run-sync": { "post": { "operationId": "run-sync-jetlaunch-document-to-markdown-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Document URLs", "maxItems": 200, "type": "array", "description": "Public http or https links to documents, one per line. Up to 200 per run. Links to private networks, localhost or cloud metadata addresses are refused.", "items": { "type": "string" } }, "ocr": { "title": "Use OCR for scanned pages and images", "type": "boolean", "description": "Read text from pages that have no text layer and from image files. Pages that already contain text are never sent to OCR, so leaving this on only costs extra for scanned content (event: OCR page). Turn it off to skip scans and images.", "default": true }, "ocrQuality": { "title": "OCR quality", "enum": [ "fast", "high" ], "type": "string", "description": "Fast uses the compact OCR model and is about three times quicker, with similar results on clean scans. High uses the larger model for noisy, small or low-contrast text.", "default": "fast" }, "pageRange": { "title": "Page range (PDF only)", "type": "string", "description": "Convert only some pages of each PDF, for example 1-10, 5 or 3- (page 3 to the end). Leave empty for all pages. Ignored for other formats." }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Put the converted Markdown text in each output record. Turn it off if you only need tables, headings and metadata.", "default": true }, "tableFormat": { "title": "Table output", "enum": [ "csv", "json", "both", "none" ], "type": "string", "description": "How extracted tables are returned in the tables list: CSV text, JSON (columns and rows), both, or none. Tables are always kept in the Markdown as well.", "default": "csv" }, "tableMode": { "title": "Table accuracy (PDF and images)", "enum": [ "fast", "accurate" ], "type": "string", "description": "Fast is right for most documents. Accurate reads complex tables better and takes about 1.5 times longer.", "default": "fast" }, "includeDoclingJson": { "title": "Save full Docling JSON", "type": "boolean", "description": "Save the complete structured document (reading order, bounding boxes, every text and table item) as a JSON file in the run's key-value store. The record has a docling_json_url link. Not available when the fallback engine was used.", "default": false }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 200, "type": "integer", "description": "Documents with more pages than this are refused without charge. The upper limit is 200. Use the page range to convert part of a longer PDF.", "default": 200 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 50, "type": "integer", "description": "Files larger than this are refused without charge. The upper limit is 50.", "default": 50 } } }, "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 } } } } } } } } } }