{ "openapi": "3.0.1", "info": { "title": "PDF, Image & Office to Text/Markdown with OCR", "description": "Input links to PDF, scanned PDF, image, DOCX, PPTX or XLSX files (Google Drive and Dropbox links work). Output one item per document: clean text, LLM-ready Markdown with tables, per-page content, optional RAG chunks. OCR in 24 languages only where needed.", "version": "0.1", "x-build-id": "dmzzuctIwMTfW7urf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jadelike_mustang~document-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jadelike_mustang-document-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jadelike_mustang~document-to-text/runs": { "post": { "operationId": "runs-sync-jadelike_mustang-document-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jadelike_mustang~document-to-text/run-sync": { "post": { "operationId": "run-sync-jadelike_mustang-document-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documents" ], "properties": { "documents": { "title": "Document URLs", "type": "array", "description": "Public links to PDF, image (PNG, JPG, TIFF, WebP, BMP, GIF), Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files. Google Drive and Dropbox share links work too.", "items": { "type": "string" } }, "ocrMode": { "title": "OCR", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto reads the PDF text layer and runs OCR only on pages without text (scans). Images are always read with OCR.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages in the scanned documents. Pick only the ones you need: more languages = slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "ita", "spa", "por", "nld", "pol", "swe", "dan", "nor", "fin", "ces", "ron", "hun", "tur", "rus", "ukr", "ell", "chi_sim", "jpn", "kor", "ara", "hin" ], "enumTitles": [ "English", "German", "French", "Italian", "Spanish", "Portuguese", "Dutch", "Polish", "Swedish", "Danish", "Norwegian", "Finnish", "Czech", "Romanian", "Hungarian", "Turkish", "Russian", "Ukrainian", "Greek", "Chinese (simplified)", "Japanese", "Korean", "Arabic", "Hindi" ] }, "default": [ "eng" ] }, "pages": { "title": "Pages", "type": "string", "description": "PDF pages to read, e.g. '1-5,8'. Leave empty for all." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Stop after this many pages in each document. 0 or empty = no limit." }, "includePages": { "title": "Include per-page content", "type": "boolean", "description": "Add a 'pages' list with text, Markdown, tables and OCR flag for each page (slide, sheet).", "default": true }, "includeTables": { "title": "Include tables as data", "type": "boolean", "description": "Add the tables found on each page as rows of cells (they are always in the Markdown).", "default": true }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "type": "integer", "description": "Also split the Markdown into chunks of at most this many characters, on paragraph boundaries (e.g. 2000). 0 or empty = no chunks." }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution used to render scanned PDF pages for OCR. 300 for small print, 200 is faster.", "default": 200 } } }, "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 } } } } } } } } } }