{ "openapi": "3.0.1", "info": { "title": "PDF & DOCX to Markdown – Excel, PowerPoint, Tables, OCR for RAG", "description": "Convert PDF, Word, Excel and PowerPoint files to clean Markdown for AI and RAG: tables as real Markdown tables and JSON rows, scanned pages via OCR, one row per document, page or chunk. Fills in the files the Website Content Crawler downloads but leaves empty.", "version": "0.1", "x-build-id": "KkkG2rhCROLSTVdwI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/perceptr0n~pdf-to-markdown-converter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-perceptr0n-pdf-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/perceptr0n~pdf-to-markdown-converter/runs": { "post": { "operationId": "runs-sync-perceptr0n-pdf-to-markdown-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/perceptr0n~pdf-to-markdown-converter/run-sync": { "post": { "operationId": "run-sync-perceptr0n-pdf-to-markdown-converter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Links to PDF, Word (.docx), Excel (.xlsx, .xls), PowerPoint (.pptx), HTML, CSV, JSON, XML or text files — one per line.", "items": { "type": "string" } }, "crawler_dataset": { "title": "Website Content Crawler run or dataset ID", "type": "string", "description": "Convert the files a **Website Content Crawler** run downloaded (option 'Save files'). The crawler stores them with an empty `text` and `markdown`; this fills them in, with the same `url`, `crawl` and `metadata` fields, so the results merge straight into your crawl. Paste the run ID or its dataset ID." }, "output": { "title": "Output", "enum": [ "documents", "pages", "chunks" ], "type": "string", "description": "**Documents**: one row per file with the full Markdown. **Pages**: one row per page — handy for citations. **Chunks**: ready-made pieces for vector databases and RAG, with the pages each chunk covers.", "default": "documents" }, "ocr": { "title": "Text recognition (scanned pages)", "enum": [ "auto", "off", "force" ], "type": "string", "description": "**Auto**: pages without a text layer (scans, photos of paper) are read with OCR and charged as OCR pages; all others are read directly. **Off**: never OCR. **Force**: OCR every page, for PDFs whose text layer is broken.", "default": "auto" }, "ocr_languages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned documents. Fewer languages recognise faster and more accurately.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "nld", "pol", "por" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Dutch", "Polish", "Portuguese" ] }, "default": [ "eng", "deu" ] }, "extract_tables": { "title": "Extract tables", "type": "boolean", "description": "Detects tables in PDFs and returns them as Markdown tables in place and as structured rows in `tables`. Excel and Word tables are always included.", "default": true }, "chunk_size": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Only for output 'RAG chunks'. Chunks break at paragraph boundaries; a table stays in one piece where it fits.", "default": 2000 }, "chunk_overlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Only for output 'RAG chunks'. Whole paragraphs from the end of one chunk are repeated at the start of the next, up to this length.", "default": 200 }, "max_pages": { "title": "Maximum pages per document", "minimum": 1, "type": "integer", "description": "Longer PDFs are cut off here and say so in `warnings`. Protects your budget from a surprise 3,000-page file.", "default": 500 }, "max_file_mb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped with a message, and not charged.", "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 } } } } } } } } } }