{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor & PDF to Markdown - OCR, Word, Excel", "description": "Document parser and PDF parser for LLMs: convert PDF, Word (DOCX/DOC), PowerPoint, Excel and CSV to clean Markdown text. PDF OCR for scanned files, RAG chunks. URLs, uploads, base64. $2/1,000 docs.", "version": "0.1", "x-build-id": "lXY7XlkcC9vYmjoFn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidytools~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidytools-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidytools~document-to-markdown/runs": { "post": { "operationId": "runs-sync-tidytools-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/tidytools~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-tidytools-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": "Main input (fill this, or `documentFile` / `base64Documents`). Public links to PDF, DOCX, DOC, RTF, PPTX, PPT, XLSX, XLS, CSV, ODT, ODS, ODP or XML files (up to 15 MB each), one per line. Google Drive, Google Docs/Sheets/Slides, Dropbox and OneDrive/SharePoint share links are turned into direct downloads automatically. HTML pages also work. Blank or invalid lines are skipped and listed in the results (not charged).", "items": { "type": "string" } }, "documentFile": { "title": "Or upload a file", "type": "string", "description": "Upload one PDF, DOCX, DOC, RTF, PPTX, PPT, XLSX, XLS, CSV, ODT, ODS or ODP file (up to 15 MB) instead of, or in addition to, the URLs." }, "base64Documents": { "title": "Base64 documents (API)", "type": "array", "description": "For API and AI-agent calls: a list of {\"fileName\": \"report.pdf\", \"data\": \"\"}. The file name's extension tells the converter the format. Up to 15 MB per file." }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "If set (e.g. 2000), each document also gets a \"chunks\" array split at paragraph boundaries. 0 = off.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated between consecutive chunks.", "default": 200 }, "outputMode": { "title": "Output rows", "enum": [ "document", "chunks" ], "type": "string", "description": "\"One row per chunk\" splits each document (chunk size above, 2,000 if 0) and outputs every chunk as its own row with chunkIndex and headingPath. Charged per document either way. Values: document = One row per document; chunks = One row per chunk (for vector databases and CSV).", "default": "document" }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many documents are converted at the same time.", "default": 10 }, "httpVia": { "title": "Plain HTTP requests from", "enum": [ "auto", "backend", "direct", "vm" ], "type": "string", "description": "Some sites block requests from data centers. Auto retries from a second network before falling back to a real browser. If both are refused, Auto also tries our second server (Oracle, different IP) before a real browser.", "default": "auto" }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Only used for requests sent from Apify's network. Apify proxy usage is billed to your Apify account." }, "pdfCleanup": { "title": "Clean up PDF text", "type": "boolean", "description": "For PDFs with a text layer: join words hyphenated at line ends (\"repre-sentation\"), put back spaces lost between text blocks (\"AbstractWe\") and rebuild simple number tables as Markdown tables. Each item reports what was changed in \"pdfCleanup\". Turn off to get the raw converter text.", "default": true }, "ocr": { "title": "OCR for scanned PDFs", "type": "boolean", "description": "Transcribe PDFs that have no text layer (scans, photos of pages) with an AI vision model, page by page. Tables become Markdown tables; most languages work, including Chinese and Japanese. Costs $0.005 per transcribed page on top of the document price, and only applies to PDFs without extractable text.", "default": false }, "ocrMaxPages": { "title": "OCR: max pages per document", "minimum": 1, "maximum": 500, "type": "integer", "description": "Only the first pages up to this number are transcribed (a cost cap). The item gets \"ocrTruncated\": true when the PDF has more pages.", "default": 20 }, "ocrLanguage": { "title": "OCR: document language (optional)", "type": "string", "description": "A hint such as \"Traditional Chinese\", \"German\" or \"Japanese\". Leave empty to detect it." }, "documentUrls": { "title": "Document URLs (request list, optional)", "type": "array", "description": "Same as the list above, in Apify's request-list format (also accepts a link to a text file of URLs). Kept for older inputs; the plain list above is recommended, especially for API calls.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } } } }, "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 } } } } } } } } } }