{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown with OCR, Tables and RAG Chunks", "description": "Turn PDF links into Markdown with headings, lists and tables, OCR for scanned pages (English and Arabic built in), a quality report per file and heading-based RAG chunks. No browser. Pay per PDF plus per OCR page.", "version": "0.1", "x-build-id": "WAXQ3EjFSvAj7welG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadharbor~pdf-to-markdown-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadharbor-pdf-to-markdown-ocr", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadharbor~pdf-to-markdown-ocr/runs": { "post": { "operationId": "runs-sync-leadharbor-pdf-to-markdown-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadharbor~pdf-to-markdown-ocr/run-sync": { "post": { "operationId": "run-sync-leadharbor-pdf-to-markdown-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "PDF links", "type": "array", "description": "Public links to PDF files (up to 100 per run, 25 MB each). Google Drive and Dropbox share links are turned into direct download links; any other link must point straight at the PDF. Links to private networks, localhost and pages that need a login are refused.", "items": { "type": "string" } }, "enableOcr": { "title": "OCR for scanned pages", "enum": [ "auto", "always", "never" ], "type": "string", "description": "'auto' reads a page with OCR only when it has no usable text layer (a page made of an image, or a text layer full of unreadable characters). 'always' runs OCR on every page. 'never' reads text layers only. Each page read by OCR is billed as an OCR page ($0.007); pages whose OCR text is unreliable are delivered but not billed.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Language codes of the text on scanned pages, at most 3, for example [\"eng\"], [\"ara\", \"eng\"] or [\"deu\", \"fra\"]. English (eng) and Arabic (ara) are built in; every other official Tesseract 'tessdata_fast' language is downloaded when needed. List the main language first. Right-to-left languages are returned in logical reading order. Only English and Arabic were benchmarked: any other language is marked experimental in the quality report.", "default": [ "eng" ], "items": { "type": "string" } }, "outputFormat": { "title": "Output", "enum": [ "all", "markdown", "per_page", "chunks" ], "type": "string", "description": "'all' returns the Markdown, one entry per page and the chunks. 'markdown' returns only the whole-document Markdown. 'per_page' returns one entry per page with its source (text layer or OCR) and confidence. 'chunks' returns only the heading-based chunks for RAG. Fields you do not ask for are null.", "default": "all" }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to convert, for example 1-5, 8, 12- (an open end means to the last page). Leave empty for the whole document. Page numbers in the output are the numbers of the original document.", "default": "" }, "maxPages": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "At most this many of the selected pages are converted per PDF. The row says so in its warnings when pages were left out. Above 300 every row carries a warning that a long OCR job can reach the 30 minute limit and come back as a partial result.", "default": 100 }, "password": { "title": "PDF password", "type": "string", "description": "Opens password-protected PDFs. The same password is tried on every link in the run. It is never stored in the output." }, "maxChunkTokens": { "title": "Maximum tokens per chunk", "minimum": 100, "maximum": 8000, "type": "integer", "description": "Longer sections are split at paragraph boundaries so no chunk goes over this size. Tokens are approximate (characters divided by 4).", "default": 800 }, "includePageMarkers": { "title": "Keep page markers", "type": "boolean", "description": "Adds before each page in the Markdown. Chunks keep their page numbers either way.", "default": true } } }, "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 } } } } } } } } } }