{ "openapi": "3.0.1", "info": { "title": "PDF & Image to Text API: OCR, Markdown, Tables, RAG Chunks", "description": "Extract text from PDFs, scanned PDFs, images (PNG, JPG, TIFF) and DOCX by URL: full text, Markdown, per-page text, OCR confidence, tables, metadata, RAG chunks. Auto-OCR in 20 languages. $1.50/1K docs, $4/1K OCR pages.", "version": "1.0", "x-build-id": "9sS98legtVNfPxeN7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/magnova~pdf-ocr-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-magnova-pdf-ocr-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/magnova~pdf-ocr-text-extractor/runs": { "post": { "operationId": "runs-sync-magnova-pdf-ocr-text-extractor", "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/magnova~pdf-ocr-text-extractor/run-sync": { "post": { "operationId": "run-sync-magnova-pdf-ocr-text-extractor", "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": "File URLs (PDF, image or DOCX)", "type": "array", "description": "Direct links to the files to extract text from: PDF (digital or scanned), PNG, JPG, TIFF (multi-page), WebP, GIF, BMP or DOCX. The link must return the file itself, not a viewer page. Example: https://www.irs.gov/pub/irs-pdf/fw9.pdf", "items": { "type": "string" } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto = use the PDF text layer and run OCR only on pages that have no text but contain an image (scanned pages). always = OCR every page (use for PDFs with broken text layers). never = never OCR; images then return no text. Example: auto", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages Tesseract should recognise. Pick every language that appears in the documents (more languages = slower). Example: [\"eng\", \"spa\"]", "items": { "type": "string", "enum": [ "eng", "spa", "fra", "deu", "por", "ita", "nld", "pol", "rus", "ukr", "tur", "ara", "hin", "urd", "chi_sim", "chi_tra", "jpn", "kor", "vie", "ind" ], "enumTitles": [ "English", "Spanish", "French", "German", "Portuguese", "Italian", "Dutch", "Polish", "Russian", "Ukrainian", "Turkish", "Arabic", "Hindi", "Urdu", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean", "Vietnamese", "Indonesian" ] }, "default": [ "eng" ] }, "pageRange": { "title": "Page range", "type": "string", "description": "Only process these pages of each PDF (1-based). Leave empty for all pages. Examples: \"1-5\", \"1,3,8-10\", \"2-\"." }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Add a Markdown version of each document (page sections, detected tables as Markdown tables, DOCX headings and lists). Example: true", "default": true }, "extractTables": { "title": "Detect tables (PDF)", "type": "boolean", "description": "Detect ruled (bordered) tables on digital PDF pages and return them as rows and Markdown. Adds processing time. Example: false", "default": false }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "If set (e.g. 1000), also return page-safe text chunks for vector databases: chunks never cross a page boundary and keep their page number for citations. 0 = off. Example: 1000", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters of overlap between consecutive chunks on the same page. Example: 100", "default": 0 }, "includePages": { "title": "Include per-page results", "type": "boolean", "description": "Return a pages array with each page's text, extraction method (text_layer or ocr), OCR confidence, word count and tables. Example: true", "default": true }, "includeFullText": { "title": "Include full text", "type": "boolean", "description": "Return the whole document text in one field. Turn off to save space when you only need pages or chunks. Example: true", "default": true }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many pages of each document. Example: 500", "default": 500 }, "maxOcrPagesPerDocument": { "title": "Max OCR pages per document", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cost guard: at most this many pages per document are OCRed (each OCR page is charged). Example: 100", "default": 100 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs, if all your PDFs share one. Leave empty otherwise." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip files larger than this (an error row is returned). Example: 50", "default": 50 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files to download at once. Parsing and OCR run one file at a time to keep memory low. Example: 4", "default": 4 } } }, "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 } } } } } } } } } }