{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown, Tables & OCR Extractor", "description": "Convert PDFs and scanned documents to Markdown, header-mapped tables (JSON + CSV) and schema JSON, with OCR and page-level provenance.", "version": "1.0", "x-build-id": "mk0nYBYEdXFsru53u" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cylindrical_lighthouse~document-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cylindrical_lighthouse-document-intelligence", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cylindrical_lighthouse~document-intelligence/runs": { "post": { "operationId": "runs-sync-cylindrical_lighthouse-document-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cylindrical_lighthouse~document-intelligence/run-sync": { "post": { "operationId": "run-sync-cylindrical_lighthouse-document-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Public PDF URLs to convert (text or scanned). Each URL becomes one dataset item with Markdown, pages and tables. Example: https://www.federalreserve.gov/releases/g19/current/g19.pdf. Duplicates are processed once; no login or paywalled URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "When to run OCR. \"auto\" (default): only pages without a usable text layer (scans). \"always\": every page, for scans with a poor embedded text layer; charged as OCR pages. \"never\": text layer only, cheapest. Example: auto.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "pattern": "^[a-z_]{3,}(\\+[a-z_]{3,})*$", "type": "string", "description": "Tesseract language code(s) of the scanned text, combined with +. Examples: eng, deu, fra, spa, eng+deu, chi_sim. English is built in; other languages are downloaded once per run (1-10 MB).", "default": "eng" }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum pages to process per document, counted from page 1. Caps cost for long PDFs; later pages are skipped and the item is marked truncated. Example: 50.", "default": 200 }, "maxDocuments": { "title": "Max documents", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum documents to process in this run, including failed ones. Example: 100.", "default": 100 }, "datasetId": { "title": "Dataset ID (chain from another Actor)", "type": "string", "description": "Read document URLs from an Apify dataset, e.g. the output of Website Content Crawler or any crawler. Example: aBcD1234EfGh5678 or username~my-dataset." }, "datasetUrlField": { "title": "Dataset URL field", "type": "string", "description": "Field of each dataset item that holds the document URL (dot paths allowed; arrays of URLs are expanded). Example: url, or links.pdf.", "default": "url" }, "keyValueStoreId": { "title": "Key-value store ID", "type": "string", "description": "Key-value store that holds PDF files, e.g. files saved by Website Content Crawler with saveFiles. Example: aBcD1234EfGh5678 or username~my-store." }, "keyValueStoreKeys": { "title": "Key-value store keys", "type": "array", "description": "Record keys of the PDF files in the key-value store above. Example: invoice-001.pdf.", "items": { "type": "string" } }, "extractionSchema": { "title": "Extraction JSON Schema (optional)", "type": "object", "description": "Optional JSON Schema describing the data to extract from each document with your own LLM API key. Example: { \"type\": \"object\", \"properties\": { \"invoiceNumber\": { \"type\": \"string\" }, \"total\": { \"type\": \"number\" } } }. The result is in \"extracted\" with page citations per field. Leave empty to skip (no LLM calls, no extraction charge)." }, "extractionInstructions": { "title": "Extraction instructions", "type": "string", "description": "Optional extra guidance for the model. Example: Amounts are in USD; use ISO dates (YYYY-MM-DD)." }, "llmProvider": { "title": "LLM provider", "enum": [ "anthropic", "openai" ], "type": "string", "description": "Which provider your API key belongs to. Example: anthropic.", "default": "anthropic" }, "llmModel": { "title": "LLM model ID", "type": "string", "description": "The model ID exactly as listed in your provider's model documentation (docs.anthropic.com or platform.openai.com). Required when an extraction schema is set." }, "llmApiKey": { "title": "LLM API key", "type": "string", "description": "Your Anthropic or OpenAI API key. Stored encrypted by Apify, never logged and never written to the output. Required when an extraction schema is set. Example format: sk-..." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Skip files larger than this, with a clear error record. Very large files need more memory. Example: 100.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Not needed for most public documents. Enable only if a server blocks direct downloads. Example: Apify datacenter proxy.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }