{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text for LLM/RAG (OCR, Tables, Chunks)", "description": "Convert PDFs (URLs or uploaded files) to clean Markdown and text with GitHub tables, per-page metadata and token-sized chunks for RAG and AI agents. Optional Tesseract OCR for scanned pages (English, Spanish and more) and a Mexican CFDI invoice mode. Pay per page. By IntegriApps.", "version": "0.1", "x-build-id": "cmIiLeGjjslVvD0Ue" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/integriapps~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-integriapps-pdf-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/integriapps~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-integriapps-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/integriapps~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-integriapps-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files (http/https). Only these files are downloaded; nothing is crawled. If all inputs are empty, a bundled sample PDF is converted for free as a demo.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "files": { "title": "Upload PDF files", "type": "array", "description": "Upload PDFs from your computer (they are stored in an Apify key-value store) or paste file URLs." }, "keyValueStoreId": { "title": "Key-value store with PDFs (bulk)", "type": "string", "description": "Optional. Pick one of your key-value stores: every PDF record in it is processed (e.g. files uploaded by another Actor or via the API). Read-only access is requested only for this store." }, "keyPrefix": { "title": "Key prefix filter", "type": "string", "description": "Optional. With a key-value store, only records whose key starts with this prefix are processed." }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "off", "always" ], "type": "string", "description": "'auto' runs Tesseract OCR only on pages without a text layer (scanned/image pages). 'always' OCRs every page (ignores the text layer). 'off' never OCRs. OCR pages are charged as 'ocr-page' instead of 'page-extracted'.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages for Tesseract OCR. Fewer languages = faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "spa", "por", "fra", "deu", "ita", "hin" ], "enumTitles": [ "English", "Spanish", "Portuguese", "French", "German", "Italian", "Hindi" ] }, "default": [ "eng", "spa" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Rendering resolution for OCR (100–400). 300 is a good balance; 200 is faster for large clean scans.", "default": 300 }, "cfdiMode": { "title": "CFDI invoice mode (Mexico)", "type": "boolean", "description": "Detect key fields of Mexican CFDI invoice PDFs (UUID/folio fiscal, RFC emisor and receptor, subtotal, total, dates, currency, series/folio, payment method). Heuristic: verify against the XML when it matters. No extra charge.", "default": false }, "extractTables": { "title": "Extract tables as Markdown", "type": "boolean", "description": "Detect ruled tables and output them as GitHub-flavored Markdown tables.", "default": true }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 0, "maximum": 32000, "type": "integer", "description": "Split each PDF into chunks of about this many tokens (1 token ≈ 4 characters) for RAG/embeddings, with page numbers. 0 = no chunks.", "default": 800 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "Tokens repeated between consecutive chunks to keep context.", "default": 100 }, "pageMarkers": { "title": "Page markers in Markdown", "type": "boolean", "description": "Insert comments between pages in the Markdown.", "default": true }, "includePlainText": { "title": "Include plain text", "type": "boolean", "description": "Also return a 'text' field without page markers.", "default": false }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Only the first N pages of each PDF are processed (and charged). 0 = all pages (up to 5,000).", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped and not charged (1–200).", "default": 50 }, "password": { "title": "PDF password", "type": "string", "description": "Optional password for encrypted PDFs (applies to all files). Stored encrypted." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "PDFs processed in parallel (1–4).", "default": 2 } } }, "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 } } } } } } } } } }