{ "openapi": "3.0.1", "info": { "title": "PDF & Document to Markdown for LLMs (OCR, Tables, RAG Chunks)", "description": "Convert PDFs, Word, PowerPoint, Excel, HTML and scanned images into clean, LLM-ready Markdown. Keeps headings, tables and two-column reading order, OCRs scanned pages, and outputs heading-aware chunks for RAG. Pay only for documents that convert.", "version": "0.0", "x-build-id": "NDba67PMbl2idHXdR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lan460308587~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lan460308587-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lan460308587~document-to-markdown/runs": { "post": { "operationId": "runs-sync-lan460308587-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lan460308587~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-lan460308587-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Links to the documents to convert: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), EPUB, HTML, CSV, JSON, text or images (PNG, JPG, TIFF). Google Drive, Google Docs, Dropbox and GitHub share links are converted to direct downloads automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "files": { "title": "Upload files", "type": "array", "description": "Upload documents from your computer instead of (or in addition to) URLs." }, "ocrMode": { "title": "OCR for scanned pages", "enum": [ "auto", "force", "off" ], "type": "string", "description": "Auto: OCR only pages without a usable text layer (scans, photos, garbled fonts). Force: OCR every page, useful when a PDF's embedded text is wrong. Off: never OCR. OCR pages are billed separately.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with +, for example eng, fra, deu, spa, ita, por, nld, pol, eng+fra. Installed: eng, fra, deu, spa, ita, por, nld, pol, chi_sim, jpn.", "default": "eng" }, "pageRange": { "title": "Page range (PDF)", "type": "string", "description": "Only convert these pages, for example \"1-5, 8, 10-\". Leave empty for all pages." }, "maxPages": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Stop after this many pages of each PDF. 0 means no limit.", "default": 0 }, "extractTables": { "title": "Extract tables as Markdown tables", "type": "boolean", "description": "Detect ruled tables in PDFs and output them as Markdown tables.", "default": true }, "removeHeadersFooters": { "title": "Remove running headers, footers and page numbers", "type": "boolean", "description": "Drops text repeated in page margins, such as journal names and page numbers, so it doesn't pollute your text.", "default": true }, "includePageBreaks": { "title": "Mark page breaks", "type": "boolean", "description": "Insert comments so you can cite page numbers.", "default": false }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs (applied to every PDF in this run)." }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Split each document into heading-aware chunks of about this many tokens for embeddings and RAG. 0 turns chunking off. Tokens are estimated at 4 characters each.", "default": 0 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "How much text consecutive chunks share, so answers that span a boundary aren't lost.", "default": 50 }, "chunkOutput": { "title": "Chunk output", "enum": [ "nested", "separateItems" ], "type": "string", "description": "Nested: chunks inside each document's result. Separate items: one dataset row per chunk, ready for Pinecone, Qdrant or other vector database integrations.", "default": "nested" }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save each result as a Markdown file in the run's key-value store and return its download link. Very large results are always saved this way.", "default": false }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip files larger than this.", "default": 100 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents to download and convert at the same time.", "default": 3 }, "httpHeaders": { "title": "HTTP headers", "type": "object", "description": "Extra headers for downloading private documents, for example {\"Authorization\": \"Bearer ...\"}." } } }, "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 } } } } } } } } } }