{ "openapi": "3.0.1", "info": { "title": "Doc to Markdown for AI Agents — PDF, Word, PowerPoint, Excel", "description": "Convert PDF, DOCX, PPTX, XLSX and HTML links into clean, LLM-ready Markdown with tables preserved, metadata and RAG-ready chunks. Predictable JSON, scanned-PDF detection, and failed files are never charged. Built for AI agents, MCP and RAG.", "version": "1.0", "x-build-id": "xLnFc9KJCSMNiz4I2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sourcewire~doc-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sourcewire-doc-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sourcewire~doc-to-markdown/runs": { "post": { "operationId": "runs-sync-sourcewire-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sourcewire~doc-to-markdown/run-sync": { "post": { "operationId": "run-sync-sourcewire-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Public links to PDF, DOCX, PPTX, XLSX/XLS, HTML, CSV, TXT or MD files. Google Docs/Sheets/Slides share links, Google Drive file links, Dropbox and GitHub 'blob' links are converted to direct downloads automatically (the file must be shared publicly).", "items": { "type": "string" } }, "chunkStrategy": { "title": "RAG chunking", "enum": [ "size", "section", "page", "none" ], "type": "string", "description": "How to split each document into chunks for embeddings. 'size' = heading-aware chunks of about chunkSize tokens (recommended). 'section' = one chunk per heading section. 'page' = one chunk per page / slide / sheet. 'none' = no chunks.", "default": "size" }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target maximum chunk size in estimated tokens (≈4 characters each). Used by 'size' and 'section' strategies. Tables are never split mid-row; long tables are split by rows with the header repeated.", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Text carried over between consecutive 'size' chunks for context. Never applied inside tables.", "default": 50 }, "includeMarkdown": { "title": "Include full Markdown", "type": "boolean", "description": "Return the whole document as one 'markdown' field.", "default": true }, "includePages": { "title": "Include per-page Markdown", "type": "boolean", "description": "Also return a 'pages' array with Markdown per PDF page, slide or sheet (useful for page-level citations).", "default": false }, "detectTables": { "title": "Detect tables in PDFs", "type": "boolean", "description": "Rebuild ruled and booktabs-style PDF tables as Markdown tables. Turn off for slightly faster text-only output.", "default": true }, "saveMarkdownFile": { "title": "Also save .md files", "type": "boolean", "description": "Save each document's Markdown as a file in the key-value store and return its link in 'markdownUrl'. Very large documents are always saved this way automatically.", "default": false }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Convert at most this many pages of each PDF (the rest is skipped with a warning). Billing counts converted pages only.", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this are rejected before conversion (not charged).", "default": 50 }, "maxDocuments": { "title": "Max documents per run", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety cap on how many URLs are processed in one run.", "default": 100 }, "timeoutSecs": { "title": "Per-document timeout (seconds)", "minimum": 10, "maximum": 1800, "type": "integer", "description": "A document that takes longer than this to convert is stopped and reported as TIMEOUT (not charged).", "default": 180 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 4, "type": "integer", "description": "How many documents to convert at the same time. 2 is ideal for 1 GB memory; raise it together with memory.", "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 } } } } } } } } } }