{ "openapi": "3.0.1", "info": { "title": "PDF & Document to Markdown — RAG Chunks, Tables, OCR", "description": "Convert PDF, DOCX and PPTX to clean Markdown, JSON and RAG-ready chunks with tables and automatic OCR. $1 per 1,000 pages, no start or per-file fee.", "version": "0.2", "x-build-id": "EMycuZBv1BtC6l6sT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/frayess_mosbehi~doc-to-markdown-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-frayess_mosbehi-doc-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/frayess_mosbehi~doc-to-markdown-rag/runs": { "post": { "operationId": "runs-sync-frayess_mosbehi-doc-to-markdown-rag", "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/frayess_mosbehi~doc-to-markdown-rag/run-sync": { "post": { "operationId": "run-sync-frayess_mosbehi-doc-to-markdown-rag", "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 or signed URLs of your PDF, DOCX, PPTX, XLSX or HTML files.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyValueStoreRecords": { "title": "Files on Apify (key-value store records)", "type": "array", "description": "Files already stored on Apify, as objects {\"storeId\": \"...\", \"key\": \"...\"}. Leave storeId empty for this run's default store.", "default": [] }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which full-document outputs to include in each document item.", "items": { "type": "string", "enum": [ "markdown", "json", "text" ], "enumTitles": [ "Markdown", "Docling JSON", "Plain text" ] }, "default": [ "markdown" ] }, "chunking": { "title": "Produce RAG chunks", "type": "boolean", "description": "Also output heading-aware chunks (one dataset item per chunk) ready for embedding.", "default": true }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 100, "maximum": 8000, "type": "integer", "description": "Approximate maximum tokens per chunk (estimated at ~4 characters per token), including overlap.", "default": 1000 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Approximate tokens repeated from the end of the previous chunk.", "default": 100 }, "ocr": { "title": "OCR", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto = OCR only pages without a text layer; always = OCR every page; never = no OCR.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Tesseract language codes used for OCR, e.g. eng, fra, deu, spa, ita, por, nld.", "default": [ "eng", "fra" ], "items": { "type": "string" } }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect table structure and output tables as Markdown and as rows in tables[].", "default": true }, "pageRange": { "title": "Page range (PDF)", "type": "string", "description": "Only convert these PDF pages, e.g. \"1-20\", \"5\" or \"10-\". Empty = all pages.", "default": "" }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "type": "integer", "description": "Safety cap: pages beyond this are skipped (with a warning) and not charged.", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Files larger than this are rejected without charge.", "default": 100 }, "layout": { "title": "Layout engine", "enum": [ "fast", "accurate" ], "type": "string", "description": "fast = no AI layout model: PDF pages with a text layer are read directly (font-based headings, ruled tables, columns) and scanned pages are OCR'd with Tesseract (no table detection on scans). accurate = AI layout model on every page: better on complex layouts and tables in scans, ~100x slower, and every page is billed at the OCR page price.", "default": "fast" } } }, "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 } } } } } } } } } }