{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & JSON for RAG (OCR, DOCX, PPTX, XLSX)", "description": "Convert PDF, DOCX, PPTX, XLSX and HTML into clean Markdown and JSON for AI and RAG pipelines. Fast mode is cheap and near-instant; accurate mode adds full layout and table analysis. OCR for scanned PDFs, tables as Markdown/HTML/JSON, page or token chunking with token counts.", "version": "0.2", "x-build-id": "vZWZjOrAhGnHcyjRU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maxatron~docmd/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maxatron-docmd", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maxatron~docmd/runs": { "post": { "operationId": "runs-sync-maxatron-docmd", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maxatron~docmd/run-sync": { "post": { "operationId": "run-sync-maxatron-docmd", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sources" ], "properties": { "sources": { "title": "Document URLs", "type": "array", "description": "URLs of documents to convert. Supported: PDF (text or scanned), DOCX, PPTX, XLSX, HTML.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "mode": { "title": "Conversion mode", "enum": [ "fast", "accurate" ], "type": "string", "description": "fast (default): pypdfium2 text extraction + pdfplumber tables + RapidOCR for scanned pages only. About as fast as reading the file (roughly 0.3-1s/page on a normal text PDF), priced near the market rate, and good enough for most RAG/LLM use. Docling's ML models never load. accurate: full docling layout analysis + TableFormer table-structure recognition. Much slower (roughly 15-70s/page on a 4 GB/1 vCPU worker) and priced higher (accurate-page + table charges), but reconstructs reading order, headings and complex table structure more faithfully - worth it for dense forms, multi-column layouts, or tables you need pixel-accurate. DOCX/PPTX/XLSX/HTML always use docling's fast native (non-ML) backends in both modes. Memory: fast mode runs fine at the default 2048 MB. Accurate mode needs 4096 MB; set it in the run options, or the run stops before charging anything.", "default": "fast" }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "json", "both" ], "type": "string", "description": "Which fields to fill on each dataset item.", "default": "both" }, "chunking": { "title": "Chunking strategy", "enum": [ "none", "page", "tokens" ], "type": "string", "description": "How to split each document's text into the `chunks` output field.", "default": "none" }, "chunkTokens": { "title": "Tokens per chunk", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target chunk size in tokens, used only when chunking = \"tokens\".", "default": 800 }, "ocr": { "title": "OCR mode", "enum": [ "auto", "off", "force" ], "type": "string", "description": "auto: OCR only pages with little or no extractable text (scanned pages). off: never OCR. force: OCR every PDF page.", "default": "auto" }, "tableFormat": { "title": "Table format", "enum": [ "markdown", "html", "json" ], "type": "string", "description": "Encoding used for each entry in the structured `tables` output field. The Markdown body always renders tables as Markdown for readability.", "default": "markdown" }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Spend guard: stop converting a single document after this many pages. Extra pages are skipped, not charged.", "default": 50 } } }, "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 } } } } } } } } } }