{ "openapi": "3.0.1", "info": { "title": "Document to Markdown Converter for RAG", "description": "Convert PDF, DOCX, XLSX, PPTX, HTML and EPUB links to clean Markdown or RAG-ready chunks. No OCR, no browser. $4 per 1,000 documents plus page fees.", "version": "0.0", "x-build-id": "aTjl7WCsK5mYvgzqL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ottomath~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ottomath-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ottomath~document-to-markdown/runs": { "post": { "operationId": "runs-sync-ottomath-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/ottomath~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-ottomath-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", "required": [ "urls" ], "properties": { "urls": { "title": "Document URLs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "One http(s) URL per line: PDF, DOCX, XLSX, XLS, CSV, PPTX, HTML, EPUB, Markdown or plain text. The format is detected from the content, not only from the file name. Up to 1,000 URLs per run. Duplicates are converted once.", "items": { "type": "string" } }, "outputMode": { "title": "Output mode", "enum": [ "document", "chunks" ], "type": "string", "description": "document: one dataset item per document with the full Markdown. chunks: one item per chunk, split on headings and paragraphs first, ready for embedding.", "default": "document" }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Maximum length of a chunk, in characters. Only used when the output mode is chunks.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated at the start of the next chunk when a section has to be split in the middle. Chunks that start at a new heading start clean. Must be at most half of the chunk size.", "default": 200 }, "maxPages": { "title": "Maximum pages, slides or sheets", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Convert at most this many PDF pages, PPTX slides or spreadsheet sheets per document. Larger documents are cut off with a warning, and only the converted units are charged.", "default": 500 }, "includeSlideNotes": { "title": "Include speaker notes", "type": "boolean", "description": "Add the speaker notes of each PPTX slide under the slide content.", "default": true }, "maxRowsPerSheet": { "title": "Maximum rows per sheet", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Row cap for each spreadsheet sheet and CSV file. Longer sheets are cut off with a warning.", "default": 1000 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Read the robots.txt of each host and download only documents it allows for this Actor's own User-Agent (or `*`). Blocked documents are reported with an error and are free. Turn off only for hosts you own or may fetch from.", "default": true }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Documents larger than this are not downloaded or converted (error, free).", "default": 50 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Give up on a download after this many seconds (headers and body).", "default": 60 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many documents are downloaded in parallel. Conversion itself runs in at most 2 worker threads, and at most 2 requests per host run at the same time.", "default": 5 } } }, "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 } } } } } } } } } }