{
"openapi": "3.0.1",
"info": {
"title": "Office Docs to Markdown – DOCX, PPTX, XLSX, HTML, EPUB for RAG",
"description": "Convert Word, PowerPoint, Excel (XLSX/XLS), CSV, HTML, EPUB and Jupyter files from URLs into clean Markdown for LLMs and RAG: headings, lists, real tables, slide titles and speaker notes, sheets as JSON, optional chunks.",
"version": "1.0",
"x-build-id": "wbqhg4kK8x10ZcAhF"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/pinkish_armada~office-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-pinkish_armada-office-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/pinkish_armada~office-to-markdown/runs": {
"post": {
"operationId": "runs-sync-pinkish_armada-office-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/pinkish_armada~office-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-pinkish_armada-office-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"documentUrls"
],
"properties": {
"documentUrls": {
"title": "Document URLs",
"type": "array",
"description": "Direct links to .docx, .pptx, .xlsx, .xls, .csv, .tsv, .html, .epub, .ipynb, .json, .xml, .txt or .md files (public URLs, signed S3/GCS links, Dropbox ?dl=1 links, Apify key-value store record URLs, ...). The format is detected from the file content. Up to 5,000 per run.",
"items": {
"type": "string"
}
},
"chunkSize": {
"title": "RAG chunk size (characters)",
"minimum": 0,
"maximum": 100000,
"type": "integer",
"description": "If set (e.g. 2000), also return chunks: Markdown split on paragraph boundaries with the current heading, ready for embedding. 0 = off.",
"default": 0
},
"chunkOverlap": {
"title": "Chunk overlap (characters)",
"minimum": 0,
"type": "integer",
"description": "Characters of the previous chunk repeated at the start of the next one.",
"default": 200
},
"includePlainText": {
"title": "Include plain text",
"type": "boolean",
"description": "Also return a plain-text version without Markdown syntax.",
"default": false
},
"sheetsAsJson": {
"title": "Spreadsheet rows as JSON",
"type": "boolean",
"description": "For Excel/CSV files, also return every sheet as JSON objects keyed by the header row in sheets[].rows.",
"default": false
},
"maxRowsPerSheet": {
"title": "Max rows per sheet",
"minimum": 0,
"type": "integer",
"description": "Rows beyond this are cut (with a warning) to keep the output usable. 0 = no limit.",
"default": 5000
},
"includeHiddenSheets": {
"title": "Include hidden sheets",
"type": "boolean",
"description": "Also convert sheets that are hidden in Excel.",
"default": false
},
"includeSpeakerNotes": {
"title": "Include speaker notes",
"type": "boolean",
"description": "Add PowerPoint speaker notes under each slide.",
"default": true
},
"slideMarkers": {
"title": "Slide markers",
"type": "boolean",
"description": "Insert <!-- slide N --> comments so you can cite slide numbers.",
"default": true
},
"htmlMainContentOnly": {
"title": "HTML: main content only",
"type": "boolean",
"description": "For HTML files, keep only <main>/<article> (or drop nav, header, footer, aside and forms).",
"default": true
},
"includeImageAltText": {
"title": "Keep image alt text",
"type": "boolean",
"description": "Keep meaningful image descriptions as . Images without a description are always dropped.",
"default": true
},
"maxFileSizeMb": {
"title": "Max file size (MB)",
"minimum": 1,
"maximum": 200,
"type": "integer",
"description": "Larger files are skipped with an error (not charged).",
"default": 50
},
"maxConcurrency": {
"title": "Parallel documents",
"minimum": 1,
"maximum": 8,
"type": "integer",
"description": "How many documents are downloaded and converted at the same time.",
"default": 2
},
"requestTimeoutSecs": {
"title": "Download timeout (seconds)",
"minimum": 10,
"maximum": 300,
"type": "integer",
"description": "Timeout for downloading each file (retried with backoff).",
"default": 60
}
}
},
"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
}
}
}
}
}
}
}
}
}
}