{
"openapi": "3.0.1",
"info": {
"title": "PDF Text Extractor & Document Parser: DOCX, XLSX, OCR, Markdown",
"description": "Parse Word, PowerPoint, Excel and PDF documents into clean Markdown and structured JSON: tables extracted cell-by-cell, document metadata, and RAG-ready chunks with heading paths. Built-in OCR for scans and images.",
"version": "0.3",
"x-build-id": "o6xF8tlJEVkHhTAnc"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/yabanana99~pdf-word-excel-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-yabanana99-pdf-word-excel-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/yabanana99~pdf-word-excel-to-markdown/runs": {
"post": {
"operationId": "runs-sync-yabanana99-pdf-word-excel-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/yabanana99~pdf-word-excel-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-yabanana99-pdf-word-excel-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"sources"
],
"properties": {
"sources": {
"title": "Documents",
"type": "array",
"description": "Documents to convert. Each item is an object with exactly one of: url (http/https link to the file), base64 (base64-encoded file content, data URIs accepted), or key (record key in a key-value store, with optional store_id). Add an optional filename (e.g. report.pdf) to help format detection when the URL has no extension. Supported formats: PDF, DOCX, PPTX, XLSX, PNG, JPG, TIFF, TXT, CSV, MD, HTML. Up to 500 sources per run.",
"default": [
{
"base64": "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",
"filename": "sample-report.pdf"
}
]
},
"output_format": {
"title": "Output format",
"enum": [
"text",
"markdown",
"json",
"all"
],
"type": "string",
"description": "Which textual representations to include in each dataset record. text = plain text only, markdown = Markdown only, json = structured data only (tables, metadata, chunks), all = everything. Tables, metadata and chunks are controlled by their own options and are always part of the record.",
"default": "all"
},
"ocr": {
"title": "OCR mode",
"enum": [
"auto",
"force",
"off"
],
"type": "string",
"description": "auto runs OCR on pages with almost no extractable text (fewer than 25 characters) and on scanned-looking pages (a raster image covering over 15% of the page with fewer than 200 characters of text), force runs OCR on every page, off disables OCR entirely. Only OCR pages that produce text are charged.",
"default": "auto"
},
"ocr_language": {
"title": "OCR languages",
"type": "string",
"description": "Tesseract language codes joined with +, e.g. eng+ita. The Docker image ships with English, Italian, French, German, Spanish, Portuguese, Dutch and Polish. Requested languages that are not installed are skipped with a warning.",
"default": "eng+ita"
},
"extract_tables": {
"title": "Extract tables",
"type": "boolean",
"description": "Detect tables and include them in the structured tables field as arrays of cell rows. For PDFs this runs a dedicated table-detection pass (pdfplumber).",
"default": true
},
"chunking": {
"title": "Chunking strategy",
"enum": [
"off",
"by_headings",
"fixed_tokens"
],
"type": "string",
"description": "How to split the document into RAG-ready chunks. by_headings splits at Markdown headings and keeps a heading_path per chunk (oversized sections are sub-split), fixed_tokens uses fixed-size token windows with overlap, off disables chunking.",
"default": "by_headings"
},
"chunk_size_tokens": {
"title": "Chunk size (tokens)",
"minimum": 32,
"maximum": 8192,
"type": "integer",
"description": "Maximum tokens per chunk (cl100k_base tokenizer). Range 32–8192.",
"default": 512
},
"chunk_overlap_tokens": {
"title": "Chunk overlap (tokens)",
"minimum": 0,
"maximum": 4096,
"type": "integer",
"description": "Token overlap between consecutive chunks when a section is sub-split. Capped at half the chunk size.",
"default": 64
},
"max_file_size_mb": {
"title": "Max file size (MB)",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "Files larger than this are skipped with a warning instead of failing the run.",
"default": 50
},
"concurrency": {
"title": "Concurrency",
"minimum": 1,
"maximum": 10,
"type": "integer",
"description": "How many documents to process in parallel. Parsing is CPU-bound (Python GIL), so values above 4 mainly pay off on OCR-heavy batches; higher values also use more memory. Range 1–10.",
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}