{ "openapi": "3.0.1", "info": { "title": "Any Document to Markdown for RAG", "description": "Convert PDF (incl. scanned/OCR), Word, PowerPoint, Excel, CSV, HTML, EPUB and images into clean, chunked Markdown for RAG and LLMs.", "version": "1.0", "x-build-id": "TYOarQ4wk3QIOcfkn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dear_enstatite~doc-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dear_enstatite-doc-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dear_enstatite~doc-to-markdown/runs": { "post": { "operationId": "runs-sync-dear_enstatite-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dear_enstatite~doc-to-markdown/run-sync": { "post": { "operationId": "run-sync-dear_enstatite-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Public http(s) links to documents: PDF (text or scanned), DOCX, PPTX, XLSX, CSV/TSV, HTML web pages, EPUB, TXT/Markdown, or images (PNG, JPG, TIFF, WebP, GIF, BMP). The type is detected from the file itself. One dataset item per URL, duplicates removed, up to 1,000 per run.", "items": { "type": "string" } }, "uploadedFiles": { "title": "Uploaded files (optional)", "type": "array", "description": "Files you upload here are stored in a key-value store and converted like URLs. You can also enter api.apify.com key-value store record URLs, or \"storeIdOrName/recordKey\"." }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "off" ], "type": "string", "description": "auto: OCR only scanned PDF pages (no text layer) and images. always: OCR every PDF page. off: never OCR (scanned pages come back empty, images fail for free). Each OCR'd page is billed as an ocr-page event.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "pattern": "^(eng|deu|fra|spa|ita|por|nld)(\\+(eng|deu|fra|spa|ita|por|nld))*$", "type": "string", "description": "Tesseract language code. Available: eng, deu, fra, spa, ita, por, nld. Combine with + (e.g. eng+fra), which is slower.", "default": "eng" }, "maxOcrPages": { "title": "Max OCR pages per document", "minimum": 0, "maximum": 200, "type": "integer", "description": "Caps OCR cost per document. Scanned pages beyond the cap are left empty and listed in warnings; `truncated` is true.", "default": 20 }, "maxPages": { "title": "Max pages / slides / chapters per document", "minimum": 1, "maximum": 500, "type": "integer", "description": "Only the first N pages (PDF), slides (PPTX), frames (TIFF) or chapters (EPUB) are converted; `truncated` is true if more exist.", "default": 100 }, "maxFileSizeMb": { "title": "Max file size (MiB)", "minimum": 1, "maximum": 50, "type": "integer", "description": "Larger downloads are stopped and rejected for free (error FILE_TOO_LARGE).", "default": 20 }, "maxCharacters": { "title": "Max Markdown characters per document", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "The combined Markdown is capped at this length; `truncated` is true if anything was cut.", "default": 200000 }, "maxRowsPerSheet": { "title": "Max rows per sheet (XLSX/CSV)", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Spreadsheet rows beyond this (per sheet) are dropped; `truncated` is true.", "default": 1000 }, "documentTimeoutSecs": { "title": "Timeout per document (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "A document that takes longer is stopped and returned as a free EXTRACTION_TIMEOUT failure.", "default": 120 }, "maxChunkCharacters": { "title": "Max characters per chunk", "minimum": 300, "maximum": 50000, "type": "integer", "description": "Pages/slides/sections longer than this are split into several chunks on paragraph boundaries. Good RAG values: 1,000–6,000.", "default": 4000 }, "includeMarkdown": { "title": "Include combined `markdown` field", "type": "boolean", "description": "Untick to return only `chunks` (smaller items when you index chunk by chunk).", "default": true }, "pageMarkers": { "title": "Page markers in Markdown", "type": "boolean", "description": "Insert comments between PDF pages, slides and image pages in the combined Markdown.", "default": true }, "includeSpeakerNotes": { "title": "Include PPTX speaker notes", "type": "boolean", "description": "Append each slide's speaker notes as a quote block.", "default": true }, "includeLinks": { "title": "Keep links in web pages", "type": "boolean", "description": "Keep hyperlinks as Markdown links when converting HTML pages (off gives cleaner text for embeddings).", "default": false } } }, "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 } } } } } } } } } }