{ "openapi": "3.0.1", "info": { "title": "Document to Markdown & JSON: DOCX, XLSX, PPTX, HTML, EPUB, CSV", "description": "Convert Word, PowerPoint, HTML and EPUB files to clean Markdown, and Excel or CSV to typed JSON rows, with metadata, image extraction and RAG chunks. Bulk links or upload. $2 per 1,000 documents, no page fees; failed files are free.", "version": "0.1", "x-build-id": "JJGnS7HuJEggQfVgq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plotpointtech~document-to-markdown-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plotpointtech-document-to-markdown-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plotpointtech~document-to-markdown-json/runs": { "post": { "operationId": "runs-sync-plotpointtech-document-to-markdown-json", "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/plotpointtech~document-to-markdown-json/run-sync": { "post": { "operationId": "run-sync-plotpointtech-document-to-markdown-json", "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": { "startUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to DOCX, XLSX, PPTX, HTML, EPUB, CSV/TSV, TXT or Markdown files. Paste many at once or upload a text file with one URL per line. The format is detected from the file itself. Links that fail to download or are not a supported format are skipped and not charged. For PDFs use our PDF to Text & Tables Extractor.", "default": [ { "url": "https://api.apify.com/v2/key-value-stores/6tG74dmDqhbuixGpx/records/quarterly-report.docx" }, { "url": "https://api.apify.com/v2/key-value-stores/6tG74dmDqhbuixGpx/records/regional-sales.xlsx" }, { "url": "https://api.apify.com/v2/key-value-stores/6tG74dmDqhbuixGpx/records/product-roadmap.pptx" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "uploadedFile": { "title": "Or upload a file", "type": "string", "description": "Upload a document from your computer. It is stored in your Apify key-value store and converted together with any URLs above." }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Clean Markdown of the whole document: headings, lists, tables, links and image references. Spreadsheets become one Markdown table per sheet.", "default": true }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Plain text version without Markdown syntax.", "default": false }, "extractImages": { "title": "Extract embedded images", "type": "boolean", "description": "Save images embedded in DOCX, PPTX and EPUB files to the run's key-value store. Markdown image references then point to the saved files. Images on HTML pages are always listed by their original URL and are not downloaded.", "default": false }, "maxImagesPerDocument": { "title": "Maximum images saved per document", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Only used when image extraction is on.", "default": 100 }, "chunking": { "title": "Split into chunks for RAG", "type": "boolean", "description": "Add a list of chunks split at headings, paragraphs and table rows (table headers are repeated in every chunk). Each chunk carries its heading path, so you can load it straight into a vector database.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 100000, "type": "integer", "description": "Maximum characters per chunk. About 4 characters make one token in English, so 2000 characters is roughly 500 tokens.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Characters of text repeated from the end of the previous chunk (whole lines; headings and table rows are not repeated). Capped at half the chunk size.", "default": 200 }, "headerDetection": { "title": "Header row", "enum": [ "auto", "firstRow", "none" ], "type": "string", "description": "Auto finds the header row even below title rows. First row always uses the first non-empty row. None keys rows by column letter (A, B, C...).", "default": "auto" }, "typedValues": { "title": "Typed values", "type": "boolean", "description": "Return numbers, booleans and dates (ISO 8601) as real JSON types. Codes with leading zeros (postcodes, IDs) stay text. Off returns every cell as text.", "default": true }, "fillMergedCells": { "title": "Fill merged cells", "type": "boolean", "description": "Copy the value of a vertically merged cell (for example a region label spanning several rows) into every row it covers, so each JSON row is complete.", "default": true }, "includeRows": { "title": "Include JSON rows", "type": "boolean", "description": "One JSON object per row, keyed by the header.", "default": true }, "includeRowNumbers": { "title": "Include source row numbers", "type": "boolean", "description": "Add a _row field with the original spreadsheet row number to each JSON row.", "default": true }, "includeSheetMarkdown": { "title": "Markdown table per sheet", "type": "boolean", "description": "Also put each sheet's Markdown table inside its sheet object (it is always part of the document Markdown).", "default": false }, "maxRowsPerSheet": { "title": "Maximum rows per sheet", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop reading a sheet or CSV after this many data rows; the sheet is then marked truncated. 0 = no limit.", "default": 10000 }, "sheetNames": { "title": "Only these sheets", "type": "array", "description": "Optional list of sheet names to convert. Empty = all visible sheets.", "items": { "type": "string" } }, "includeHiddenSheets": { "title": "Include hidden sheets", "type": "boolean", "description": "Also convert sheets that are hidden in the workbook.", "default": false }, "csvDelimiter": { "title": "CSV delimiter", "enum": [ "auto", "comma", "semicolon", "tab", "pipe" ], "type": "string", "description": "Auto-detect works for comma, semicolon, tab and pipe.", "default": "auto" }, "includeSpeakerNotes": { "title": "Include speaker notes (PPTX)", "type": "boolean", "description": "Add each slide's speaker notes below the slide in the Markdown and in the slides list.", "default": true }, "htmlMainContentOnly": { "title": "Main content only (HTML)", "type": "boolean", "description": "For web pages, keep the main content and drop navigation, headers, footers, sidebars and forms. Off converts the whole page body.", "default": true }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 50 }, "maxConcurrency": { "title": "Downloads at once", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents to download in parallel.", "default": 4 } } }, "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 } } } } } } } } } }