{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown: DOCX, PPTX, XLSX, OCR & RAG Chunks", "description": "Convert PDF, DOCX, PPTX, XLSX, and HTML to clean Markdown that preserves tables and headings. Optional Tesseract OCR for scanned pages and heading-aware RAG chunks with source, page, and section metadata.", "version": "1.1", "x-build-id": "bRgAub28VAFAAqgch" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sunburst077~document-to-markdown-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sunburst077-document-to-markdown-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sunburst077~document-to-markdown-rag/runs": { "post": { "operationId": "runs-sync-sunburst077-document-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sunburst077~document-to-markdown-rag/run-sync": { "post": { "operationId": "run-sync-sunburst077-document-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "HTTP(S) links to PDF, DOCX, PPTX, XLSX, or HTML documents. HTML pages are cleaned with a readability pass before Markdown conversion. One bad URL does not fail the run.", "default": [ { "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "files": { "title": "Upload files", "type": "array", "description": "Upload PDF, Word, PowerPoint, Excel, or HTML files. The Console stores each file in a key-value store and passes the record URL to the Actor." }, "keyValueStoreId": { "title": "Key-value store", "type": "string", "description": "Read documents already stored in an Apify key-value store. Combine with keys below, or leave keys empty to convert every supported record." }, "keyValueStoreKeys": { "title": "Key-value store keys", "type": "array", "description": "Specific record keys to convert (for example report.pdf). Leave empty to convert every PDF/DOCX/PPTX/XLSX/HTML record in the store.", "items": { "type": "string" } }, "quality": { "title": "Conversion quality", "enum": [ "auto", "fast", "accurate" ], "type": "string", "description": "Auto (recommended) and Fast use MarkItDown for office/HTML and PyMuPDF for born-digital PDFs. Accurate uses Docling layout + table reconstruction when Docling is installed in the image; this Store build does not include Docling, so Accurate falls back to Fast and still returns Markdown.", "default": "auto" }, "saveMarkdownToKvs": { "title": "Save Markdown files to the key-value store", "type": "boolean", "description": "Write each successful conversion as a .md record (document--.md) in the default key-value store, in addition to the dataset row.", "default": true }, "enableOcr": { "title": "Enable OCR for scanned pages", "type": "boolean", "description": "Run Tesseract on PDF pages (or images) that have no usable text layer. Leave off for born-digital PDFs — it is the slowest and most expensive option. Uses the system Tesseract binary, not a cloud OCR API.", "default": false }, "ocrLanguage": { "title": "OCR language", "type": "string", "description": "Tesseract language. This build ships English only (eng). Other codes are not available.", "default": "eng" }, "enableChunking": { "title": "Create RAG chunks", "type": "boolean", "description": "Split the Markdown into overlapping chunks for embeddings / vector stores. Each chunk keeps source, page, and section (heading path) metadata.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Target characters per chunk. 800–1500 works well for most embedding models. Tables larger than this stay in one chunk so rows are not split.", "default": 1000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters copied from the end of the previous chunk onto the next one so sentences are not cut off at the boundary.", "default": 150 }, "headingAware": { "title": "Heading-aware chunks", "type": "boolean", "description": "Start a new chunk when the heading path changes (for example ## Revenue → ### Q3) and attach the heading path as section metadata.", "default": true }, "pushChunksAsItems": { "title": "Also push each chunk as its own dataset row", "type": "boolean", "description": "Useful for Zapier / Make / RAG loaders that expect one dataset item per chunk. The parent document row is still written.", "default": false }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip (do not fail the run) any file larger than this. Keeps memory and download time predictable.", "default": 50 }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only the first N PDF pages (or PPTX slides / XLSX sheets) are converted. Extra pages are billed after the first 10 on successful documents.", "default": 100 }, "timeoutSeconds": { "title": "Per-document timeout", "minimum": 15, "maximum": 1800, "type": "integer", "description": "Give up on a single document after this many seconds and move on.", "default": 300 }, "maxDocuments": { "title": "Max documents per run", "minimum": 1, "maximum": 500, "type": "integer", "description": "Hard cap on how many sources this run will process, in input order.", "default": 50 } } }, "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 } } } } } } } } } }