{ "openapi": "3.0.1", "info": { "title": "Document to Markdown: PDF, DOCX & HTML for RAG", "description": "Convert PDF, Word (DOCX), HTML pages, CSV and text into clean Markdown + JSON for LLMs and RAG: headings, tables, links, metadata and ready-to-embed chunks with heading paths and page numbers. URLs, Drive/Dropbox links or base64. No OCR, no AI cost.", "version": "0.0", "x-build-id": "Zrb8SwU8C86BmJSK0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dodiabak~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dodiabak-document-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dodiabak~document-to-markdown/runs": { "post": { "operationId": "runs-sync-dodiabak-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dodiabak~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-dodiabak-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 a URL string or an object: {\"url\": \"https://…/file.pdf\"}, {\"base64\": \"…\", \"fileName\": \"report.docx\"}, {\"html\": \"

…

\"}, {\"text\": \"…\"} or {\"markdown\": \"…\"}. Optional per item: \"type\" (pdf, docx, html, csv, markdown, text), \"password\" (encrypted PDF) and \"id\" (your own reference, copied to the output). Google Drive, Google Docs, Dropbox and GitHub share links are converted to direct downloads automatically. Max 1,000 per run." }, "outputMode": { "title": "Output mode", "enum": [ "document", "chunks" ], "type": "string", "description": "\"document\": one dataset item per document (Markdown, tables, links, metadata, optional chunks). \"chunks\": one dataset item per RAG chunk, ready to embed and load into a vector database.", "default": "document" }, "includeChunks": { "title": "Add chunks to document items", "type": "boolean", "description": "In \"document\" mode, also add a \"chunks\" array to each item. Always on in \"chunks\" mode.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target maximum chunk length in characters (about 4 characters per token). Chunks break at headings and paragraphs and never split a table row or code block unless a single block is too long.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters of the previous chunk repeated at the start of the next one (cut at a word boundary). The overlap resets at H1/H2 headings.", "default": 200 }, "mainContentOnly": { "title": "Web pages: main content only", "type": "boolean", "description": "For HTML pages, keep only the main article (Mozilla Readability), removing navigation, footers, cookie banners and ads. Turn this off to convert the whole .", "default": true }, "linkStyle": { "title": "Links in Markdown", "enum": [ "inline", "text" ], "type": "string", "description": "\"inline\" keeps [text](url) links. \"text\" keeps only the link text: shorter, cleaner input for LLMs and embeddings (URLs stay available in the \"links\" array).", "default": "inline" }, "detectTables": { "title": "PDF: detect tables", "type": "boolean", "description": "Rebuild tables from column-aligned text in PDFs and output them as Markdown tables and JSON rows. This uses layout heuristics: complex tables (merged cells, ruled grids with wrapped text) may come out partly as text.", "default": true }, "pageMarkers": { "title": "PDF: page markers", "type": "boolean", "description": "Insert comments between PDF pages so chunks keep their page number (useful for citations).", "default": true }, "maxPages": { "title": "PDF: max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only the first N pages of each PDF are converted and billed.", "default": 300 }, "includeTables": { "title": "Include tables as JSON", "type": "boolean", "description": "Add a \"tables\" array (rows of cell strings) to document items.", "default": true }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Add a \"links\" array (text + absolute URL) to document items.", "default": true }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Also add a \"text\" field with plain text (no Markdown syntax).", "default": false }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save each document as a .md file in the run's key-value store and return its download URL as \"markdownUrl\".", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger downloads are rejected with FILE_TOO_LARGE.", "default": 25 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "How long to wait for each URL download before failing it with FETCH_FAILED.", "default": 60 }, "concurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents are processed at the same time. Use 1–2 for very large PDFs with low memory.", "default": 3 } } }, "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 } } } } } } } } } }