{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown: PDF & DOCX Document to Markdown for LLM & RAG", "description": "Convert PDF, DOCX, HTML and text documents to clean Markdown for LLMs and RAG: headings, lists, de-hyphenated text, removed headers/footers, per-page output and token-sized chunks. Bulk PDF to Markdown and PDF to text from URLs.", "version": "0.1", "x-build-id": "9veSqbDVvOzsIQSUK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-co~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-co-pdf-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-co~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-api-co-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-co~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-api-co-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 links to PDF, DOCX, HTML or TXT/MD files. Google Drive, Google Docs, Dropbox and GitHub share links are converted to direct downloads automatically.", "items": { "type": "string" } }, "urlsText": { "title": "Bulk URLs (paste)", "type": "string", "description": "Paste many URLs, one per line." }, "includeMarkdown": { "title": "Markdown output", "type": "boolean", "description": "Full document as Markdown (headings, lists, paragraphs).", "default": true }, "includeText": { "title": "Plain text output", "type": "boolean", "description": "Also return plain text without Markdown syntax.", "default": false }, "includePages": { "title": "Per-page Markdown", "type": "boolean", "description": "Add a 'pages' array with Markdown for each PDF page (for citations and page-level search).", "default": false }, "chunking": { "title": "RAG chunks", "type": "boolean", "description": "Add a 'chunks' array split on headings and paragraphs with heading path, page numbers and token estimates, ready for embeddings.", "default": false }, "chunkTokens": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target chunk size in tokens (about 4 characters per token).", "default": 800 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Approximate overlap carried between consecutive chunks.", "default": 100 }, "pageRange": { "title": "Page range", "type": "string", "description": "PDF pages to convert, e.g. '1-5,8,10-'. Leave empty for all." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "type": "integer", "description": "Safety cap on pages converted (and charged) per PDF.", "default": 500 }, "removeHeadersFooters": { "title": "Remove repeated headers/footers and page numbers", "type": "boolean", "description": "Drop running headers, footers and page numbers that repeat across pages.", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "For password-protected PDFs (the same password is tried for every file)." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Skip files larger than this.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Documents converted in parallel.", "default": 3 }, "maxItems": { "title": "Max documents", "minimum": 1, "type": "integer", "description": "Stop after this many documents (defaults to all inputs)." } } }, "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 } } } } } } } } } }