{ "openapi": "3.0.1", "info": { "title": "PDF & Document to Markdown for RAG - Word, PPT, Excel", "description": "Convert PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX/XLS), EPUB, HTML, CSV and more from URLs into clean LLM-ready Markdown with page counts, metadata and heading-aware RAG chunks. $4 per 1,000 documents, any format. Failed files are free.", "version": "1.1", "x-build-id": "FcNQWItcvHXhOJP7Q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kantolabs~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kantolabs-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/kantolabs~document-to-markdown/runs": { "post": { "operationId": "runs-sync-kantolabs-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/kantolabs~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-kantolabs-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": [ "documentUrls" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to documents, one per line. Supported: PDF, DOCX, PPTX, XLSX, XLS, CSV, EPUB, HTML, IPYNB, MSG, TXT, MD, JSON, XML, RSS/Atom and ZIP archives of these. The type is detected from the file itself, so links without an extension work too. Via the API you can also pass objects: [{\"url\": \"https://...\"}].", "default": [ "https://arxiv.org/pdf/1706.03762" ], "items": { "type": "string" } }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Split each document into heading-aware chunks of about this many characters for embeddings / vector databases. 0 turns chunking off.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many characters from the end of the previous chunk are repeated at the start of the next one.", "default": 150 }, "includeMarkdown": { "title": "Include full Markdown in results", "type": "boolean", "description": "Put the whole Markdown text in each result. Turn off if you only need the chunks or the saved .md files.", "default": true }, "saveMarkdownFiles": { "title": "Save .md files to the key-value store", "type": "boolean", "description": "Also store each converted document as a downloadable .md file. The key is returned in `markdownFileKey`.", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (and not charged).", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents are downloaded and converted in parallel.", "default": 3 }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 900, "type": "integer", "description": "Give up downloading a file after this many seconds.", "default": 120 }, "conversionTimeoutSecs": { "title": "Conversion timeout (seconds)", "minimum": 10, "maximum": 1800, "type": "integer", "description": "Give up converting a single file after this many seconds.", "default": 300 } } }, "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 } } } } } } } } } }