{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown, Tables & RAG Chunks (with OCR)", "description": "Convert PDF, DOCX and image files to clean Markdown, tables as CSV and RAG-ready chunks with page numbers. Scanned pages are read with OCR. No API keys, pay per page, built for AI agents and LLM pipelines.", "version": "0.1", "x-build-id": "YJvrfceHCalMfdtxF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/errandkit~pdf-to-markdown-tables/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-errandkit-pdf-to-markdown-tables", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/errandkit~pdf-to-markdown-tables/runs": { "post": { "operationId": "runs-sync-errandkit-pdf-to-markdown-tables", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/errandkit~pdf-to-markdown-tables/run-sync": { "post": { "operationId": "run-sync-errandkit-pdf-to-markdown-tables", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Public links to PDF, DOCX or image files (PNG, JPEG, TIFF, GIF, BMP, WEBP). Use the direct file link, not a viewer page.", "items": { "type": "string" } }, "uploadedFile": { "title": "Or upload a file", "type": "string", "description": "Upload one PDF, DOCX or image from your computer." }, "documents": { "title": "Documents (advanced, JSON)", "type": "array", "description": "For API and agent use: [{\"name\": \"a.pdf\", \"url\": \"https://...\"}] or [{\"name\": \"a.pdf\", \"content_base64\": \"...\"}]." }, "outputMode": { "title": "Output mode", "enum": [ "documents", "chunks" ], "type": "string", "description": "documents: one dataset item per document (Markdown, tables, chunks, metadata). chunks: one item per chunk, ready for a vector database.", "default": "documents" }, "pages": { "title": "Pages (PDF)", "type": "string", "description": "Page selection, 1-based, e.g. 1-3,7. Leave empty for all pages." }, "ocr": { "title": "OCR", "enum": [ "auto", "force", "off" ], "type": "string", "description": "auto: OCR only pages without a text layer (scans). force: OCR every page. off: never (scanned pages come back empty).", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "enum": [ "eng", "spa", "fra", "deu", "por", "ita", "eng+spa", "eng+fra" ], "type": "string", "description": "Tesseract language code. Combine with + (e.g. eng+spa).", "default": "eng" }, "tables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables with drawn cell borders in PDFs (and all DOCX tables) and return them as rows and CSV.", "default": true }, "chunking": { "title": "Make RAG chunks", "type": "boolean", "description": "Split each document into chunks that keep the nearest heading and the page range.", "default": true }, "chunkMaxChars": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target maximum characters per chunk.", "default": 1500 }, "chunkOverlapChars": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Characters repeated from the end of the previous chunk.", "default": 150 }, "includeMarkdown": { "title": "Include full Markdown in results", "type": "boolean", "description": "Turn off to keep dataset items small when you only need chunks or tables.", "default": true }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save each document's Markdown as a file in the key-value store.", "default": true }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages beyond this are skipped (and not charged).", "default": 500 }, "failOnEmpty": { "title": "Fail the run if no text is found", "type": "boolean", "description": "Marks the run failed (not succeeded-but-empty) when no document yields any text.", "default": true } } }, "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 } } } } } } } } } }