{ "openapi": "3.0.1", "info": { "title": "Documents to Markdown for RAG (Docling)", "description": "Convert PDF and DOCX files to clean Markdown with Docling: page count, detected tables, metadata and optional RAG-ready chunks.", "version": "0.1", "x-build-id": "pghcwxdlGg48Wk6uG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/br_data_hub~docs-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-br_data_hub-docs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/br_data_hub~docs-to-markdown/runs": { "post": { "operationId": "runs-sync-br_data_hub-docs-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/br_data_hub~docs-to-markdown/run-sync": { "post": { "operationId": "run-sync-br_data_hub-docs-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Enter public links to PDF or DOCX files, one per line, up to 100 per run. The format is detected from the file, so links without an extension work too.", "default": [ "https://raw.githubusercontent.com/docling-project/docling/v2.145.0/tests/data/pdf/sources/2305.03393v1-pg9.pdf" ], "items": { "type": "string" } }, "uploadedFile": { "title": "Upload a file", "type": "string", "description": "Upload a PDF or DOCX from your computer instead of giving a link. It is converted together with the URLs above." }, "chunking": { "title": "Split into chunks for RAG", "type": "boolean", "description": "Turn on to also get the Markdown split into heading-aware chunks, ready for embeddings. Each chunk keeps its heading path.", "default": false }, "chunkSize": { "title": "Chunk size", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Set the maximum characters per chunk, overlap included, e.g. 2000. About 4 characters make one token in English.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Set how many characters to repeat from the end of the previous chunk of the same section, e.g. 200, so context is not lost at the cut. Capped at half the chunk size.", "default": 200 }, "tableStructure": { "title": "Recognize table structure", "type": "boolean", "description": "Keep on to rebuild PDF tables cell by cell with Docling's TableFormer model. Turn off for faster runs on text-only documents.", "default": true }, "includeTables": { "title": "Tables as Markdown", "type": "boolean", "description": "Keep on to add every detected table (page, rows, columns and Markdown) to the result. Turn off to list only table position and size.", "default": true }, "ocr": { "title": "OCR scanned pages", "type": "boolean", "description": "Turn on for scanned PDFs and text inside images. Slower; leave off for digital PDFs, which already contain their text.", "default": false }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Set a page limit, e.g. 200. Longer documents are skipped with an error and not charged.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Set a size limit in MB, e.g. 50. Larger files are skipped with an error and not charged.", "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 } } } } } } } } } }