{ "openapi": "3.0.1", "info": { "title": "PDF Text & Table Extractor: OCR, DOCX, PPTX to Data, RAG Chunks", "description": "Extract text from PDF, DOCX, PPTX, HTML, TXT, MD and EML by URL. One document in, hundreds of rows out: typed elements (titles, paragraphs, lists, tables), RAG-ready chunks and a per-document summary. Unofficial wrapper around unstructured (Apache-2.0).", "version": "1.0", "x-build-id": "5lMS6QLC2p3ci89Vy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ntriqpro~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ntriqpro-pdf-text-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ntriqpro~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-ntriqpro-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ntriqpro~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-ntriqpro-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "disclaimerAck" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "One or more public URLs of documents to parse. Supported: PDF, DOCX, PPTX, HTML, TXT, Markdown, EML, plus PNG/JPG/TIFF/BMP images (read via OCR). Scanned PDFs without a text layer are OCR'd automatically. Each document is broken into typed elements (titles, paragraphs, lists, tables), RAG-ready chunks and one summary row. Max 50 per run.", "items": { "type": "string" } }, "includeElements": { "title": "Include detailed element rows", "type": "boolean", "description": "Off by default. Turn on to also receive one row per structural element — title, paragraph, list item, table. This is the detailed, high-volume view of each document (hundreds of rows per document, billed per row)." }, "enableOcr": { "title": "OCR scanned documents & images", "type": "boolean", "description": "On by default. Scanned/image-only PDFs (no text layer) are automatically re-read with OCR (Tesseract), and PNG/JPG/TIFF/BMP image URLs are read with OCR. Turn off to skip OCR entirely." }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages Tesseract should read. Available: \"eng\" (English, default) and \"kor\" (Korean). Other codes are ignored.", "items": { "type": "string" } }, "includeChunks": { "title": "Include RAG-ready chunks", "type": "boolean", "description": "Smart chunks that respect section boundaries (chunk-by-title), ready to embed into a vector database for RAG pipelines." }, "chunkMaxChars": { "title": "Max characters per chunk", "minimum": 500, "maximum": 8000, "type": "integer", "description": "Upper bound on the size of each RAG chunk. 500-8000." }, "perFileTimeoutSecs": { "title": "Per-document timeout (seconds)", "minimum": 30, "maximum": 600, "type": "integer", "description": "How long a single document may take to parse before it is abandoned. 30-600." }, "maxRunSecs": { "title": "Run time budget (seconds)", "minimum": 60, "maximum": 21600, "type": "integer", "description": "Stop parsing new documents after this many seconds. Everything already parsed stays in the dataset. 60-21600." }, "maxResults": { "title": "Max result rows", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper bound on billable result rows for this run — your cost ceiling. Free-plan runs return at most 25 rows regardless of this value." }, "disclaimerAck": { "title": "I acknowledge the legal disclaimer", "type": "boolean", "description": "Required. By checking this you confirm that (1) you only process publicly accessible documents you are authorized to access; (2) you will respect each source's Terms of Service and applicable copyright; (3) you are responsible for any personal data contained in the documents you process." } } }, "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 } } }, "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 } } } } } } } } } }