{ "openapi": "3.0.1", "info": { "title": "CJK PDF to RAG Chunks – Traditional Chinese & Japanese OCR", "description": "Convert Traditional Chinese and Japanese PDFs (including scans) into heading-aware, sentence-safe chunks with page numbers for RAG and vector DBs. Parallel OCR, header/footer removal, optional Markdown tables, estimate mode. Pay per page.", "version": "0.1", "x-build-id": "WHPqLogJGF0fTp86E" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/robertwang~cjk-pdf-rag-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-robertwang-cjk-pdf-rag-chunker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/robertwang~cjk-pdf-rag-chunker/runs": { "post": { "operationId": "runs-sync-robertwang-cjk-pdf-rag-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/robertwang~cjk-pdf-rag-chunker/run-sync": { "post": { "operationId": "run-sync-robertwang-cjk-pdf-rag-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Public PDF URLs", "default": [ "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" ], "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "extract", "estimate" ], "type": "string", "description": "estimate = count pages / OCR pages only", "default": "extract" }, "chunkChars": { "title": "Target chunk size (chars)", "type": "integer", "description": "Approx characters per chunk", "default": 500 }, "maxPages": { "title": "Max pages per PDF", "type": "integer", "description": "Hard cap", "default": 200 }, "forceOcr": { "title": "Force OCR on all pages", "type": "boolean", "description": "Testing: OCR even if text layer exists", "default": false }, "ocrLang": { "title": "OCR languages", "type": "string", "description": "Tesseract langs. Empty = auto (jpn+chi_tra for Japanese docs, else chi_tra+jpn)" }, "ocrDpi": { "title": "OCR DPI", "type": "integer", "description": "Render DPI for OCR", "default": 150 }, "ocrWorkers": { "title": "OCR parallel workers", "type": "integer", "description": "Default: CPU count (min 2)" }, "detectTables": { "title": "Detect tables", "type": "boolean", "description": "Off by default (slow, ~7 s/page). Emit tables as markdown chunks with type=table", "default": false }, "pageBreak": { "title": "Break chunks at page end", "type": "boolean", "description": "Flush at page end (unfinished sentence carried over)", "default": true }, "uploadStore": { "title": "Upload key-value store", "type": "string", "description": "Key-value store holding uploaded PDFs (use when the source site blocks download)." }, "uploadKeys": { "title": "Uploaded PDF keys", "type": "array", "description": "Record keys in the upload store (or this run's default store if no store chosen).", "items": { "type": "string" } }, "verticalText": { "title": "Vertical text (直書)", "enum": [ "auto", "on", "off" ], "type": "string", "description": "Scanned pages: detect vertical (top-to-bottom, right-to-left) text and OCR with jpn_vert / chi_tra_vert.", "default": "auto" }, "deskew": { "title": "Deskew scans", "type": "boolean", "description": "Straighten scanned pages tilted 0.8–4.5°.", "default": true }, "denoise": { "title": "Denoise scans", "type": "boolean", "description": "Median filter, applied only to pages with heavy speckle noise.", "default": true }, "trustOcrLayer": { "title": "Trust existing invisible OCR layer", "type": "boolean", "description": "Scanned PDFs often carry a hidden OCR text layer of poor quality for CJK. By default such pages are re-OCRed; enable to use the existing layer (cheaper, billed as text pages).", "default": false }, "maxRunSeconds": { "title": "Max run seconds / 最長執行秒數", "minimum": 30, "type": "integer", "description": "Stop early (marking results 'truncated') before this many seconds. The platform run timeout is always respected too. / 超過秒數前提早停止並標記 truncated；平台逾時也會自動遵守。" } } }, "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 } } } } } } } } } }