{ "openapi": "3.0.1", "info": { "title": "CJK Invoice & Receipt OCR to JSON", "description": "Invoice OCR and receipt parser for Chinese & Japanese documents: Taiwan e-invoice (統一發票), Japanese invoice (請求書), receipts and quotes from PDF or photo to validated JSON with per-field confidence. Custom fields, no data retention.", "version": "0.1", "x-build-id": "hFNSuhtwKSdacSy1Q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/robertwang~cjk-document-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-robertwang-cjk-document-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/robertwang~cjk-document-extractor/runs": { "post": { "operationId": "runs-sync-robertwang-cjk-document-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/robertwang~cjk-document-extractor/run-sync": { "post": { "operationId": "run-sync-robertwang-cjk-document-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "fileUrls": { "title": "File URLs (PDF / PNG / JPEG / TIFF / WEBP)", "type": "array", "description": "Public URLs of documents to extract. Leave empty (and no uploads) to run a free built-in demo on two synthetic invoices.", "items": { "type": "string" } }, "uploadStore": { "title": "Upload key-value store ID", "type": "string", "description": "Optional. Store holding uploaded files (default: run's store)" }, "uploadKeys": { "title": "Upload keys", "type": "array", "description": "Record keys of uploaded files", "items": { "type": "string" } }, "template": { "title": "Template", "enum": [ "auto", "tw_einvoice", "jp_invoice", "receipt", "quote", "custom" ], "type": "string", "description": "Built-in templates work offline (rules) and better with an LLM; custom requires an LLM key", "default": "auto" }, "customSchema": { "title": "Custom JSON Schema", "type": "object", "description": "Used when template=custom. Object schema with properties; descriptions help the model" }, "engine": { "title": "Engine", "enum": [ "auto", "llm", "rules" ], "type": "string", "description": "auto = vision LLM if a key is available (cross-checked with rules), else rules only", "default": "auto" }, "llmProvider": { "title": "LLM provider", "enum": [ "gemini", "openai", "none" ], "type": "string", "description": "openai = any OpenAI-compatible endpoint (set base URL)", "default": "gemini" }, "llmApiKey": { "title": "Your LLM API key (optional)", "type": "string", "description": "Bring your own key (e.g. free Gemini key from aistudio.google.com/apikey). Sent only to the provider, never stored or logged" }, "llmModel": { "title": "Model", "type": "string", "description": "Default gemini-flash-lite-latest (falls back to gemini-flash-latest) / gpt-4o-mini" }, "llmBaseUrl": { "title": "LLM base URL", "type": "string", "description": "For OpenAI-compatible providers" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract languages, e.g. chi_tra+jpn+eng", "default": "chi_tra+jpn+eng" }, "forceOcr": { "title": "Force OCR", "type": "boolean", "description": "OCR even if the PDF has a text layer", "default": false }, "maxPages": { "title": "Max pages per document", "type": "integer", "description": "Pages beyond this are ignored", "default": 10 }, "deleteUploadsAfter": { "title": "Delete uploaded files after run", "type": "boolean", "description": "Remove uploaded records from the key-value store when done", "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 } } } } } } } } } }