{ "openapi": "3.0.1", "info": { "title": "Pdf Invoice Table Extraction", "description": "Automation workflows need to convert varied native-text or scanned invoices into consistent accounting-ready line items while detecting uncertain fields and arithmetic mismatches before downstream import.", "version": "0.0", "x-build-id": "k23lcm6VFHZi5pGig" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/first_watch~pdf-invoice-table-extraction/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-first_watch-pdf-invoice-table-extraction", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/first_watch~pdf-invoice-table-extraction/runs": { "post": { "operationId": "runs-sync-first_watch-pdf-invoice-table-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/first_watch~pdf-invoice-table-extraction/run-sync": { "post": { "operationId": "run-sync-first_watch-pdf-invoice-table-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sources" ], "properties": { "sources": { "title": "Invoice sources", "minItems": 1, "maxItems": 50, "type": "array", "description": "1 to 50 sources. Inline: {mode:'inline', name, format: records|text|html|csv|json|base64_document, content, mediaType?}. URL: {mode:'url', name, url (https only), format?: auto|text|html|csv|json|pdf}." }, "currencyHint": { "title": "Currency hint", "pattern": "^[A-Z]{3}$", "type": "string", "description": "ISO 4217 code used when the document does not state a currency, e.g. USD." }, "localeHint": { "title": "Locale hint", "minLength": 2, "maxLength": 35, "type": "string", "description": "Settles ambiguous notation such as 1.234 vs 1,234 or 03/04/2025. de-DE, fr-FR, es-ES etc. use comma decimals and day-first dates; en-US uses month-first dates. Without a hint, ambiguous values are rejected with AMBIGUOUS_NUMBER or AMBIGUOUS_DATE." }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 500, "type": "integer", "description": "Pages beyond this limit are ignored and reported as a warning.", "default": 100 }, "minimumConfidence": { "title": "Minimum confidence (reserved)", "minimum": 0, "maximum": 1, "type": "number", "description": "Accepted for compatibility. The Actor reports evidence lines, exceptions and reconciliation instead of confidence scores, so this value has no effect.", "default": 0.75 }, "reconciliationTolerance": { "title": "Reconciliation tolerance", "minimum": 0, "maximum": 10, "type": "number", "description": "Maximum absolute difference between stated and calculated amounts.", "default": 0.02 }, "vendorAliases": { "title": "Vendor column aliases", "type": "object", "description": "Map canonical fields to extra labels or column names, e.g. {'invoiceNumber': ['Bill No'], 'lineTotal': ['Ext Amount']}." }, "targetSchema": { "title": "Target field names", "type": "object", "description": "Optional canonical-to-customer field name mapping. Produces a mappedInvoice copy, e.g. {'invoiceNumber': 'bill_id'}." } } }, "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 } } } } } } } } } }