{ "openapi": "3.0.1", "info": { "title": "Document and PDF to JSON, Arabic and English", "description": "Returns JSON from a PDF, Word DOCX, image or text file: every paragraph and clause, or only the fields your JSON Schema names, each with the page, paragraph and quoted sentence it came from. English and Arabic, with Hijri dates, Arabic-Indic digits and right to left repair. No LLM, no API key.", "version": "0.1", "x-build-id": "alFtdTX67OBoCYide" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/omargnagy~document-to-json-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-omargnagy-document-to-json-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/omargnagy~document-to-json-extractor/runs": { "post": { "operationId": "runs-sync-omargnagy-document-to-json-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/omargnagy~document-to-json-extractor/run-sync": { "post": { "operationId": "run-sync-omargnagy-document-to-json-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "analyze", "extract" ], "type": "string", "description": "analyze returns every paragraph and clause with its page and anchor. extract returns only the fields named in your JSON Schema, each with its page and quoted evidence.", "default": "analyze" }, "sample": { "title": "Bundled sample", "enum": [ "none", "english-services-agreement", "arabic-services-agreement", "english-invoice-scan" ], "type": "string", "description": "A document bundled with the actor, for a first try with no file. When you give your own document below, the sample is ignored, so you can leave this as it is.", "default": "none" }, "documentUrl": { "title": "Document URL", "type": "string", "description": "Direct http or https link to a PDF, DOCX, image or text file. A link to a web page (HTML) is refused." }, "documentFile": { "title": "File upload", "type": "string", "description": "Upload a PDF, DOCX, image or text file instead of giving a URL." }, "keyValueStoreRecordKey": { "title": "Key-value store record key", "type": "string", "description": "Advanced, API only. Key of a record in this run's own default key-value store, which starts empty. Most callers should use Document URL or File upload." }, "documentText": { "title": "Pasted text", "type": "string", "description": "Paste the document text directly instead of giving a file." }, "documentBase64": { "title": "Base64 file", "type": "string", "description": "The file itself, base64 encoded, for callers that hold the bytes and have nowhere to host them." }, "fileName": { "title": "File name", "type": "string", "description": "Optional. Helps detect the format when the source has no name, as with base64. The file's bytes are checked first." }, "schema": { "title": "JSON Schema of the fields to extract", "type": "object", "description": "Required for extract, ignored for analyze. Properties name your fields. Types: string, number, integer, boolean, array of string. Optional per field: x-keywords (extra terms to look for) and x-pattern (a regex whose first group is the value). No nested objects." }, "ocr": { "title": "Read images with OCR", "type": "boolean", "description": "When on, an image is read with the bundled OCR. When off, an image is refused. Scanned PDFs are not OCR'd and their empty pages are not charged.", "default": true }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Language models OCR uses. Only eng and ara are bundled; any other value is refused.", "default": [ "eng", "ara" ], "items": { "type": "string" } } } }, "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 } } } } } } } } } }