Document Structured Extractor
Pricing
$50.00 / 1,000 document structured extractor results
Go to Apify Store
Document Structured Extractor
Pricing
$50.00 / 1,000 document structured extractor results
You can access the Document Structured Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youโll need an Apify account and your API token, found in API & Integrations in Apify Console.
![Handelsregister.de [$8๐ฐ] German Company Registry avatar](https://images.apifyusercontent.com/KgKGCeLeSWEoHI6V5NiA6P4lpjAVi4OtWdqjGEIoQxM/rs:fill:76:76/cb:1/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vbmduOHZSRVNUa3NleVdFNnAtYWN0b3Itb0F2Y09hM2EwUDN4cUh3TmQtbGhnZ2N3ajIwby1oYW5kbGVyZWcucG5n.webp){kind=avatar}
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "r2ZbOz9Jqe0rhKiKe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/encouraged_offspring~document-structured-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-encouraged_offspring-document-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/encouraged_offspring~document-structured-extractor/runs": { "post": { "operationId": "runs-sync-encouraged_offspring-document-structured-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/encouraged_offspring~document-structured-extractor/run-sync": { "post": { "operationId": "run-sync-encouraged_offspring-document-structured-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": [ "profile", "source" ], "properties": { "profile": { "title": "Extraction profile", "enum": [ "tender", "invoice", "contract-dates", "privacy-policy", "generic-key-values" ], "type": "string", "description": "Supported extraction profile.", "default": "invoice" }, "source": { "title": "Source", "type": "object", "description": "Use text or a public URL. Scanned PDF/image OCR is unsupported.", "properties": { "type": { "title": "Source type", "type": "string", "enum": [ "text", "url", "base64" ], "prefill": "text", "description": "Source type.", "editor": "select" }, "text": { "title": "Text", "type": "string", "editor": "textarea", "description": "Text source to inspect.", "prefill": "Invoice Number: INV-100. Total: $42.00." }, "url": { "title": "Public URL", "type": "string", "prefill": "https://example.com/invoice", "description": "Public URL.", "editor": "textfield" }, "data": { "title": "Base64 text", "type": "string", "editor": "textarea", "description": "Base64 decoded as text only.", "prefill": "SW52b2ljZSBOdW1iZXI6IElOVi0xMDAu" }, "mimeType": { "title": "MIME type", "type": "string", "prefill": "text/plain", "description": "MIME type.", "editor": "textfield" } } }, "fields": { "title": "Requested fields", "maxItems": 50, "type": "array", "description": "Requested fields.", "items": { "type": "object" } } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Document Structured Extractor from the options below:
If youโd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: