# ID to JSON Parser (`parseforge/id-to-json-parser`) Actor Extract structured JSON data from passports, driver’s licenses, and ID cards using advanced AI vision. Automatically capture personal details, document info, dates, and all relevant fields from ID images, turning them into clean, accurate JSON for fast verification workflows. - **URL**: https://apify.com/parseforge/id-to-json-parser.md - **Developed by:** [ParseForge](https://apify.com/parseforge) (community) - **Categories:** AI, Jobs, Automation - **Stats:** 5 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: 5.00 out of 5 stars ## Pricing Pay per event This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ![ParseForge Banner](https://github.com/ParseForge/apify-assets/blob/ad35ccc13ddd068b9d6cba33f323962e39aed5b2/banner.jpg?raw=true) ## πŸͺͺ ID to JSON Parser > πŸš€ **Extract structured data from identity documents in seconds.** Upload passports, driver's licenses, or ID cards. No coding, no manual data entry required. > πŸ•’ **Last updated:** 2026-04-23 Β· **πŸ“Š 15+ fields** Β· **πŸ”„ Runs on Apify cloud or locally** Β· **πŸ“ Export: JSON, CSV, Excel** The ID to JSON Parser converts identity documents into clean, structured JSON data using advanced AI vision. Upload images of **passports, driver's licenses, or ID cards** and get back structured data with names, document numbers, dates, addresses, and all other visible fields. Each document yields **15+ data points** extracted automatically, ready for database ingestion, compliance workflows, or verification systems. Built for companies processing identity documents at scale, KYC compliance teams automating customer verification, HR departments digitizing employee records, and developers building identity data pipelines. The parser handles multiple image formats (JPEG, PNG, WebP) and PDFs, processes multi-page documents, and lets you specify exactly which fields to extract. No manual data entry, no template configuration, just upload and get structured output. | **Target Audience** | **Use Cases** | |---|---| | KYC/Compliance Teams | Customer identity verification | | HR Departments | Employee document digitization | | Financial Institutions | Account opening automation | | Immigration Services | Document processing and validation | | Insurance Companies | Policy holder verification | | Software Developers | ID extraction pipeline integration | --- ### πŸ“‹ What the ID to JSON Parser does - πŸ†” **Identifies document type** automatically, distinguishing between passports, driver's licenses, national ID cards, and other identity documents - πŸ‘€ **Extracts full personal details** including first name, last name, middle name, date of birth, gender, and nationality - πŸ“„ **Captures document metadata** such as document number, issue date, expiry date, and issuing authority - πŸ“ **Pulls address information** including street, city, state, and postal code when present on the document - 🧬 **Reads physical details** like height, weight, eye color, and hair color from driver's licenses and ID cards - πŸ”§ **Supports custom field selection** so you can specify exactly which fields to extract for your workflow The parser processes uploaded images through AI vision models that understand document layouts across countries and formats. It handles different orientations, image quality levels, and document types without manual template configuration. > πŸ’‘ **Why it matters:** Manual data entry from ID documents is slow, expensive, and error-prone. This parser automates the entire process, extracting structured data from any identity document in seconds instead of minutes. --- ### 🎬 Full Demo _🚧 Coming soon..._ --- ### βš™οΈ Input
FieldTypeRequiredDescription
idImagearrayYesOne or more ID document images or PDFs. Supports JPEG, PNG, GIF, WebP, and PDF formats.
maxItemsintegerNoMaximum documents to process. Free users: limited to 10. Paid users: up to 1,000,000.
fieldsToExtractstringNoComma-separated list of specific fields to extract (e.g., "firstName, lastName, dateOfBirth"). Leave blank for all fields.
systemPromptstringNoCustom instructions to guide extraction. Leave blank for default behavior.
**Example 1: Extract all fields from an ID image** ```json { "idImage": ["https://example.com/passport-scan.jpg"], "maxItems": 10 } ```` **Example 2: Extract specific fields only** ```json { "idImage": ["https://example.com/drivers-license.png"], "fieldsToExtract": "firstName, lastName, dateOfBirth, documentNumber, expiryDate", "maxItems": 5 } ``` > ⚠️ **Good to Know:** You can upload multiple documents in a single run by adding more URLs to the idImage array. The parser handles both image files and multi-page PDFs. Free users are automatically limited to 10 documents per run. *** ### πŸ“Š Output #### 🧾 Schema | Emoji | Field | Type | Description | |---|---|---|---| | πŸ“„ | documentType | string | Type of document (passport, driver's license, ID card) | | πŸ†” | documentNumber | string | Unique document number or ID | | πŸ‘€ | firstName | string | First name | | πŸ‘€ | lastName | string | Last name | | πŸ‘€ | middleName | string | Middle name (if present) | | 🌍 | nationality | string | Nationality or citizenship | | 🌍 | country | string | Country of issue | | πŸ“… | dateOfBirth | string | Date of birth | | πŸ“… | issueDate | string | Document issue date | | πŸ“… | expiryDate | string | Document expiry date | | 🧬 | gender | string | Gender | | πŸ“ | height | string | Height (driver's licenses) | | πŸ‘οΈ | eyeColor | string | Eye color (driver's licenses) | | πŸ“ | address | string | Full address on document | | πŸ–ΌοΈ | sourceImage | string | URL of the processed image | | ❌ | error | string | Error message if extraction failed | #### πŸ“¦ Sample records
πŸ“„ Record 1 - Passport ```json { "documentType": "passport", "documentNumber": "X12345678", "firstName": "John", "lastName": "Smith", "nationality": "United States", "country": "US", "dateOfBirth": "1985-03-15", "issueDate": "2020-06-10", "expiryDate": "2030-06-09", "gender": "M", "sourceImage": "https://example.com/passport-scan.jpg" } ```
πŸ“„ Record 2 - Driver's License ```json { "documentType": "driver's license", "documentNumber": "D1234567", "firstName": "Jane", "lastName": "Doe", "dateOfBirth": "1990-07-22", "issueDate": "2022-01-15", "expiryDate": "2026-07-22", "gender": "F", "height": "5'6\"", "eyeColor": "BRN", "address": "123 Main Street, Springfield, IL 62704", "country": "US" } ```
πŸ“„ Record 3 - National ID Card ```json { "documentType": "national ID card", "documentNumber": "AB1234567", "firstName": "Carlos", "lastName": "Garcia", "middleName": "Miguel", "nationality": "Spain", "country": "ES", "dateOfBirth": "1978-11-03", "issueDate": "2021-05-20", "expiryDate": "2031-05-19", "gender": "M" } ```
*** ### ✨ Why choose this Actor | Feature | Details | |---|---| | πŸͺͺ Multi-document support | Passports, driver's licenses, national ID cards, and more | | 🌍 International coverage | Handles documents from countries worldwide | | πŸ”§ Custom field selection | Extract only the fields you need | | πŸ“„ PDF support | Processes multi-page PDF documents | | πŸ–ΌοΈ Multiple image formats | JPEG, PNG, GIF, WebP | | ⚑ Fast processing | Seconds per document, not minutes | | πŸ“ Structured output | Clean JSON ready for databases and APIs | > πŸ“ˆ **Typical performance:** Processes **1 document in 3-5 seconds.** A batch of 50 documents completes in about 4 minutes. *** ### πŸ“ˆ How it compares to alternatives | Feature | This Actor | Manual Data Entry | Generic OCR Tools | |---|---|---|---| | Structured JSON output | βœ… | ❌ | Partial | | Multi-document type support | βœ… | βœ… (slow) | Partial | | International document handling | βœ… | βœ… (slow) | Partial | | Custom field selection | βœ… | N/A | ❌ | | Batch processing | βœ… | ❌ | Partial | | No template configuration | βœ… | N/A | ❌ | | API and automation support | βœ… | ❌ | Partial | Built specifically for identity documents, with AI vision that understands document layouts rather than generic text recognition. *** ### πŸš€ How to use 1. **Create a free Apify account** - [Sign up here](https://console.apify.com/sign-up?fpr=vmoqkp) (includes free credits) 2. **Open the ID to JSON Parser** - Navigate to the Actor page and click "Start" 3. **Upload your documents** - Add image URLs or PDF links to the idImage field 4. **Choose fields (optional)** - Specify which fields to extract, or leave blank for all 5. **Run and download** - Click "Start", wait for results, then export as JSON, CSV, or Excel > ⏱️ **First results appear in under 10 seconds.** A typical run processing 10 documents completes in about 1 minute. *** ### πŸ’Ό Business use cases
**KYC & Compliance** - Automate identity verification workflows - Extract document data for compliance checks - Process customer onboarding documents at scale - Build audit trails from ID submissions **Human Resources** - Digitize employee identity documents - Verify work authorization documents - Build structured employee records from scans - Process new hire paperwork automatically
**Financial Services** - Accelerate account opening processes - Extract data for anti-money laundering checks - Validate customer identity across channels - Automate loan application document processing **Insurance & Healthcare** - Process policyholder identity documents - Verify patient identity for medical records - Extract data from insurance claims submissions - Digitize legacy paper-based ID archives
*** *** ### 🌟 Beyond business use cases Data like this powers more than commercial workflows. The same structured records support research, education, civic projects, and personal initiatives.
#### πŸŽ“ Research and academia - Empirical datasets for papers, thesis work, and coursework - Longitudinal studies tracking changes across snapshots - Reproducible research with cited, versioned data pulls - Classroom exercises on data analysis and ethical scraping #### 🎨 Personal and creative - Side projects, portfolio demos, and indie app launches - Data visualizations, dashboards, and infographics - Content research for bloggers, YouTubers, and podcasters - Hobbyist collections and personal trackers
#### 🀝 Non-profit and civic - Transparency reporting and accountability projects - Advocacy campaigns backed by public-interest data - Community-run databases for local issues - Investigative journalism on public records #### πŸ§ͺ Experimentation - Prototype AI and machine-learning pipelines with real data - Validate product-market hypotheses before engineering spend - Train small domain-specific models on niche corpora - Test dashboard concepts with live input
### πŸ€– Ask an AI assistant about this scraper Open a ready-to-send prompt about this ParseForge actor in the AI of your choice: - πŸ’¬ [**ChatGPT**](https://chat.openai.com/?q=How%20do%20I%20use%20the%20ID%20to%20JSON%20Parser%20by%20ParseForge%20on%20Apify%3F%20Show%20me%20input%20examples%2C%20output%20fields%2C%20common%20use%20cases%2C%20and%20how%20to%20integrate%20it%20into%20a%20workflow.) - 🧠 [**Claude**](https://claude.ai/new?q=How%20do%20I%20use%20the%20ID%20to%20JSON%20Parser%20by%20ParseForge%20on%20Apify%3F%20Show%20me%20input%20examples%2C%20output%20fields%2C%20common%20use%20cases%2C%20and%20how%20to%20integrate%20it%20into%20a%20workflow.) - πŸ” [**Perplexity**](https://perplexity.ai/search?q=How%20do%20I%20use%20the%20ID%20to%20JSON%20Parser%20by%20ParseForge%20on%20Apify%3F%20Show%20me%20input%20examples%2C%20output%20fields%2C%20common%20use%20cases%2C%20and%20how%20to%20integrate%20it%20into%20a%20workflow.) - πŸ…’ [**Copilot**](https://copilot.microsoft.com/?q=How%20do%20I%20use%20the%20ID%20to%20JSON%20Parser%20by%20ParseForge%20on%20Apify%3F%20Show%20me%20input%20examples%2C%20output%20fields%2C%20common%20use%20cases%2C%20and%20how%20to%20integrate%20it%20into%20a%20workflow.) ### ❓ Frequently Asked Questions
πŸ’³ Do I need a paid Apify plan to run this actor? No. You can start right now on the free Apify plan, which includes **$5 in free monthly credit**. That is enough to run this actor several times and explore the output before committing to anything. Paid plans unlock higher limits, more concurrent runs, and larger datasets. [Create a free Apify account here](https://console.apify.com/sign-up?fpr=vmoqkp) to get started.
🚨 What happens if my run fails or returns no results? Failed runs are not charged. If the source site changes, proxies get rate-limited, or a specific input matches nothing, re-run the actor or open our [contact form](https://tally.so/r/BzdKgA) and we will investigate. You can also check the run log in the Apify console to see why the run stopped.
πŸ“ How many items can I scrape per run? Free users are limited to **10 items per run** so you can preview the output and confirm the actor works for your use case. Paid users can raise maxItems up to **1,000,000** per run. [Upgrade here](https://console.apify.com/sign-up?fpr=vmoqkp) if you need full scale.
πŸ•’ How fresh is the data? Every run fetches live data at the moment of execution. There is no cache or delay: the records you get reflect what the source returned at that moment. Schedule the actor to maintain a rolling snapshot of the data you need.
πŸ§‘β€πŸ’» Can I call this actor from my own code? Yes. Apify exposes every actor as a REST endpoint and ships first-class SDKs for [Node.js](https://docs.apify.com/sdk/js) and [Python](https://docs.apify.com/sdk/python). You can start a run, read the dataset, and handle webhooks from your own app in a few lines. All you need is your Apify API token.
πŸ“€ How do I export the data? Every Apify dataset can be downloaded in one click from the console as CSV, JSON, JSONL, Excel, HTML, XML, or RSS. You can also pull results programmatically via the [Apify API](https://docs.apify.com/api/v2) or stream them into BigQuery, S3, and other destinations through built-in integrations.
πŸ“… Can I schedule the actor to run automatically? Yes. Use the Apify scheduler to run the actor on any cadence, from hourly to monthly. Results are saved to your dataset and can be delivered to webhooks, email, Slack, cloud storage, or automation tools such as Zapier and Make. ***
### πŸ”Œ Automating ID to JSON Parser **Node.js** ```javascript import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ token: 'YOUR_API_TOKEN' }); const run = await client.actor("parseforge/id-to-json-parser").call({ idImage: ["https://example.com/passport.jpg"], maxItems: 10 }); const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items); ``` **Python** ```python from apify_client import ApifyClient client = ApifyClient("YOUR_API_TOKEN") run = client.actor("parseforge/id-to-json-parser").call(run_input={ "idImage": ["https://example.com/passport.jpg"], "maxItems": 10 }) items = list(client.dataset(run["defaultDatasetId"]).iterate_items()) print(items) ``` - πŸ“– [Apify API Reference](https://docs.apify.com/api/v2) - 🐍 [Python API Client docs](https://docs.apify.com/api/client/python) - 🟒 [Node.js API Client docs](https://docs.apify.com/api/client/js) **Schedules:** While ID parsing is typically triggered on demand, you can set up [Apify Schedules](https://docs.apify.com/platform/schedules) to process batch uploads at regular intervals, such as daily processing of submitted documents. ### πŸ”Œ Integrate with any app - πŸ”— **Make (Integromat)** - Connect ID parsing output to CRM, compliance, or database apps - πŸ”— **Zapier** - Trigger workflows when new ID data is extracted - πŸ”— **Slack** - Send notifications when document processing completes - πŸ”— **Airbyte** - Sync extracted data to your data warehouse - πŸ”— **GitHub** - Automate document processing pipelines with GitHub Actions - πŸ”— **Google Drive** - Export parsed data to Google Sheets *** ### πŸ”— Recommended Actors | Actor | Description | |---|---| | πŸ“„ [PDF to JSON Parser](https://apify.com/parseforge/pdf-to-json-parser) | Extract structured data from any PDF document | | πŸ” [HTML to JSON Smart Parser](https://apify.com/parseforge/html-to-json-smart-parser) | Convert HTML content to structured JSON | | 🎀 [Audio Transcriber](https://apify.com/parseforge/audio-transcriber) | Transcribe audio files to text | | πŸ“ [CV Optimizer](https://apify.com/parseforge/cv-optimizer) | Analyze and optimize resume/CV documents | | πŸ”— [Address Normalizer](https://apify.com/parseforge/address-normalizer) | Standardize and validate extracted addresses | > πŸ’‘ **Pro Tip:** Use the ID to JSON Parser to extract address data, then pipe it through the Address Normalizer to standardize and validate the results. *** **πŸ†˜ Need Help?** [**Open our contact form**](https://tally.so/r/BzdKgA) and we will get back to you within 24 hours. For bug reports, feature requests, or integration help, we are here to assist. *** > **Disclaimer:** This Actor is provided as-is, without warranty. Users are responsible for ensuring they have proper authorization to process identity documents and comply with applicable privacy laws and data protection regulations. The authors are not responsible for how the extracted data is used. Always verify extracted data for critical applications. # Actor input Schema ## `idImage` (type: `array`): Upload one or more ID document images (passport, driver's license, identity card, etc.) or PDF files using file upload. Both images and PDFs will be automatically processed. ## `maxItems` (type: `integer`): Free users: Limited to 100. Paid users: Optional, max 1,000,000. Leave empty for unlimited (paid users only). ## `fieldsToExtract` (type: `string`): Specify which fields you want extracted (e.g., "firstName, lastName, dateOfBirth, documentNumber"). If not provided, the AI will automatically extract all important fields it identifies. ## `systemPrompt` (type: `string`): Optional custom system prompt to guide the AI extraction. If not provided, a smart default prompt will be used that extracts meaningful information from the ID document. ## Actor input object example ```json { "idImage": [ "https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp" ], "maxItems": 10 } ``` # Actor output Schema ## `extractedData` (type: `string`): Complete dataset with all extracted ID document information including personal details, document information, and metadata ## `overview` (type: `string`): Overview view of extracted ID data with key fields displayed in a table format # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "idImage": [ "https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp" ], "maxItems": 10, "fieldsToExtract": "", "systemPrompt": "" }; // Run the Actor and wait for it to finish const run = await client.actor("parseforge/id-to-json-parser").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`πŸ’Ύ Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // πŸ“š Want to learn more πŸ“–? Go to β†’ https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "idImage": ["https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp"], "maxItems": 10, "fieldsToExtract": "", "systemPrompt": "", } # Run the Actor and wait for it to finish run = client.actor("parseforge/id-to-json-parser").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("πŸ’Ύ Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # πŸ“š Want to learn more πŸ“–? Go to β†’ https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "idImage": [ "https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp" ], "maxItems": 10, "fieldsToExtract": "", "systemPrompt": "" }' | apify call parseforge/id-to-json-parser --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=parseforge/id-to-json-parser", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "ID to JSON Parser", "description": "Extract structured JSON data from passports, driver’s licenses, and ID cards using advanced AI vision. Automatically capture personal details, document info, dates, and all relevant fields from ID images, turning them into clean, accurate JSON for fast verification workflows.", "version": "1.0", "x-build-id": "IDeCOQuo6igDj3zco" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~id-to-json-parser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-id-to-json-parser", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~id-to-json-parser/runs": { "post": { "operationId": "runs-sync-parseforge-id-to-json-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~id-to-json-parser/run-sync": { "post": { "operationId": "run-sync-parseforge-id-to-json-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "idImage": { "title": "ID Image or PDF", "type": "array", "description": "Upload one or more ID document images (passport, driver's license, identity card, etc.) or PDF files using file upload. Both images and PDFs will be automatically processed." }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 100. Paid users: Optional, max 1,000,000. Leave empty for unlimited (paid users only)." }, "fieldsToExtract": { "title": "Fields to Extract (Optional)", "type": "string", "description": "Specify which fields you want extracted (e.g., \"firstName, lastName, dateOfBirth, documentNumber\"). If not provided, the AI will automatically extract all important fields it identifies." }, "systemPrompt": { "title": "System Prompt (Optional)", "type": "string", "description": "Optional custom system prompt to guide the AI extraction. If not provided, a smart default prompt will be used that extracts meaningful information from the ID document." } } }, "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 } } } } } } } } } } ```