Elevate your data handling capabilities with Extracta.ai's Document Data Extraction API. Our cutting-edge solution empowers your systems to automatically extract structured data from a myriad of documents - whether they are scanned images, PDFs, emails, invoices, contracts, or any digital file format you can think of. Tailored to meet the needs of various industries, our API facilitates the seamless automation of workflows, significantly reducing manual efforts and enhancing overall efficiency.
Features:
Whether you're a software developer, a business analyst, or a data scientist, our Document Data Extraction API is designed to streamline your data processing tasks, allowing you to focus on what truly matters - driving your business forward. Start with Extracta.ai today and transform the way you handle documents forever.
Structure your request with mandatory parameters: 'name', 'language', 'fields' and 'file'. Each field requires a 'key', with 'description' and 'example' being optional. The document must be provided as either 'base64String' or a 'fileUrl'.
## API Documentation
This section provides guidelines for structuring your Document Parsing API requests to Extracta.ai. Ensure to follow the format below for successful data extraction:
## Request Format
```
{
"extractionDetails": {
"name": "Extraction Name", // required - Name your extraction process
"language": "Supported Language", // required - Choose from the supported languages
"fields": [
{
"key": "Field Key", // required - Define the key for data extraction
"description": "Field Description", // optional - Describe the field
"example": "Field Example" // optional - Provide an example value
},
...
]
},
"file": "base64String or file URL" // required - Provide the document in base64String format or as a URL
}
```
## Advanced Format
In addition to the basic format outlined in the previous sections, Extracta.ai also supports more complex data structures for specialized extraction needs. This advanced format allows the definition of **nested objects and arrays**, catering to a broader range of data representation.
### Type `object`
The **object** type represents a structured object with multiple **properties**. Each property is defined as an object within an array, and can include its own **key**, **description**, **type**, and **example**.
```
{
"key": "personal_info",
"description": "Personal information of the person", // optional
"type": "object",
"properties": [
{
"key": "name",
"description": "Name of the person", // optional
"example": "Alex Smith", // optional
"type": "string" // optional
},
{
"key": "email",
"description": "Email of the person",
"example": "[email protected]",
"type": "string"
},
.....
]
}
```
### Type `array`
The **array** type is used for lists of **items**, such as a collection of work experiences. The items key contains an object defining the structure of each item in the array.
```
{
"key": "work_experience",
"description": "Work experience of the person", // optional
"type": "array",
"items": {
"type": "object",
"properties": [
{
"key": "title",
"description": "Title of the job", // optional
"example": "Software Engineer", // optional
"type": "string" // optional
},
{
"key": "start_date",
"description": "Start date of the job",
"example": "2022",
"type": "string"
},
...
]
}
}
```
### Notes on Usage | Document Parsing API
- For both `object` and `array` types, the `example` parameter is applicable only for their inner properties/items.
- When defining fields, if no `type` is specified, it defaults to `string`.
- For `object` and `array` types, the inner fields can only be of type `string`. This means that each property within an object or each item within an array should be a string type, ensuring consistency and simplicity in data representation.
- These advanced field types enable more detailed and structured data representation, enhancing the capabilities of Extracta.ai's data extraction process.
## Supported File Types
Extracta.ai is capable of processing documents in **image (JPG, PNG), PDF, and DOCX formats**. This enhancement allows for a wider range of document types to be submitted for extraction.
## Supported Languages
Extracta.ai currently supports document extraction in the following languages: **Romanian, English, French, Spanish, Arabic, Portuguese, German, Italian**. Additional support for 20 more languages is planned.
**Note**: If an unsupported language is specified, the API will return an error message indicating an invalid language choice. Keep updated with our API documentation for new language additions.
Object | Description |
---|---|
Request Body |
[Required] Json |
{
"name": "Darren Charles",
"email": "[email protected]",
"phone": "+1-709-680-9033",
"address": "9 Corpus Christi, Texas",
"soft_skills": "highly motivated, ability to translate business strategies, learn new things",
"hard_skills": "Matlab, MeVisLab, Keras, CUDA, Git, DataStage, MQTT",
"last_job": "Trainee With English Communications",
"years_of_experience": "Ongoing"
}
curl --location --request POST 'https://zylalabs.com/api/3606/document+data+extraction+api/4000/process+document' --header 'Authorization: Bearer YOUR_API_KEY'
After signing up, every developer is assigned a personal API access key, a unique combination of letters and digits provided to access to our API endpoint. To authenticate with the Document Data Extraction API REST API, simply include your bearer token in the Authorization header.
Header | Description |
---|---|
Authorization
|
[Required] Should be Bearer access_key . See "Your API Access Key" above when you are subscribed. |
No long term commitments. One click upgrade/downgrade or cancellation. No questions asked.
Extracta.ai represents an advanced technological platform dedicated to the extraction of structured data from diverse documents, such as resumes and invoices. This service aims to streamline workflows, eliminate the need for manual data entry, and boost productivity in numerous sectors.
We are capable of handling a broad spectrum of documents, encompassing both structured and unstructured formats, such as PDFs, Word documents, text files, and scanned images (in PNG, JPG formats), employing OCR technology as required.
Indeed, Extracta.ai is built for effortless integration. Our service can be easily connected to your current software and workflows via our API. Furthermore, we intend to provide options for local system deployment in the future to increase data privacy.
Diverging from the approach of competitors who depend on fixed templates and models, Extracta.ai employs meticulously adjusted Large Language Models (LLMs) for extracting data from any document without the need for previous training, achieving an accuracy rate of up to 99%. This method ensures enhanced flexibility, quicker deployment, reduced costs
Our dedicated support team is available to assist you with any technical queries or further information. For support or any inquiries, please email us at: [email protected]
Zyla API Hub is, in other words, an API MarketPlace. An all-in-one solution for your developing needs. You will be accessing our extended list of APIs with only your user. Also, you won't need to worry about storing API keys, only one API key for all our products is needed.
Prices are listed in USD. We accept all major debit and credit cards. Our payment system uses the latest security technology and is powered by Stripe, one of the world’s most reliable payment companies. If you have any trouble with paying by card, just contact us at [email protected]
Sometimes depending on the bank's fraud protection settings, a bank will decline the validation charge we make when we attempt to be sure a card is valid. We recommend first contacting your bank to see if they are blocking our charges. If more help is needed, please contact [email protected] and our team will investigate further
Prices are based on a recurring monthly subscription depending on the plan selected — plus overage fees applied when a developer exceeds a plan’s quota limits. In this example, you'll see the base plan amount as well as a quota limit of API requests. Be sure to notice the overage fee because you will be charged for each additional request.
Zyla API Hub works on a recurring monthly subscription system. Your billing cycle will start the day you purchase one of the paid plans, and it will renew the same day of the next month. So be aware to cancel your subscription beforehand if you want to avoid future charges.
Just go to the pricing page of that API and select the plan that you want to upgrade to. You will only be charged the full amount of that plan, but you will be enjoying the features that the plan offers right away.
Yes, absolutely. If you want to cancel your plan, simply go to your account and cancel on the Billing page. Upgrades, downgrades, and cancellations are immediate.
You can contact us through our chat channel to receive immediate assistance. We are always online from 9 am to 6 pm (GMT+1). If you reach us after that time, we will be in contact when we are back. Also you can contact us via email to [email protected]
Service Level:
96%
Response Time:
446ms
Service Level:
100%
Response Time:
0ms
Service Level:
99%
Response Time:
1,791ms
Service Level:
100%
Response Time:
1,580ms
Service Level:
65%
Response Time:
1,252ms
Service Level:
100%
Response Time:
2,331ms
Service Level:
100%
Response Time:
11,188ms
Service Level:
100%
Response Time:
599ms
Service Level:
100%
Response Time:
1,883ms
Service Level:
100%
Response Time:
1,322ms
Service Level:
100%
Response Time:
413ms
Service Level:
100%
Response Time:
2,610ms
Service Level:
100%
Response Time:
3,535ms
Service Level:
100%
Response Time:
1,744ms
Service Level:
100%
Response Time:
285ms
Service Level:
100%
Response Time:
687ms