Affinda Resume & Invoice parsers engines are available on Eden AI

We are pleased to announce that Affinda Resume and Invoice parsers have been integrated into Eden AI API.

‍

‍What is Affinda?

Affinda is an AI-powered Document Parsing solution provider for the automation of high-volume document workflow including emails, contracts, invoices, forms, financial statements, and more. Their approach is deliberately designed to overcome the typical issues associated with AI investment, removing the need for high-cost and error-prone manual processes.

‍

Why do we offer Affinda in addition to other Document Parsing APIs?

Eden AI offers Affinda AI solutions on its platform amongst several other technologies. We want our users to have access to multiple AI engines and manage them in one place so they can reach high performance, optimize cost and cover all their needs. There are many reasons for using multiple AI APIs : ‍ 

• Fallback provider is the ABCs. You need to set up an AI API that is requested if and only if the main AI API does not perform well (or is down). You can use the confidence score returned or other methods to check provider accuracy. 
• Performance optimization. After the testing phase, you will be able to build a mapping of AI vendors' performance that depends on the criteria that you chose. Each data that you need to process will be then sent to the best API. 
• Cost - Performance ratio optimization. This method allows you to choose the cheapest provider that performs well for your data. Let's imagine that you choose Google Cloud API for customer "A" because they all perform well and this is the cheapest. You will then choose Microsoft Azure for customer "B", a more expensive API but Google performances are not satisfying for customer "B". (this is a random example) 
• Combine multiple AI APIs. This approach is required if you look for extremely high accuracy. The combination leads to higher costs but allows your AI service to be safe and accurate because AI APIs will validate and invalidate each other for each piece of data.

Interview with Affinda Product Lead

We had the chance to talk to Affinda Product Lead, Charlie Bellingham, who agreed to answer some of our questions:

‍

‍

Can you introduce Affinda?

We’re a team of total AI nerds from Melbourne, Australia, and our focus is on using AI technology to extract data from documents. We have all seen funny or cute applications of AI, but our focus is on building products that actually help people in their businesses. At Affinda, what we’re trying to do is help customers automate previously manual workflows to reduce costs and free up staff to focus on higher-value activities. Affinda was launched in 2020 and has developed a suite of products, starting within the Recruitment and Accounts Payable industries. We are continually working on developing new features and functionality for these existing products, as well as looking to expand into new industries and products such as identification documents, logistics, and legal.

‍

Who are your customers?

Affinda targets both technology platforms and enterprise customers. Our multilingual capabilities (Affinda’s VEGA engine can understand documents in 56 different languages) mean that we have a global presence that can easily adapt to any customer’s requirements. Technology companies such as applicant tracking systems and AP automation providers benefit from the market-leading accuracy of our document parsers while making our interfaces as intuitive as possible for enterprise users. In addition to our off-the-shelf products, we also work with various customers to develop customized models and solutions that are specific to their requirements.

‍

Why did you decide to be integrated into Eden AI?

A very common pain point for customers is the integration of solutions like ours into their platforms. We were attracted to partnering with Eden AI as the solution simplifies this component by offering a single, easy-to-use API that customers can use across multiple document types and requirements. It means that Affinda document extraction products can be offered alongside solutions from other industry leaders. This allows customers to improve a wide range of business processes and drive efficiency through the latest advancements in AI technology.

‍

‍

How to use Affinda on Eden AI?

To use Affinda invoice parser on Eden AI, you just need to the documentation and call the API:

import json
import requests

headers = {'Authorization': 'Bearer your_API_key'}

response = requests.post("https://api.edenai.run/v2/ocr/invoice_parser", 
                            headers=headers,
                            data={'providers': "['affinda']", 'language':'en'},
                            files = {'files': open("file_path",'rb')})

result = json.loads(response.text)

‍

Don’t hesitate to check it out with the API or on the platform.

‍

Eden AI is a must-have

Eden AI is the future of AI usage in companies. Our platform not only allows you to call multiple AI APIs but also gives you :

• Centralized and fully monitored billing for all AI APIs
• A unified API for all providers: simple and standard to use, quick switch between providers, access to the specific features of each provider
• Standardized response format: the JSON output format is the same for all suppliers thanks to Eden AI's standardization work. The response elements are also standardized thanks to Eden AI's powerful matching algorithms.
• Best Artificial Intelligence APIs of the market: big cloud providers (Google, AWS, Microsoft, and more specialized engines)
• Data protection: Eden AI will not store or use any data. Possibility to filter to use only GDPR engines.

‍

You can see Eden AI documentation here.