Mindee introduces docTI, which needs no data model training

With docTI (Document Tailored Intelligence), the document processing startup Mindee (YC W21) is launching an AI-powered Optical Character Recognition (OCR) tool that leverages their knowledge of Deep Learning, Computer Vision, and Large Language Models (LLMs) and eliminates the tedious process of data collection, annotation, and model training.

Mindee, a developer platform for AI document processing, announced March 28 that it has launched docTI, its new AI-powered document processing tool. docTI (Document Tailored Intelligence) enables the processing of any document type in any language without the need for data model training.

According to Mindee, data scientists spend up to 39% of their time on data preparation, including tasks such as cleaning and annotating data before it can be used to train a model. With docTI, Mindee is changing this, enabling product managers to create custom document processing APIs, test them, and integrate them in minutes rather than months.

Jonathan Grandperrin, CEO of Mindee, commented: “Mindee’s core vision is to deliver solutions that align perfectly with the specific needs of our clients. With docTI, we’re bringing a one-of-a-kind expertise of deep learning, computer vision, and large language models (LLMs) to provide the most adaptable, dynamic, and high-performing document processing tool on the market.”

docTI builds on Mindee’s initial offering, a comprehensive API catalog for processing documents such as invoices, identity documents and more, and extends that capability to any document type.

Headquartered in Paris, France, Mindee specializes in advanced Optical Character Recognition (OCR) APIs, enabling easy integration of Intelligent Document Processing (IDP) capabilities into any application or system.

You can find more information here.

📨Get IDP industry news, distilled into 5 minutes or less, once a week. Delivered straight to your inbox:

Share This Post
Have your say!