Mistral Introduces New OCR API That Can Convert PDF Documents Into AI-Ready Format

Mistral launched the Mistral Optical Character Recognition (OCR) software programming interface (API) on Thursday. The synthetic intelligence (AI) mannequin is able to analysing and processing PDF paperwork and changing it into an AI-ready textual content format akin to Markdown or uncooked textual content file. The software is able to extracting knowledge from PDFs to make them digestible for AI fashions. The Paris-based AI agency claimed that the Mistral OCR API will permit builders to construct AI functions for PDF information in addition to permit them to create datasets to coach new AI fashions.

Mistral OCR API Launched

PDF paperwork pose a novel problem for AI fashions. The content material on this file format can’t be accessed by massive language fashions (LLMs) utilizing conventional Retrieval-Augmented Technology (RAG) methods as the info can’t be processed by them. For instance, when you ask an AI software to scan via PDF paperwork in your laptop computer to discover a piece of knowledge, it would battle to take action.

Because of this builders constructing AI functions will probably be restricted in providing PDF-analysis functionality. Whereas Google’s NotebookLM, Adobe’s AI assistant, and several other different instruments use specialised OCR instruments to beat this problem, builders within the open-source neighborhood would not have entry to a high-efficiency software.

Mistral OCR API solves this problem by permitting builders to extract PDF knowledge into an AI-ready format. The corporate claims in a newsroom post that the software can perceive separate components in paperwork, together with media, textual content, tables, and equations with excessive accuracy. As soon as analysed, it might extract and current the data within the Markdown or a uncooked textual content file format.

AI fashions can then use this extracted textual content as enter and RAG methods can simply entry them and reply queries about them. “Mistral OCR excels in understanding advanced doc components, together with interleaved imagery, mathematical expressions, tables, and superior layouts akin to LaTeX formatting. The mannequin allows deeper understanding of wealthy paperwork akin to scientific papers with charts, graphs, equations and figures,” the put up acknowledged.

The corporate claimed that the Mistral OCR can course of as much as 2,000 pages per minute on a single node. The API additionally lets builders use the doc as a immediate, and chain outputs to construct operate calling instruments and AI brokers.

Primarily based on inner testing, the Mistral OCR outperformed fashions akin to Google Doc AI, Azure OCR, and GPT-4o model 2024-11-20 for “text-only” paperwork. It additionally outperformed Google and Azure in multilingual capabilities.

These concerned about making an attempt out the aptitude of the mannequin can go to Mistral’s Le Chat platform. The API may be accessed from la Plateforme.