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

Mistral launched the Mistral Optical Character Recognition (OCR) utility 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 comparable 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 enable builders to construct AI purposes for PDF recordsdata in addition to enable them to create datasets to coach new AI fashions.

Mistral OCR API Introduced

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

This implies that builders constructing AI purposes will likely be restricted in providing PDF-analysis functionality. While Google’s NotebookLM, Adobe’s AI assistant, and a number of other different instruments use specialised OCR instruments to beat this problem, builders within the open-source group 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 firm 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. Once analysed, it may 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 comparable to LaTeX formatting. The mannequin permits deeper understanding of wealthy paperwork comparable to scientific papers with charts, graphs, equations and figures,” the publish acknowledged.

The firm 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.

Based on inside testing, the Mistral OCR outperformed fashions comparable to Google Document AI, Azure OCR, and GPT-4o model 2024-11-20 for “text-only” paperwork. It additionally outperformed Google and Azure in multilingual capabilities.

Those concerned with attempting out the aptitude of the mannequin can go to Mistral’s Le Chat platform. The API will be accessed from la Plateforme.