Yeshwanth Reddy Profile image

Yeshwanth Reddy

Yeshwanth is a senior data scientist with a strong focus on the research and implementation of cutting-edge technologies to solve problems in the ML and computer vision domains.

9 Posts

The Ultimate Guide to Assessing Table Extraction

Assess table extraction with metrics beyond accuracy. This guide covers essential criteria—row/column integrity, content similarity, and advanced metrics such as TEDS and GriTS—helping you gauge extraction quality effectively in real-world applications.

Beginner's guide to ChatGPT Post feature image

Beginner's guide to ChatGPT

Explore ChatGPT as we dive into over 50 questions across various topics to uncover its strengths and weaknesses.

Beginner's Guide to Ministral Post feature image

Beginner's Guide to Ministral

Explore Ministral as we dive into over 50 questions across various topics to uncover its strengths and weaknesses.

Avoiding Hallucinations: Using Confidence Scores to Trust Your LLM Post feature image

Avoiding Hallucinations: Using Confidence Scores to Trust Your LLM

Discover what causes LLMs to hallucinate, methods to measure these hallucinations, and effective strategies to overcome them in this comprehensive guide.

Fine-Tuning Vision Language Models (VLMs) for Data Extraction Post feature image

Fine-Tuning Vision Language Models (VLMs) for Data Extraction

Fine-tune Vision Language Models (VLMs) effectively for document data extraction in this comprehensive tutorial. Learn the step-by-step process, best practices, and key considerations to optimize performance for your specific use cases.

Best PDF Parser for RAG Apps: A Comprehensive Guide Post feature image

Best PDF Parser for RAG Apps: A Comprehensive Guide

Discover the best PDF parsers for RAG systems, tackling complex layouts, tables, and images.

Table Extraction using LLMs: Unlocking Structured Data from Documents Post feature image

Table Extraction using LLMs: Unlocking Structured Data from Documents

Nanonets evaluates multiple LLM APIs for table extraction, comparing their performance and summarizing the challenges, advantages, and drawbacks of each model.

Best Vision Language Models for Document Data Extraction Post feature image

Best Vision Language Models for Document Data Extraction

Bridging Images and Text - a Survey of VLMs Post feature image

Bridging Images and Text - a Survey of VLMs

Distilling insights from over 50 arXiv papers, let's explore the current state-of-the-art models, with dedicated discussions on documents based models, datasets and benchmarks.