Tenzin Lhakpa

AI Engineer specializing in Generative AI, LLMs, Multi-modal Learning, AI Agents, and RAG Systems, driving innovative solutions at the intersection of NLP, computer vision, and advanced machine learning.

Page Views: web counter

Featured Work

🤖RestroBot: AI Chatbot for Future Restaurants

A smart RAG based virtual assistant for restaurants built with GPT-4 and advanced conversational AI, RestroBot handles reservations and orders with the efficiency of a machine and the courtesy of your best staff member.

  • Can handle multiple request from customer
  • Consistent and accurate service
  • Large Language Models (LLMs)
  • Tools: Python, PyTorch, LangChain, GPT-4 API, Pinecone, OpenAIEmbeddings, SQLite
Visit GitHub Repo
Project Screenshot

⚙️Rotatory Machinery Fault Detection

A machine learning model to detect mechanical faults in rotatory machines using the vibration signal generated by a rotatory machine for heavy industries.

  • 98% accuracy in fault detection
  • Deployed on Machine Motoring Systems, LLC
  • Tools: Python, PyTorch, AWS, Pandas, Numpy, Matplotlib
Visit GitHub Repo
Project Screenshot

📚Student's Grade Predictor

An intelligent system that predicts student performance using machine learning algorithms and historical academic data.

  • Advanced prediction algorithms
  • Comprehensive data analysis
  • Tools: Python, Pandas, SQLite, Matplotlib, Numpy
Visit GitHub Repo
Project Screenshot

🗃️PDF Figure Caption Extractor

A Machine Learning based tool to extract figures and their associated captions from PDF documents. Particularly useful for developing LLMs.

  • Automatically identifies figures, diagrams, and plots within PDF documents
  • Uses computer vision techniques to detect figure boundaries
  • Intelligently pairs figures with their corresponding captions
  • Maintains the relationship between figures and their descriptions
  • Tools: Python, Numpy, OpenCV, PIL (Python Imaging Library), Selenium, lxml
Visit GitHub Repo
Project Screenshot

📚PDFs and Books Harvester

A specialized tool designed to facilitate the collection of large-scale textual data for training and fine-tuning Large Language Models (LLMs).

  • Takes a search term and automatically generates download links from Library Genesis across multiple pages
  • Downloads hundreds of books in parallel with built-in error handling
  • Fully automates the book collection pipeline from search to download
  • Tools: Python, BeautifulSoup4, ThreadPoolExecutor, HTML
Visit GitHub Repo
Project Screenshot

Publications

EndoAssistant

Submitted to ICLR 2025

An AI Assistant for Endoscopy Applications that leverages advanced machine learning techniques to assist medical professionals in endoscopic procedures. The system provides real-time analysis, anomaly detection, and procedural guidance to enhance diagnostic accuracy and treatment outcomes.

Keywords:
Computer Vision Medical AI Deep Learning
Read Paper
EndoAssistant Visualization

Let's Connect

Tenzin Lhakpa

I'm passionate about advancing the field of AI and Machine Learning through meaningful collaboration, with a focus on building practical solutions that solve real-world challenges. Whether you're working on neural architecture design, exploring applications in computer vision, developing ML pipelines, building Retrieval-Augmented Generation (RAG) systems, or implementing Generative AI solutions, I'd love to connect.

My expertise spans from traditional statistical learning to cutting-edge large language models and GenAI applications, with hands-on experience in designing RAG architectures that enhance AI's contextual understanding and reliability. I'm committed to creating AI solutions that deliver tangible impact across industries.