My Projects
A showcase of my recent work, personal projects, and collaborations.
PODLITE: AI-Powered Podcast Intelligence
Revolutionize how you consume podcasts. PODLITE is an AI application that generates intelligent summaries, identifies guests, and extracts key highlights directly from episode transcripts. Built with cutting-edge technologies like faster-whisper for accurate transcription and orchestrated via Langchain with high-speed Groq LLMs, it offers a streamlined way to gain insights from audio content.
RAGi: Agentic RAG Chatbot
An intelligent chatbot for deep document understanding. RAGi leverages agentic design and Retrieval Augmented Generation (RAG) to autonomously find, verify, and deliver accurate, citable answers from complex documents, preventing hallucinations. Interact via a Streamlit interface. Built with Langchain/LangGraph and high-speed Groq LLMs.
Smart Identity
The issue of handling paper-based documents poses a noteworthy challenge within the industry. This challenge not only necessitates a considerable amount of human workforce but also takes up a substantial amount of time, resulting in both frustration and inefficiency. The objective of this undertaking is to employ a CNN model for the categorization of ECOWAS ID cards.
Tomato ripeness detection in the fields
This project aims to develop an automated tomato ripeness detection system directly in the field using the state-of-the-art YOLO model, which enables accurate and efficient real-time crop monitoring to boost agricultural productivity while promoting sustainable farming practices.
Testimonial
This is what client think about me.
"I worked with Andriamarolahy R. for 1.5 years in a part-time capacity as a Junior Software Developer. During this time, he contributed to code implementation and revision in a methodologically complex innovation project, consistently demonstrating reliability and a solid grasp of best software engineering practices. His technical skills, particularly in Python (medical imaging algorithms, ML/AI, data visualization, data analysis, OOP), were at a mid-level when he joined, and he showed clear improvement over time. He was proactive in asking questions whenever clarification was needed, and he was always motivated and eager to learn. With his excellent work ethic and kind personality, he brought well-appreciated contributions to the project and team. I definitely recommend working with him."