Welcome to my personal blog! 🚀
This is a space where I share technical insights, experiments, and tutorials based on my work in Computer Vision and Large Language Models (LLMs). The blog reflects my journey, experiments, and learnings in building AI-powered systems that blend perception and reasoning.
- Object Detection – real-time and batch-level detection pipelines
- Image Segmentation – instance and semantic segmentation for various domains
- Image Processing – classical techniques and pre/post-processing for CV models
- ChatGPT / Gemini – custom prompt engineering and advanced use cases
- RAG (Retrieval-Augmented Generation) – multi-source document QA and summarization
- Agents – ReAct-style agents that reason, act, and interact with tools
- Vector Databases – like ChromaDB, Pinecone, Qdrant for semantic retrieval
- Graph Databases – for storing and reasoning over structured knowledge