https://github.com/403errors/403errors
Config files for my GitHub profile.
https://github.com/403errors/403errors
config github-config
Last synced: 14 days ago
JSON representation
Config files for my GitHub profile.
- Host: GitHub
- URL: https://github.com/403errors/403errors
- Owner: 403errors
- Created: 2022-03-27T07:20:39.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2025-11-29T14:08:40.000Z (3 months ago)
- Last Synced: 2025-12-01T15:58:59.946Z (3 months ago)
- Topics: config, github-config
- Language: Jupyter Notebook
- Homepage:
- Size: 44.9 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 👋 Hey, I'm Sameer Verma
### AI Prompt Engineer | Machine Learning & Full-Stack Developer | Building Intelligent, Autonomous Systems
---
## 🚀 About Me
I'm a passionate developer and **B.Tech. graduate from IIT Madras**, specializing in **AI Full-Stack Web Development**, **Machine Learning** and **Natural Language Processing**,. I thrive on creating intelligent, autonomous systems and building scalable applications that solve real-world challenges with innovative solutions.
### 🎯 Quick Facts
- 🎓 **Education:** B.Tech from IIT Madras
- 💼 **Current Role:** AI Researcher
---
## 💻 Tech Stack & Expertise
Programming Languages
Frontend Development
Backend Development
Machine Learning & AI
Tools & Platforms
---
## 🚀 Featured Projects
### 🧠 [RepoMind](https://github.com/403errors/repomind)
[](https://repomind-ai.vercel.app)
[](https://github.com/403errors/repomind)
An open-source, AI-powered application using **Agentic CAG** to chat with any public GitHub repository or developer profile, offering deep code analysis, visual architecture maps, and security audits.
**🎯 Key Highlights:**
- **Context-Aware Engine (CAG):** Intelligently selects relevant code snippets instead of loading entire repositories
- **Visual Architecture Maps:** Auto-generates Mermaid flowcharts from complex code logic for instant visualization
- **Deep Profile Intelligence:** Analyzes coding styles, commit patterns, and developer habits across entire portfolios
- **Zero-Config Security Audits:** Detects vulnerabilities with AI-powered triage and actionable fix recommendations
- **Mobile-First Design:** The only tool in its class optimized for on-the-go code reviews
**💡 Why It Stands Out:**
- ✅ Works instantly on any public repo—no installation, login, or GitHub App required
- ✅ Uses Context Augmented Generation (CAG) vs traditional RAG for superior code understanding
- ✅ Generates interactive visuals instead of text walls
- ✅ Analyzes developers, not just code
**🛠️ Tech Stack:** Next.js • Google Gemini • Vercel KV • TypeScript • Tailwind CSS • Framer Motion
---
### 🗣️ [EchoTasks](https://github.com/403errors/echotasks)
[](https://echotasks-ai.vercel.app)
[](https://github.com/403errors/echotasks)
A voice-first to-do list application for intuitive task management entirely through natural language commands, powered by **Deepgram** for real-time transcription and **Groq's qwen-2.5-32b** for AI command analysis.
**🎯 Key Highlights:**
- **Voice-First Interface:** Create, update, and manage tasks using natural language—no typing required
- **Real-Time Transcription:** Leverages Deepgram's blazing-fast speech-to-text for instant feedback
- **AI-Powered Command Analysis:** Understands complex intents like "remind me to buy groceries tomorrow at 5pm"
- **Client-Side Intelligence:** Local models for instant priority detection and date parsing
- **Seamless UX:** Combines Groq's speed with intuitive animations for a smooth experience
**📊 Impact:**
- ⚡ 95%+ transcription accuracy with sub-second latency
- 🎯 Handles 20+ natural language command variations
- 📱 Fully responsive with touch and voice support
**🛠️ Tech Stack:** Next.js • React • Deepgram • Groq (qwen-2.5-32b) • ShadCN/UI • Tailwind CSS • Framer Motion
---
### 🛣️ [RoadSafetyAI](https://github.com/403errors/roadsafetyai)
[](https://studio--studio-7508206524-6fb40.us-central1.hosted.app)
[](https://github.com/403errors/roadsafetyai)
An advanced web application providing expert-level road safety intervention recommendations using **Retrieval-Augmented Generation (RAG)** architecture with Google's Gemini LLM and Vertex AI Search.
**🎯 Key Highlights:**
- **RAG Architecture:** Grounded recommendations from a curated knowledge base of road safety research
- **AI Orchestration:** Leverages Google Genkit to manage the entire AI workflow seamlessly
- **Evidence-Based Advice:** Provides detailed rationale with direct citations from authoritative source documents
- **Optimized Query Flow:** Brainstorms multiple search queries and executes parallel searches for reduced latency
- **Domain Expertise:** Built on real-world road safety data and best practices
**📊 Impact:**
- 📚 Processes 100+ authoritative safety documents
- ⚡ 60% faster response time through parallel search optimization
- 🎯 Provides source-backed recommendations with verifiable citations
**🛠️ Tech Stack:** Next.js • React • TypeScript • Tailwind CSS • ShadCN UI • Google Genkit • Gemini 2.5 Flash • Vertex AI Search • Firebase App Hosting
---
### 🏥 [CancerCareAI](https://github.com/403errors/CancerCareAI)
[](https://github.com/403errors/CancerCareAI)
[](https://colab.research.google.com/drive/13bzx0MyOojzwq6f8PcUOp5o_LvXt6B1E?usp=sharing)
An AI-powered system for extracting cancer-related information from patient Electronic Health Record (EHR) notes, focusing on information retrieval and structured medical data extraction.
**🎯 Key Highlights:**
- **Multi-Stage Information Retrieval:** Combines keyword search (BM25) with semantic search (Sentence Transformers, CrossEncoder)
- **LLM-Based Data Extraction:** Uses quantized Qwen/Qwen2.5-7B-Instruct-1M for structured JSON output
- **Robust Error Handling:** Implements advanced mechanisms for JSONDecodeError recovery
- **GPU Efficiency:** Utilizes 4-bit quantization for running 7B parameter models on T4 GPUs
- **Medical-Grade Accuracy:** Designed for precision in clinical information extraction
**📊 Impact:**
- 📄 Processes complex medical notes with 90%+ extraction accuracy
- ⚡ Runs efficiently on consumer GPUs through quantization
- 🎯 Extracts structured data from unstructured clinical text
**🛠️ Tech Stack:** Python • NLTK • BM25 • Sentence Transformers • CrossEncoder • Qwen LLM • bitsandbytes • PyTorch
---
### 🎥 [TubeQuery](https://github.com/403errors/TubeQuery)
[](https://github.com/403errors/TubeQuery)
[](https://www.kaggle.com/code/sitama/tubequery)
An LLM-powered tool that enables users to extract information, transcribe, and ask questions about YouTube video content, providing a seamless way to interact with video transcripts.
**🎯 Key Highlights:**
- **Speech-to-Text:** Utilizes OpenAI Whisper for high-quality, multilingual audio transcription
- **Audio Extraction:** Employs FFMPEG for efficient audio extraction from video streams
- **NLP-Driven Querying:** Leverages Hugging Face Transformers for natural language understanding and query resolution
- **Scalable Design:** Architected for multilingual transcription, advanced summarization, and AI-powered Q&A
**📊 Impact:**
- 🌐 Supports 50+ languages through Whisper
- 📝 Generates accurate transcripts and summaries
- 🎯 Enables semantic search across video content
**🛠️ Tech Stack:** Python • OpenAI Whisper • Hugging Face Transformers • FFMPEG • NLP
---
## 🏆 Machine Learning Competitions
| Competition | Rank | Achievement |
|------------|------|-------------|
| **ML for Marine Autonomy** (OCEANA IIT-Madras) | 🥉 **3rd Place** | Developed a **CNN-based Convolutional Autoencoder** for efficient underwater image transmission with **85%+ reconstruction accuracy**. Optimized for bandwidth-constrained marine environments. |
| **Pravartak Datathon** (Research Park, IIT-Madras) | 🏅 **4th Place** | Built a hypertuned regression model for US house price prediction achieving **92% MSE reduction**. Used advanced EDA, spatial analysis (**GeoPandas**, **Matplotlib**), and feature engineering. |
---
## 💭 My Development Philosophy
I believe in building AI systems that are:
- **🎯 Purpose-Driven:** Every line of code should solve a real problem
- **🧠 Intelligently Designed:** Leverage AI where it adds genuine value, not as a buzzword
- **⚡ Performance-First:** Optimize for speed and efficiency without sacrificing functionality
- **📱 User-Centric:** Complex technology should feel simple and intuitive
- **🔓 Open & Collaborative:** Knowledge grows when shared
> **"The best AI is invisible—it just works."**
My approach combines deep technical expertise with a focus on practical impact. Whether it's prompt engineering, building RAG systems, or creating voice-first interfaces, I prioritize solutions that are both innovative and production-ready.
---
## 🤝 Let's Connect
I'm always excited to collaborate on interesting projects, discuss AI/ML innovations, or explore new opportunities!
### 📬 Get In Touch
- 💼 **LinkedIn:** [linkedin.com/in/127001-sameer](http://linkedin.com/in/127001-sameer)
- 📧 **Email:** [pieisnot22by7@gmail.com](mailto:pieisnot22by7@gmail.com)
- ⏱️ **Response Time:** Within 24 hours
- 🎯 **Open To:** Hackathons • ML Competitions • Collaborative Projects • AI Consulting
### 🌟 Currently Seeking
- 🏆 **Hackathons & Competitions:** Love building innovative solutions under pressure
- 🤝 **Open Source Collaborations:** Interested in contributing to impactful AI/ML projects
- 💡 **Freelance Opportunities:** Prompt engineering, RAG systems, and AI automation
- 🎓 **Knowledge Sharing:** Speaking engagements, workshops, or technical writing
---
### ⭐ If you find my projects interesting, consider starring them!
**💻 Happy Coding! 🚀**
---
Built with ❤️ by Sameer Verma | Last Updated: November 2025