DEV Community: chanveer singh

From First-Timer to Finisher: My Hacktoberfest 2026 Journey

chanveer singh — Thu, 15 Oct 2026 10:06:47 +0000

Another Hacktoberfest in the books! 🍂💻 I managed to complete my pull requests and officially earned my 2026 completion certificate. Here’s a quick look at what I built, the challenges I faced, and what I’m taking away from this year's event.

TrailPal Punjab: An Offline Open-Source AI Nature Guide That Gets You Off the Screen

chanveer singh — Mon, 12 Oct 2026 04:33:30 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

TrailPal Punjab is an offline "what's that?" app for walks. Snap a plant, bird or insect and a local open-weight model names it and gives a fun fact, checked against a local list of Punjab species. A daily quest ("find 3 things") nudges you to go outside, and once it's done the app tells you to put the phone away. The screen is the shortest part of the experience. Built for hikers, kids, students and anyone curious about the trees and birds around them.

Demo

screenshots

Code

chanveersinghdev / trailpal

🌿 TrailPal Punjab

Offline "what's that?" for the outdoors. Point your camera at a plant, bird or insect, get the name plus a fun fact from a local open-weight model. No internet, no cloud, no photos leave your device. A daily quest (find 3 things) gets you outside.

Run it

# 1. install Ollama: https://ollama.com
ollama pull gemma3:4b          # one-time download (~3.3 GB); works offline after
pip install -r requirements.txt
streamlit run app.py

Open on your phone via the "Network URL" Streamlit prints (same Wi-Fi/hotspot), or just run it on a laptop and carry it on a walk.

Open-source pieces

Gemma 3 (open-weight vision model) via Ollama (local inference)
Streamlit UI, Pillow, local JSON species list (data/species.json)
Swap the model by changing MODEL in app.py (e.g. qwen2.5vl:3b).

Add your own species

Edit data/species.json, no retraining needed.

View on GitHub

How I Built It

Gemma 3 (4B), an open-weight vision model, run locally with Ollama
Streamlit for a simple camera-friendly UI
A local species.json of Punjab plants and birds to ground answers and reduce hallucinations
JSON-mode prompts so the model returns name, type, confidence and a fact
Sound tab: describe a bird call in words and the model suggests likely birds

Why Does Open Innovation Matter?

Works with no signal. Trails don't have bars. After a one-time model download it runs fully offline.
Privacy. Photos never leave the device.
Free. No API key, no per-call cost, which matters for students.
Swappable and tunable. Change one line to try another model, or add local species to the JSON. A closed API can't be tuned to Punjab's trees and birds.

How It Went Outside

Prize Categories

Studymat

chanveer singh — Sat, 03 Oct 2026 08:32:42 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

StudyMate: An AI Study Partner That Tells You What to Do Next

What I Built

I built StudyMate, an AI study partner for a friend who is a real student. She has plenty of study material, but when she gets stuck on a topic she often doesn't know what to do next: re-read, watch a video, practice, or revise.

Most AI tools work like this: Ask → Get answer. Then the student is on their own again.

StudyMate works like this:

Ask → Understand → Practice → Revise → Improve

It looks at what the student asked and offers the right next actions.

Concept question ("Explain electromagnetic induction"): Explain simply, Use an analogy, Real-world example, Quiz me.
Numerical ("Calculate the induced emf…"): Give me a hint, Show formula, Solve step-by-step, Similar problem.
Revision: Quick revision, Flashcards, Common mistakes, Quiz, Exam practice.

The options are adaptive, not fixed. The same app gives different next steps depending on what the student is doing.

Demo

Video Demo

Screenshot

StudyMate's chat interface. After each answer, it offers adaptive next actions based on what the student asked.

Code

chanveersinghdev / Studymate

AI study assistant that explains topics, adapts to your goals and level (Beginner to Advanced), and remembers context so you don't repeat yourself. Built with FastAPI, Ollama Cloud, and GPT-OSS. Privacy-first: it only uses what you provide or allow it to remember. Get quizzes, follow-ups, and clear answers in your style.

StudyMate — Ollama Cloud Edition

Personalized AI study partner with contextual learning actions.

AI provider

This version uses Ollama Cloud by default. The default configurable model is gpt-oss:120b.

Setup

1. Backend

cd backend
python -m venv .venv
.venv\\Scripts\\activate
pip install -r requirements.txt
copy .env.example .env

Open backend/.env and add your Ollama Cloud API key:

AI_PROVIDER=ollama_cloud
OLLAMA_HOST=https://ollama.com
OLLAMA_API_KEY=YOUR_KEY_HERE
OLLAMA_MODEL=gpt-oss:120b

Then:

uvicorn app.main:app --reload --port 8000

Check:

http://127.0.0.1:8000/api/health

2. Frontend

In a second terminal:

cd frontend
npm install
npm run dev

Open the Vite URL shown in the terminal.

Included

Rounded Claude-inspired chat UI
Hover and message animations
Dark/light mode
Responsive layout
Context-aware study actions
Learning-phase detection
Ollama Cloud API integration
Configurable model
Server-side API key handling
Fallback UI when no key is configured

Security

Never commit backend/.env. It contains your private API key.

The React frontend does…

View on GitHub

The repo has the React + Vite frontend, the FastAPI backend, and a .env.example with setup instructions.

📧 Contact: chanveersinghdev@gmail.com

How I Built It

        Student (question / doubt)
                  │
                  ▼
         React + Vite (UI)
                  │
                  ▼
           FastAPI backend
                  │
                  ▼
      Context / prompt engine
                  │
                  ▼
   Ollama Cloud ─► gpt-oss:120b
                  │
                  ▼
     Answer + adaptive actions

Tech stack

Part	Tool
Frontend	React + Vite
Backend	FastAPI
AI	gpt-oss:120b (open-weight) via Ollama Cloud
Storage	SQL database for user data
Built with	Claude Code

Learning phases

StudyMate is designed around how people actually learn:

Discover → Understand → Practice → Revise → Exam prep

The prompt engine detects the question type and phase, then chooses which actions to show.

Why open-weight AI is the core

The AI is an open-weight model (gpt-oss:120b) running through Ollama Cloud, not a closed proprietary API. The learning logic is separated from the provider and model:

StudyMate learning logic → AI provider → Model

The model is set in .env, so I can switch models or providers, or move to local inference later, without rewriting the product. That means less vendor lock-in and more control over the AI layer.

Security

The Ollama API key stays on the FastAPI backend (.env). The browser never sees it, and only .env.example is committed to GitHub.

Honest about PYQs

StudyMate never calls AI-generated questions "PYQs." They are labelled Practice question. Real previous-year questions will come from a verified database (year + exam + subject + chapter), so students can trust what they study.

UI

I designed the interface like a real product: dark theme, rounded chat and composer, contextual action buttons, hover animations, chat history, and a responsive layout.

Challenges

Adaptive actions: making the options change correctly by question type (concept vs numerical vs revision) instead of showing the same buttons every time.
Keeping the key safe: routing every AI call through the backend so the Ollama key never reaches the browser.
Academic trust: separating AI-generated practice questions from real PYQs so the app never misleads a student.
Model independence: keeping the learning logic separate from the model so changing models doesn't mean a rewrite.

What's Next

PDF and notes upload with RAG, so students can ask questions about their own material
Verified PYQ database and NCERT integration, with chapter-wise and exam filters
Quiz engine, flashcards, progress tracking, and weak-topic detection
Web sources and book/resource recommendations
Streaming responses, image-based question solving, and a personalized learning profile

Final Thoughts

The biggest lesson was that a good study tool shouldn't stop at the answer. Knowing what to do next is what turns an answer into learning. StudyMate is the foundation for that, and I want to keep building it with my friend's feedback.

My First Experience with SigNoz: Exploring Open-Source Observability

chanveer singh — Wed, 15 Jul 2026 10:31:10 +0000

As part of my project preparation, I explored SigNoz, an open-source observability platform. The goal was to understand how developers can monitor applications using traces, metrics, and logs from a single dashboard.

Getting Started

I installed SigNoz locally and connected a sample application using OpenTelemetry. Within a few minutes, telemetry data started appearing in the dashboard, making it easy to verify that everything was working correctly.

Features I Explored
Distributed Traces to follow requests across services.
Metrics to monitor application performance.
Logs for troubleshooting and debugging.
Dashboards for visualizing system health.
Alerts to notify users when predefined conditions are met.
My Favorite Feature

The feature I liked the most was Distributed Tracing. It provides a clear view of how a request moves through an application and quickly identifies slow or failing components. This makes debugging much faster than relying only on logs.

Final Thoughts

SigNoz provides a powerful and developer-friendly observability solution. Its unified interface for traces, metrics, logs, and dashboards makes monitoring applications straightforward. Exploring SigNoz gave me a solid understanding of modern observability and prepared me for building larger projects with better monitoring from the start.