Skip to content
View Karn2898's full-sized avatar
  • jalpaiguri , west bengal
  • 03:08 (UTC -12:00)

Highlights

  • Pro

Block or report Karn2898

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Karn2898/README.md

role: B.Tech ECE student & developer — Alipurduar Government Engineering and Management College (2023-2027)
focus: [AI & ML Engineering, MLOps, AI-Backend Engineering]
goal: AI/ML Engineer • MLOps Engineer • AI-Backend Engineer
experience: "ML Intern @ Unified Mentor — probabilistic decision models, AWS ML deployment"
status: "shipping agents, training models, breaking builds, fixing them again"

What I'm Building

🧩 Vertico — Full-Stack AI Coding Agent GitHub →

  • LangGraph orchestration + Gemini LLM for refactor & tool-calling
  • FastAPI + SQLModel + PostgreSQL + pgvector for session, chat, diff & RAG routes
  • VS Code / JetBrains extensions · CI/CD on a self-hosted Oracle Cloud runner

🌌 AuroraQ — Multimodal LLM App GitHub → · Demo →

  • Text, image & audio input across multi-turn conversations
  • Bearer-token auth, rate limiting, file-size validation
  • FastAPI, Google Gemini, SlowAPI, SQLite, Streamlit

🩺 RAG Medical Chatbot GitHub →

  • +40–60% response relevance over baseline QA
  • Embedding-retrieval-generation via Docker on Render/AWS, <1.5s latency

📚 RAG-Enhanced Language Model GitHub →

  • Vector DB + fine-tuned LLM retrieval-augmented generation
  • Optimized for low-latency, edge-deployable inference on Colab

🔧 Open Source — extra-org/extra PR #36 →

  • Merged a self-contained OpenAI-default test-fixture system

Stack

python · c · c++ · typescript · fastapi · langgraph · langchain · huggingface · pytorch · streamlit · react · mlflow · fastmcp · postgresql · pgvector · sqlite · aws · oracle cloud · docker · celery · redis · git · vscode · pycharm · linux · jupyter · postman · colab


📜 Certifications

OCI GenAI Pro Columbia ML freeCodeCamp


🐍 Contribution Snake


🔗 Connect



Pinned Loading

  1. Language_model_RAG Language_model_RAG Public

    A Retrieval-Augmented Generation (RAG) system that combines language models with external knowledge retrieval to provide accurate, context-aware responses.

    Python

  2. Multimodal_LLM Multimodal_LLM Public

    Python

  3. vertico vertico Public

    AI coding assistant to be used in IDE

    Python 1