Skip to content
View Rahul2512Chauhan's full-sized avatar

Highlights

  • Pro

Block or report Rahul2512Chauhan

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Rahul2512Chauhan/README.md
Typing SVG
🎓 IIT Roorkee '27  ·  📍 Dehradun, India  ·  🧠 AI Tinkerer

Image

✨ a little about me ✨

I'm that person who gets way too excited about making AI do useful things.

Currently obsessed with multi-agent systems, RAG pipelines, and shipping stuff that actually works.

I believe in: building > talking, shipping > perfecting, learning > pretending


🌱 where i've been growing

🚀 Nitrolens AI (Silicon Valley) — built multi-agent co-pilots
💊 kokoro.doctor — shipped production features in React & Django
🦜 Ragas — open source contributor (RAG evaluation)

🛠️ things i've made with love


🔍 RAG-EngineX 📚 Auto-Researcher
smart retrieval pipeline AI research assistant
reranking · observability · eval search · summarize · export
📦 Reverse Supply Chain 🧪 + more experiments
ML-powered returns optimizer always cooking something

💭 tools i think in

python · typescript · react · next.js · langchain · langgraph

pinecone · faiss · django · postgresql · hugging face


📬 let's be friends?

Portfolio GitHub LinkedIn


Footer
Profile views



thanks for stopping by 💗

Pinned Loading

  1. RAG-EngineX RAG-EngineX Public

    RAG-EngineX: Designed and built a modular, plug-and-play RAG framework supporting customizable chunking, embedding, vector DBs, and reranking strategies. Integrated LangSmith and RAGAS for observab…

    Python 1

  2. Auto-Researcher-LLM-Powered-Research-Assistant Auto-Researcher-LLM-Powered-Research-Assistant Public

    Automates the research process using a locally-run Zephyr 7B model to extract insights, generate research questions, and summarize papers through a Streamlit interface.

    Python 1

  3. TinyLlama-LoRA-on-Alpaca TinyLlama-LoRA-on-Alpaca Public

    Fine-tuned TinyLlama on Alpaca with LoRA — and here’s how it learned basic instructions on my Mac M2

    Jupyter Notebook 1

  4. ai-resume-roaster ai-resume-roaster Public

    will write later 😎

    Python 1

  5. ragas ragas Public

    Forked from vibrantlabsai/ragas

    Supercharge Your LLM Application Evaluations 🚀

    Python