#information-retrieval

A 4-stage adversarial research auditor that fetches papers from arXiv & HuggingFace, extracts claims, and uses DeepSeek-R1 to verify them against raw abstracts.A self-correcting research & paper digest pipeline powered by local LLMs & reasoning agents

An Agentic RAG-powered chatbot delivering intelligent, fact-grounded and context-aware answers for the DIEM Department at the University of Salerno.

🤖 An advanced, policy-compliant RAG-powered Internal Knowledge Assistant for TechNova. Built with LangChain, Chroma DB, and Llama 3.3 (Groq). Features strict source grounding, 100% retrieval precision, comprehensive factual citations, automated evaluation pipelines, and a dynamic multi-category Gradio chat interface. 🚀

A fully local, zero-cost RAG chatbot for mac.du.ac.in — built with FAISS, Llama 3.2 3B, FastAPI, and React. CPU-only, 8GB RAM, zero cloud dependency.

End-to-end RAG system built from scratch with recursive chunking, persistent indexing, vector + BM25 hybrid retrieval, evaluation, FastAPI, Docker, and AWS deployment testing.

A hybrid AI candidate ranking system combining Latent Semantic Analysis (LSA) embeddings, structural requirements, and behavioral signals to rank 100K profiles in under 5 seconds. Built for the Redrob AI Hackathon

🧠 HireGraph — AI-powered multi-signal candidate ranking engine | INDIA.RUNS Hackathon 2026 | Beats keyword filters using semantic embeddings + career trajectory + behavioral intelligence