#rag-pipeline

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

Two-pipeline Agentic RAG system with side-by-side comparison. Custom sequential agent pipeline vs LlamaIndex inspired ReAct reasoning loop, with full chunk, trace, token and timing visibility for fine-tuning.

AI Video Intelligence & Knowledge Synthesis Platform built with LangChain,LangSmith, ChromaDB, Whisper, and LLMs.

A Privacy-Preserving Edge AI System for Trustworthy Safety Compliance

A Rust-based PostgreSQL extension that makes relational query optimizers natively aware of LLM token costs, semantic entropy, and latency budgets.

Personalized AI assistant capable of handling automated conversations across WhatsApp and Gmail using LLM APIs, Retrieval-Augmented Generation (RAG), semantic search, conversation memory, and real-time information retrieval.

This a POC on Customer Support Agent built using RAG and LLM. The below course was used as reference to learn and implement the same: -https://www.udemy.com/course/build-a-customer-support-ai-agent-with-langchain/learn/lecture/56401085?start=1#reviews The course uses legacy LangChain version. The code repository uses Modern LangChain version.

AI-powered career intelligence platform built with FastAPI, PostgreSQL, pgvector, and Ollama. Analyze resumes, identify skill gaps, generate learning roadmaps, prepare for interviews, and chat with an intelligent career assistant using Retrieval-Augmented Generation (RAG).

A RAG system built with Laravel 13, PostgreSQL 16 + pgvector, and OpenAI / Ollama. Upload PDFs/DOCX — text is chunked and embedded, then you can ask questions with source-cited answers. Hybrid search, MMR reranking, term aliases, runtime-tunable settings, Vue 3 SPA.

Hands-on implementation of Retrieval-Augmented Generation (RAG) using vector databases, embeddings, semantic search, and Anthropic Claude.

Archive of small projects and exercises done while following the [AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents] Udemy Course

Digital Garage Enterprise

Mellow is a character-based, RAG-optimized AI conversational discovery engine. Built on Bun & React, it fuses live web scraping, API data streams, and Web3 wallet authentication into a stunning, minimalist Claude-inspired interface.

An Advanced RAG Document Search Agent built with FastAPI, LangChain, and Chroma DB. Features hybrid │ search (BM25 + Vector), FlashRank reranking, real-time SSE log streaming, and dynamic web search .