Universal MCP memory service with semantic search, multi-client support, and autonomous consolidation for Claude Desktop, VS Code, and 13+ AI applications

Semantic Retrieval Engine for Contrasting Ideas and Opposing Viewpoints.

Multimodal AI assistant with RAG, web search & email generation – Built for Esprit

Powerful book recommender using Large Language Models (LLMs) and semantic vector search. It analyzes book descriptions to recommend contextually and emotionally similar titles. Includes zero-shot classification and an interactive Gradio interface for seamless user experience.

A simple RAG pipeline for PDF based QnA

AI-powered book recommendation system using semantic search, sentiment analysis, and interactive web interface. Find books through natural language queries and emotional tone filtering.

A Retrieval-Augmented Generation (RAG) Web App powered by LangChain and Flask. Live Demo: https://rag-chatbot-1090137452187.us-west1.run.app/

Agentic RAG System – A multi-agent Retrieval-Augmented Generation (RAG) system built with CrewAI for business intelligence and document analysis. It integrates ChromaDB for document storage and retrieval, real-time web search, and specialized agents for code execution and visualization, enabling automated trend analysis and insights generation

A fully local RAG pipeline that answers natural language questions about movie reviews. Uses Ollama for embeddings + local LLM, Chroma for the vector store, and LangChain to retrieve, summarize, and generate answers.

AI-powered support copilot for ticket classification and query resolution. RAG, Chroma DB, Streamlit. Atlan AI Engineer Internship.

Local RAG chatbot that answers questions about pizza restaurant reviews using LangChain, Ollama, and Chroma vector database - fully offline with no API dependencies