Podcast Summary & Q&A App is project takes podcast episodes from the Podcast Index, converts the audio into text, summarizes the content, generates an image based on the summary, translates the summary into French, and allows users to ask questions about the episode. ElevenLabs, HuggingFace, Replicate services are used

The LinkedIn Profile Search Assistant is a tool designed to streamline the process of finding the most relevant LinkedIn profiles based on company information provided through Google search results. This service automates the task of identifying and selecting the appropriate LinkedIn account, saving time and ensuring accuracy

This Java Spring Boot service leverages TogetherAI's advanced models to convert image and text inputs into PlantUML diagrams

The AI Video Insights Assistant is a backend service that uses advanced AI orchestration to analyze YouTube video content and accurately answer user questions. Built on LangChain4j or Spring AI, it leverages embeddings and similarity search for precise responses and includes fallback options for comprehensive coverage.

Museo Insight is a virtual museum guide offering rich insights into artworks. Built with Java 21, Spring Boot 3.3.3, and LangChain4J, it integrates the MET Museum API for easy searches and image access. AI-driven descriptions reveal historical, cultural, and visual details, plus artist background and creation year for each piece.

LangChain4j Neo4j Graph RAG - Movies Search Demo. An AI-powered movie database application built with Java 21, Spring Boot 3.3.3, and Neo4j. The app uses LangChain4j to enable natural language queries, providing personalized recommendations, interactive graph visualizations, and dynamic data exploration.

A collection of demonstrations showcasing different patterns for implementing multi-agent workflows using LangGraph. Each example highlights specific orchestration approaches to help developers understand and build collaborative AI systems.

A self-reflective and adaptive RAG system that dynamically routes queries between web search and vector retrieval, assesses document relevance, checks for hallucinations, and ensures answer quality using a graph-based flow architecture.

A showcase implementation demonstrating how to build an intelligent Q&A system using LangGraph and Neo4j Graph Database. This project combines the power of Large Language Models (LLMs) with graph database capabilities to answer questions about movie data.

This application is a full-stack document indexing and retrieval system that allows users to upload documents, index their content, and perform natural language queries against the indexed documents. It utilizes LlamaIndex, OpenAI embeddings, and a modern React frontend to provide an interactive experience for semantic search and document retrieval