Terraform-based Infrastructure as Code (IaC) for deploying complete AWS backend services, integrated with Google's free-tier Gemini Pro and Gemini Embedding models for AI powered document querying including streamlit UI..

An Interactive Infinite Story Generation Framework Based on Multi-Agent

IAttorney is an intelligent legal assistant built using Flask, LangChain, FAISS, OpenAI, and a RAG (Retrieval-Augmented Generation) pipeline.

AI Assistant for FMBench (foundation model benchmarking tool)

A RAG agent using Google's ADK & Vertex AI that lets set up semantic search across documents in under 2 minutes. Features GCS integration and natural language querying

A Retrieval-Augmented Generation (RAG) system that leverages Google's Agent Development Kit (ADK) and Qdrant vector database via MCP server.

GovChat-NL is a Dutch government-focused fork of azure-search-openai-demo. It integrates ChatGPT-style Q&A with an app launcher for LLM-powered applications, designed for secure and shared use in the public sector.

Rag bot for Keploy Docs and Website

A RAG video chatbot to deliver accurate, context-aware answers. Users can upload videos, which are split into chunks and embedded into a vector database. When a question is asked, the chatbot retrieves relevant chunks using similarity search and generates response.

About A simple RAG (Retrieval-Augmented Generation) app built with Streamlit. Upload PDFs, ask questions, and get context-aware answers using Qdrant and Hugging Face Transformers.

A Streamlit-based Retrieval-Augmented Generation (RAG) application that enables searching within PDF files using Ollama and DeepSeek R1. It leverages FAISS for vector search, HuggingFace embeddings, and LangChain for document retrieval and response generation in Arabic.

A complete hierarchical corrective multi-agent Retrieval-Augmented Generation (RAG) stack designed to ingest MathWorks documentation and power an interactive troubleshooting assistant for MATLAB and Simulink users.

融合大模型推理与RAG检索增强的诈骗短信甄别系统

POC - Hybrid two phase RAG

AI chatbot for PDF documents

EfficienGPT is a quick-learning engine designed to optimize knowledge acquisition using the Pareto Principle (80/20 Rule). By leveraging Open Source LLMs, MongoDB Atlas and LangChain, it provides fast, insightful, and actionable learning experiences tailored to individual needs.

A ChatBot that can help you with your food choices anytime!!! DineBot leverages web scraping, embeddings, and a Retrieval-Augmented Generation (RAG) workflow to provide personalized food recommendations. Built with Streamlit, DineBot offers an interactive interface for users to explore menu options and receive tailored suggestions.

RAG Q&A App with LangChain, FAISS, and LLaMA 3

Chatbot for answering questions about the Systems Engineering program at Univalle Tuluá.

Integrated a real-time SLR system with a domain-specific LLM chatbot to enable natural, webcam-based communication for sign language users without the need for text or voice input.