Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

Intuitive RAG system on top of LllamaIndex

This project aims to compare different Retrieval-Augmented Generation (RAG) frameworks in terms of speed and performance.

A simple AgenticAI RAG agent showcasing autonomous reasoning and decision-making by integrating thought, logic, and action in real-time tasks.

A RAG-powered customer support chatbot using LlamaIndex, Ollama, and Streamlit for efficient and accurate query responses.

This repository contains my personal documentation and learning journey through the Hugging Face Agents Course. I'm documenting my progress, notes, and implementations as I work through the course materials.

Using MLflow to deploy your RAG pipeline, using LLamaIndex, Langchain and Ollama/HuggingfaceLLMs/Groq

Knowledge Graph (Graph RAG) from Turkish News with LlamaIndex

Wikipedia Retrieval-Augmented Generation System with LlamaIndex and GPT-4o

RAG Document Query System with LlamaIndex

Ever wished you could chat with your PDFs like they're your personal sidekicks? Now you can! This wild project lets you ask your documents questions and get real-time answers. Powered by LlamaIndex and Next.js, it's basically turning your files into chatty little helpers. Let's talk docs!

Development of a AI chatbot (a desktop pet) with persistent & organic cognitive and memory system

🎸 Hands-on tutorial for building RAG applications with LlamaIndex

Experimenting with different kinds of RAGs Systems

Instantly access Anyparser's robust document processing and data extraction capabilities directly within your LlamaIndex workflows. Enhance your AI applications with superior content understanding and data quality.

a template for multi-agent collaboration using chainlit, llamaindex, autogen

Utilizes the Nike_Catalog document for answering queries regarding price, category, etc

A project demonstrating the ability to utilize Agentic AI workflows to perform analysis and discovery on aspects of US Healthcare Taxation Laws. Utilizes an underlying RAG framework for Response Generation. Also includes a comparison of LlamaIndex vs a custom framework that makes use of retrieval strategies like Hyde and Multi-Query Transformations

This project implements a modular and customizable Retrieval-Augmented Generation (RAG) pipeline, designed to enable question-answering and context-aware response generation using external document knowledge.