RAG Applications for Document Understanding

RAG Projects Overview

Project	Focus	Description
Agentic RAG	Agentic retrieval	RAG implementation with Agno and GPT-5
Agentic RAG with Web Search	Hybrid search	Advanced RAG with CrewAI, Qdrant, and Exa for web + document hybrid search
Resume Optimizer	Document enhancement	AI-powered resume optimization and improvement tool
LlamaIndex RAG Starter	Getting started	LlamaIndex + Nebius RAG starter template
PDF RAG Analyzer	PDF chat	Multi-PDF conversational analysis system
Qwen3 RAG Chat	Streamlit UI	PDF chatbot interface built with Streamlit and Qwen3
Chat with Code	Code documents	Conversational code explorer and documentation assistant
Gemma3 OCR	OCR + RAG	OCR-based document and image processor using Gemma3
Nvidia Nemotron OCR	OCR + parsing	OCR and image parsing using Nvidia Nemotron-Nano-V2-12b
Contextual AI RAG	Enterprise RAG	Managed datastores with quality evaluation for production use
Advanced RAG with Reranking	Production pipeline	Contextual retrieval, Qdrant hybrid search, reranking, streaming answers, ingestion, and citations
Simple RAG	Quick start	Basic RAG implementation with Nebius for rapid prototyping

How to Run a RAG Project

Most RAG projects share a similar setup flow:

Enter the project directory

cd rag_apps/<project_name>

Configure your environment and indexing strategy

cp .env.example .env

Many RAG projects require embedding model keys (e.g., OpenAI, Nebius) and a vector database connection (e.g., Qdrant).

Install and run

pip install -r requirements.txt
python main.py

Some projects use Streamlit for the front end. Run with:

streamlit run app.py

If you are building a RAG pipeline for the first time, try the LlamaIndex RAG Starter or Simple RAG first. They require minimal configuration and clearly illustrate how documents are ingested and queried.

Get Started

App Categories

Contributing

RAG Projects Overview

How to Run a RAG Project

​RAG Projects Overview

​How to Run a RAG Project

RAG Projects Overview

How to Run a RAG Project