A modular framework for building and deploying Retrieval-Augmented Generation (RAG) systems with built-in evaluation and monitoring.

Understand and build embedding models, focusing on word and sentence embeddings, dual encoder architectures. Learn to train embedding models using contrastive loss, implement them in semantic search and RAG systems.

RAG Gateway Service 🚪🤖: FastAPI gateway that auto-detects query topics using OpenAI embeddings 🧠🔍 and routes requests to topic-specific RAG agents 🎯, with fallback support and Docker-ready 🚀🐳.

Turn any LLM into a self-extending knowledge agent powered by a graph-structured memory - complete with PDF-to-graph ingestion, budget-aware optimisation, and dual-engine orchestration.

Experimenting with different kinds of RAGs Systems

The course provides a comprehensive guide to optimizing retrieval systems in large-scale RAG applications. It covers tokenization, vector quantization, and search optimization techniques to enhance search quality, reduce memory usage, and balance performance in vector search systems.

This project processes and retrieves information from PDF file or PDF collection. It leverages Qdrant as a vector database for similarity searches and employs a Retrieval-Augmented Generation (RAG).

Training Data Generator for SPLADE Model Fine-tuning

Implements a Retrieval-Augmented Generation (RAG) system.

Advanced Retrieval-Augmented Generation system supporting multimodal document processing (text, tables, images) with multiple reasoning strategies and comprehensive evaluation framework.