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

酒店评论分析与智能问答系统——基于花园酒店近三年上千条真实住客评论，提供评论查询、分析与智能问答服务。

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.

🤖 Production-ready samples for building multi-modal AI agents that understand images, documents, videos, and text using Amazon Bedrock and Strands Agents. Features Claude integration, MCP tools, streaming responses, and enterprise-grade architecture.

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.

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 🚀🐳.

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.

Four Tests Standard (4TS) - Vendor-neutral specification for verifiable AI governance

This project implements a Retrieval-Augmented Generation (RAG) based chatbot designed to handle university-related queries using natural language understanding. It combines semantic search with generative AI to provide precise, context-aware answers to students, faculty, and visitors.

Experimenting with different kinds of RAGs 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).

Production-grade RAG system for Singapore government documents with OpenAI integration

Training Data Generator for SPLADE Model Fine-tuning

This repository covers extensive tutorials on how to integrate LangSmith with LangChain with LangGraph to incorporate observability, monitoring, alerting, evaluation, etc. within complex LLM workflows and applications.

A comprehensive surveillance-grade framework for monitoring the Information Labyrinth. Implements HLSP and AAIL protocols under the 2030 Directive logic.

Decision-level observability for LLM pipelines, making system behavior explainable even when no outputs exist.

🚀 Complete AI Development Toolkit Template - Add RAG, MCP, and AI assistance to any project in 2 minutes

A comprehensive Asset Administrative Shell (AAS) data modeling platform for Quality Infrastructure systems. Features AASX package processing, digital twin management, AI-powered analytics with RAG, and multi-format data transformation capabilities.

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