ragas-evaluation

Building RAG and Agentic Applications with Haystack 2.0, RAGAS and LangGraph 1.0 published by Packt

RAG using LlamaIndex：Computer Network Q&A System powered by LlamaIndex | 基于 LlamaIndex 框架的计算机网络智能问答系统 - HyDE+混合检索 + vLLM 推理+Ragas评估

🔰 A Comprehensive RAG repository covering basic vanilla RAG techniques, advanced retrieval methods, hybrid search fusion approaches, hands-on reranking techniques with code + explanation 📚✨

Multi-agent LangGraph RAG for financial Q&A — 72.7% on FinanceBench under κ=0.932 calibrated judge. RBAC at the vector layer, multi-party HITL on high-stakes answers, self-hosted LLM observability. pip install financebench-rag-agent

Winning solution of Capital One Launchpad Hackathon 2025

An enterprise-grade, full-stack AI travel planner which provides data-driven itineraries for Lucknow, India and showcases production-ready architecture, combining a FastAPI backend with a Streamlit frontend. It leverages an advanced agentic RAG system, context-aware responses by integrating a local knowledge base with live, external APIs.

A curated collection of papers, frameworks, tools, and resources on Retrieval-Augmented Generation (RAG). Maintained for students of the Text Mining and Data Visualization course as a starting point for thesis research.

Hybrid retrieval-augmented generation(RAG) pipeline for financial document.

AI/ML Engineer Portfolio | Japanese RAG Production System (FastAPI + real evaluation) | Credit Card Fraud Detection (XGBoost + SHAP + Docker) | Japanese Sentiment Analysis (BERT) | Open to mid-level AI/ML roles

Universal Agent Evaluation Framework (UAEF) is a framework-agnostic evaluation system for AI agents. Invoke any agent and score it on multiple metrics spanning tool calling, response quality, safety, performance, and reasoning. Track experiments against baselines, catch regressions automatically, and get LLM-generated insights.

Autonomous multi-agent due-diligence desk — LangGraph orchestration, agentic hybrid RAG, MCP tools, and a self-improving LLM-Ops loop.

Intelligent document Q&A platform powered by Retrieval-Augmented Generation (RAG), hybrid search, reranking, and LLM-based reasoning.

Minimal RAG pipeline for Indian nutrition Q&A — Chroma + Groq + FastAPI, evaluated with RAGAS, containerized with CI/CD

Advanced RAG system with enhanced retrieval and error-handling capabilities. Implemented totally locally with open-source tools — LangGraph, Qdrant, Llama.cpp server, Qwen3-0.6B-UD-Q8_K_XL.gguf and MLflow server for observability.

LangGraph-orchestrated RAG multi-agent pipeline that routes queries to specialized agents. Modular design for ingestion, routing and evaluation.

Production RAG pipeline for F-16 technical manual using Docling, Qdrant, Ollama, and evaluation pipeline

Production-grade RAG Document Intelligence Platform — LangGraph Adaptive RAG + CRAG, LangSmith observability, RAGAS evaluation,Qdrant hybrid search (BGE dense + BM42 sparse + RRF), jinaai/jina-reranker-v1-tiny-en  re-ranking, FastAPI + Docker

This project integrates LangFlow as a backend API with a Streamlit frontend for a chatbot interface. It also includes RAGAS evaluation for measuring the performance of RAG (Retrieval-Augmented Generation) pipelines.

A high-performance Retrieval-Augmented Generation pipeline for technical Q&A workloads. Combines hybrid retrieval (dense + BM25), query expansion, Reciprocal Rank Fusion (RRF), and cross-encoder re-ranking to improve retrieval precision and answer grounding. Evaluated with Ragas, showing measurable gains in context recall and faithfulness.