#retrieval-augmented-generation

企业级 AI Agent 平台 | Spring Boot 3 + LangChain4j | ReAct 推理 + 多路召回 RAG + 语义缓存 + 多智能体协作

ESG knowledge graph + RAG agent. Turn long-form sustainability disclosures into cited answers, extracted entities, and a reviewable graph of evidence.

Hands-on Generative AI: 15 RAG modules from document loaders to guardrails, plus Papeer — a research paper assistant with citations and claim verification. Also LangGraph workflows and LangSmith tracing.

Trustworthy AI Knowledge Workbench — Verifiable RAG with citation tracking, document-grounded review, and self-contained desktop mode. Windows / macOS / Linux / Android / iOS.

AI document assistant with a production RAG pipeline — hybrid BM25 + semantic search, cross-encoder reranking, and streaming answers. Built with FastAPI, Streamlit, ChromaDB, and DeepSeek LLM. Fully Dockerized and deployed on Railway.

Agent + Multimodal RAG 全栈学习项目：LangGraph PAE/ReAct、Multi-Query、BM25 + pgvector 混合检索、RAG-Fusion/RRF、MinerU/OCR/ASR、evidence 引用与 HITL；React + Spring Boot + FastAPI。

Self-hosted knowledge base for AI agents: ingest Markdown into Qdrant with H1-H...-aware chunking, hybrid (dense+sparse) search and cross-encoder reranking.

AI Research Agent 2026 🔍 - Autonomous Deep Web Explorer & Adversarial Synthesis

Self-healing RAG on n8n with LLM-as-judge eval, drift detection, investigator agent, and canary A/B deploys.

A reference n8n workflow that turns a folder of business documents into a chat agent that only answers from those documents. Retrieval-augmented, grounded, with refusal when the answer is not in the indexed sources.

AI agent for Azure DevOps work item analysis, sprint readiness, RAG-based code understanding, and developer task planning.

A small, working Retrieval-Augmented Generation API (FastAPI + Chroma + Claude). Ingest documents, ask questions, get answers grounded only in your data with cited sources.

🧠 A persistent memory RAG chatbot that never forgets. Uses Phi-3-mini LLM, ChromaDB vector database, and Ebbinghaus memory decay curves.

On-Premise RAG (продвинутая версия): vLLM/Ollama + bge-m3 + reranker + Qdrant + hybrid (BM25+RRF) + PDR + Basic Auth + Prometheus/Grafana + локальная оценка. Запускается на Ollama без GPU. Тех-задача Petrel AI (Astana Hub).

A practical, first-principles handbook on production RAG & agentic systems — RU/EN/SK, built with Docusaurus.

A RAG pipeline that reads PDFs and answers questions using LangChain and ChromaDB. The Streamlit app uses Qwen/Qwen2.5-7B-Instruct while a quantized Zephyr-7B LLM is used in the notebook.

RAG over industrial maintenance manuals that abstains with a calibrated error guarantee: conformal risk control for selective QA, a from-scratch agent, and a prompt-injection suite enforced in CI.

Enterprise RAG platform for secure document intelligence using hybrid retrieval, reranking, Gemini LLM, RBAC, HITL, citations, and web search.

Cost-aware agentic RAG with iterative multi-hop retrieval, benchmarked against 4 baselines using an independent LLM judge on MultiHop-RAG.

A Research Cortex. A research companion for Claude. Your library, notes & memory stay on your machine; answers cited from your own library; 30+ specialist skills; auto cross-pollination across papers, meetings, ideas, notes & journal; weekly self-review that drafts improvements for your approval. Reasoning runs on the Claude API.

AI agent that answers questions about YouTube tutorials and your own codebase — available as a Chrome extension, desktop app, and web app.

🧠 RepoMind — A RAG-powered chatbot that lets you ask natural-language questions about any GitHub repository, with answers grounded in the actual source code and cited by file & line number.

An AI-powered YouTube Q&A system that lets users chat with video content using RAG pipelines, LangChain, FastAPI, and vector search.

12-question wizard that recommends an optimal RAG architecture (Standard / Graph / Agentic) with an AI-evaluated pipeline.

Federal Acquisition Regulation Retrieval-Augmented Generation (RAG) Chatbot

Production-shaped agentic RAG: LangGraph plan->act->verify agent + hybrid retrieval + guardrails + an eval gate in CI. Provider-agnostic; runs offline with no keys.

🏥 AI-powered Clinical Document RAG Engine — Ask questions about medical documents, get precise answers with citations. 86% retrieval accuracy. Free LLM support (Gemini/Groq/Claude).

And end to end RAG-based medical application (medibot) - Groq LLM, Langchain & Pinecone Vector Database.

Agentic AI portfolio: planning agents, multi-agent orchestration, RAG, memory systems, semantic routing, evaluation pipelines, and business workflow automation.

HarryBot is a retrieval-based chatbot that answers Harry Potter questions using FAISS vector search, conversational memory, similarity thresholding, and a Streamlit interface.

Identify bird species from images along with audio and explore them with AI-powered insights.

AI-powered e-commerce assistant using Gemini, RAG pipeline, FAISS vector search, and Streamlit for interactive product recommendations.

Agente de RR. HH. con LangGraph, RAG, FAISS, Groq y Llama 3.3 para responder consultas internas, solicitar información adicional y generar tickets de soporte.

Document-Driven Aviation RAG Assistant built using FastAPI, FAISS, BM25, Gemini API, and Streamlit. Provides grounded answers from aviation manuals with citations, hallucination prevention, and hybrid retrieval.

Reproducibility materials for: A Multi-Source RAG Framework for Intelligent Agent Orchestration in Enterprise CRM Systems (IEEE Access 2026)

AI chatbot that searches documents and answers questions using relevant context.

Enterprise document assistant built with ASP.NET Core, FastAPI, PostgreSQL, Redis, Docker Compose, semantic search and a local RAG workflow.

A Retrieval-Augmented Generation (RAG) chatbot for answering LPDP scholarship questions using Hybrid Retrieval, Cross-Encoder Reranking, and Llama 3.3.

Local-first RAG assistant for contracts — grounded answers with citations, agentic tool-use, hybrid search + reranking, and an evaluation harness. Python · Ollama · pgvector · FastAPI.

Production-style RAG operations console with grounded retrieval, document ingestion, evaluation, cost analysis, and bias-aware LLM judging.