Retrieval-augmented generation (RAG) is a technique that improves large language models by retrieving relevant information from external sources and using it to generate more accurate and context-aware responses.
A RAG system combines information retrieval with a language model. It is commonly used in AI assistants, search systems, document question answering, and applications that need access to private or frequently updated information.
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
Samples showing architectural patterns for Modular RAG using Spring AI and Ollama.
Sample Spring AI Application with several use cases
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
Java 23, SpringBoot 3.4.1 Examples using Deep Learning 4 Java & LangChain4J for Generative AI using ChatGPT LLM, RAG and other open source LLMs. Sentiment Analysis, Application Context based ChatBots. Custom Data Handling. LLMs - GPT 3.5 / 4o, Gemini Pro 1.5, Claude 3, Llama 3.1, Phi-3, Gemma 2, Falcon 3, Qwen 2.5, Mistral Nemo, Wizard Math
LiSSA: A Framework for Generic Traceability Link Recovery
Retrieval Augmented Generation, Function Calling and Code Generation on GitHub Projects with Java
Enterprise AI-powered customer support platform built with Java 21, Spring Boot 4.1.0, Spring AI 2.0.0, Kafka, Metadata-aware RAG, and PostgreSQL (pgvector).
Aether — Private local AI OS for desktop. Smart assistant (Alfred) powered by Ollama + cloud fallback, with PDF RAG, web search, and memory. Built with Java + Spring Boot.
Samples showing a Java Spring Backend Application powered by Ollama's Generative AI and LLMs using Spring AI
OAuth2 Authorization Server with MariaDB, Docker OpenTelemetry LGTM, and Redis Integrations with Spring Boot 4, Java 25 and Docker. Integration Tests with Testcontainers and unit Tests with Junit 5, and Mockito
面向中小企业的开源私有化知识库：单实例部署、数据本地可控、LLM 中立。LangChain4j RAG、PgVector 混合检索、Docker 一键部署。
A chat-based AI travel planning assistant that helps users create personalized travel itineraries using real-time data from TripAdvisor
Production-style RAG learning project — trace the full pipeline from ingestion to hybrid retrieval, RRF, reranking, and LLM answers. Java 21, Spring Boot, pgvector & Docker.
Retrieval Augmented Generation using LangChain4j on Apache Karaf with LocalAI
Memory and RAG runtime for long-running AI agents: hybrid recall, tiered memory, and checkpointed task recovery.
Source-grounded chunk validation as a primitive. Spring Boot service exposing two interfaces (LLM-to-LLM and human-facing) over the same hierarchical document model.
A self-hosted Agent RAG knowledge base for campus documents, featuring hybrid retrieval, async ETL, rerank fallback, and evaluable answer grounding.（一款用于校园文档的自托管 Agent RAG 知识库，具备混合检索、异步 ETL、重排回退以及可评估的答案溯源能力。）
Dubbo 技术知识检索与故障排查实验RAG项目
A Spring Boot application that leverages Retrieval-Augmented Generation (RAG) to provide ABNT (Brazilian Technical Standards Association) bibliographic reference formatting assistance using OpenAI's GPT-4 model and ChromaDB for vector storage.