langchain4j-aideepin

About langchain4j-aideepin

LangChain4j-AIDeepin is a comprehensive AI application platform designed to rapidly build intelligent business assistants. Built on Spring Boot, LangChain4j, and LangGraph4j for the backend and Vue 3 with Naive UI for the frontend, it integrates advanced capabilities including multi-character AI chat with streaming output, text-to-image generation and editing, and a robust knowledge base supporting both vector search and knowledge graph retrieval via RAG. The platform features a visual AI workflow editor with conditional branching and parallel execution for orchestrating complex tasks. It includes an MCP service marketplace to extend AI with external tools and data sources, plus full ASR and TTS support for flexible voice and text interactions with selectable AI voices. Unique long and short-term memory features automatically extract and store key information to enable personalized responses based on historical context. The system supports multiple model providers such as OpenAI, Qwen, SiliconFlow, Ollama, an

m

Published by

moyangzhan

Visit View Profile

README.md

View on GitHub

Getting Started

🇨🇳 中文文档 | English

LangChain4j-AIDeepin — AI application platform.

Integrates AI chat, knowledge base (RAG), workflow orchestration, long/short-term memory, MCP tools, and more — for rapidly building intelligent business assistants.

Demo: http://www.aideepin.com

Repository Structure

Directory	Description	Docs
server/	Backend service (Spring Boot + langchain4j + langgraph4j)	README
admin-web/	Admin dashboard (Vue 3 + Naive UI)	README
user-web/	User-facing web app (Vue 3 + Naive UI)	README

Quick Start

See Development Guide for secondary development. For deployment, see docker/README.md or each sub-project's README.

Features

Feature	Description
AI Chat	Multi-character (multi-conversation) with configurable prompts, models, and parameters. Streaming output
Image Generation	Text-to-image and image editing. Supports GPT-Image-2, DashScope Wanx, and more
Knowledge Base (RAG)	Supports both vector search and knowledge graph retrieval
AI Workflow	Visual editor with conditional branching, parallel execution, and built-in nodes for LLM calls, knowledge base queries, human feedback, and more
MCP Service Marketplace	Integrate MCP services to extend AI with external tools and data sources
ASR & TTS	Flexible text/voice input and output combinations (text⇄text, text⇄voice, voice⇄text, voice⇄voice), with selectable AI voice tones
Short & Long-term Memory	Automatically extracts and stores key information from conversations for personalized responses based on historical context
Storage	Local file storage, Alibaba Cloud OSS integration
Open API	RESTful API for Characters, Knowledge Bases, and Workflows — generate API keys and integrate with external systems. Supports streaming and blocking response modes

Integrated Platform Features

Model Platform	Chat	Image Generation	Image Recognition	Text-to-Speech	Speech Recognition
OpenAI	✓	✓	✓	✓	✓
Qwen	✓	✓	✓	✓	✓
SiliconFlow	✓	✓	✓	✓	✓
Ollama	✓
DeepSeek	✓

Screenshots


AI Chat	Image Generation

Knowledge Base	Workflow

⭐ Support the Project

If you find LangChain4j-AIDeepin useful, please consider:

Starring the repository on GitHub
Recommending it to others
Sharing your experience

❤️ Thanks to

Contributors

Infrastructure Sponsor:

Recommended Projects

Mango Finder — A local-first desktop app for semantic search across documents, images, and audio files using natural language, with cross-device search support. It helps you find information based on what you remember, not file names or folder structures.