moyangzhan/langchain4j-aideepin

基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)

What it solves

LangChain4j-AIDeepin is an AI application platform designed to help users rapidly build intelligent business assistants. It provides a comprehensive suite of tools for integrating AI chat, knowledge bases, and complex workflows into a business environment.

How it works

The project is built on a backend powered by Spring Boot, LangChain4j, and LangGraph4j. It features a separate admin dashboard and a user-facing web application. The platform integrates with various model platforms (such as OpenAI, Qwen, and DeepSeek) to provide an AI-powered experience across multiple modalities

Who it’s for

Developers and businesses looking to create customized AI assistants with integrated RAG, memory, and visual workflow orchestration without starting from scratch.

Highlights

  • AI Chat & Memory: Supports multi-character conversations with streaming output and both short- and long-term memory for personalized responses.
  • RAG Capabilities: A knowledge base that supports both vector search and knowledge graph retrieval.
  • Visual Workflow Editor: A visual editor for creating AI workflows with conditional branching, parallel execution, and built-in nodes for LLM calls and human feedback.
  • Multimodal Support: Integration of ASR (Automatic Speech Recognition) and TTS (Text-to-Speech) for voice interactions, as well as text-to-image generation and editing.
  • MCP Service Marketplace: Ability to integrate MCP services to extend AI capabilities with external tools and data sources.
  • Open API: RESTful APIs for Characters, Knowledge Bases, and Workflows for external system integration.