Knowledge Base Management Based on RAG (Retrieval-Augmented Generation)

Features • Quick Start • Deployment • Architecture • Development • Contributing • DeepWiki

📖 Introduction

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology that helps build intelligent Q&A systems based on your own knowledge base. By combining document retrieval and large language models, it achieves accurate and reliable knowledge-based question answering services.

The system supports multiple LLM deployment options, including cloud services like OpenAI and DeepSeek, as well as local model deployment through Ollama, meeting privacy and cost requirements in different scenarios.

It also provides OpenAPI interfaces for convenient knowledge base access via API calls.

✨ Features

• 📚 Intelligent Document Management

  • Support for multiple document formats (PDF, DOCX, Markdown, Text)
  • Automatic document chunking and vectorization
  • Support for async document processing and incremental updates

• 🤖 Advanced Dialogue Engine

  • Precise retrieval and generation based on RAG
  • Support for multi-turn contextual dialogue
  • Support for reference citations in conversations

• 🎯 Robust Architecture

  • Frontend-backend separation design
  • Distributed file storage
  • High-performance vector database: Support for ChromaDB, Qdrant with easy switching through Factory pattern

🖼️ Screenshots

Knowledge Base Management Dashboard

Document Processing Dashboard

Document List

Intelligent Chat Interface with References

API Key Management

API Reference

Project Flowchart

graph TB
    %% Role Definitions
    client["Caller/User"]
    open_api["Open API"]
    
    subgraph import_process["Document Ingestion Process"]
        direction TB
        %% File Storage and Document Processing Flow
        docs["Document Input<br/>(PDF/MD/TXT/DOCX)"]
        job_id["Return Job ID"]
        
        nfs["NFS"]

        subgraph async_process["Asynchronous Document Processing"]
            direction TB
            preprocess["Document Preprocessing<br/>(Text Extraction/Cleaning)"]
            split["Text Splitting<br/>(Segmentation/Overlap)"]
            
            subgraph embedding_process["Embedding Service"]
                direction LR
                embedding_api["Embedding API"] --> embedding_server["Embedding Server"]
            end
            
            store[(Vector Database)]
            
            %% Internal Flow of Asynchronous Processing
            preprocess --> split
            split --> embedding_api
            embedding_server --> store
        end
        
        subgraph job_query["Job Status Query"]
            direction TB
            job_status["Job Status<br/>(Processing/Completed/Failed)"]
        end
    end
    
    %% Query Service Flow  
    subgraph query_process["Query Service"]
        direction LR
        user_history["User History"] --> query["User Query<br/>(Based on User History)"]
        query --> query_embed["Query Embedding"]
        query_embed --> retrieve["Vector Retrieval"]
        retrieve --> rerank["Re-ranking<br/>(Cross-Encoder)"]
        rerank --> context["Context Assembly"]
        context --> llm["LLM Generation"]
        llm --> response["Final Response"]
        query -.-> rerank
    end
    
    %% Main Flow Connections
    client --> |"1.Upload Document"| docs
    docs --> |"2.Generate"| job_id
    docs --> |"3a.Trigger"| async_process
    job_id --> |"3b.Return"| client
    docs --> nfs
    nfs --> preprocess

    %% Open API Retrieval Flow
    open_api --> |"Retrieve Context"| retrieval_service["Retrieval Service"]
    retrieval_service --> |"Access"| store
    retrieval_service --> |"Return Context"| open_api

    %% Status Query Flow
    client --> |"4.Poll"| job_status
    job_status --> |"5.Return Progress"| client
    
    %% Database connects to Query Service
    store --> retrieve

    %% Style Definitions (Adjusted to match GitHub theme colors)
    classDef process fill:#d1ecf1,stroke:#0077b6,stroke-width:1px
    classDef database fill:#e2eafc,stroke:#003566,stroke-width:1px
    classDef input fill:#caf0f8,stroke:#0077b6,stroke-width:1px
    classDef output fill:#ffc8dd,stroke:#d00000,stroke-width:1px
    classDef rerank fill:#cdb4db,stroke:#5a189a,stroke-width:1px
    classDef async fill:#f8edeb,stroke:#7f5539,stroke-width:1px,stroke-dasharray: 5 5
    classDef actor fill:#fefae0,stroke:#606c38,stroke-width:1px
    classDef jobQuery fill:#ffedd8,stroke:#ca6702,stroke-width:1px
    classDef queryProcess fill:#d8f3dc,stroke:#40916c,stroke-width:1px
    classDef embeddingService fill:#ffe5d9,stroke:#9d0208,stroke-width:1px
    classDef importProcess fill:#e5e5e5,stroke:#495057,stroke-width:1px

    %% Applying classes to nodes
    class docs,query,retrieval_service input
    class preprocess,split,query_embed,retrieve,context,llm process
    class store,nfs database
    class response,job_id,job_status output
    class rerank rerank
    class async_process async
    class client,open_api actor
    class job_query jobQuery
    style query_process fill:#d8f3dc,stroke:#40916c,stroke-width:1px
    style embedding_process fill:#ffe5d9,stroke:#9d0208,stroke-width:1px
    style import_process fill:#e5e5e5,stroke:#495057,stroke-width:1px
    style job_query fill:#ffedd8,stroke:#ca6702,stroke-width:1px

🚀 Quick Start

Prerequisites

• Docker & Docker Compose v2.0+
• Node.js 18+
• Python 3.9+
• 8GB+ RAM

Installation

1. Clone the repository

   git clone https://github.com/rag-web-ui/rag-web-ui.git
   cd rag-web-ui

2. Configure environment variables

You can check the details in the configuration table below.

cp .env.example .env

3. Start services(development server)

   docker compose up -d --build

Verification

Access the following URLs after service startup:

• 🌐 Frontend UI: http://127.0.0.1.nip.io
• 📚 API Documentation: http://127.0.0.1.nip.io/redoc
• 💾 MinIO Console: http://127.0.0.1.nip.io:9001

🏗️ Architecture

Backend Stack

• 🐍 Python FastAPI: High-performance async web framework
• 🗄️ MySQL + ChromaDB: Relational + Vector databases
• 📦 MinIO: Distributed object storage
• 🔗 Langchain: LLM application framework
• 🔒 JWT + OAuth2: Authentication

Frontend Stack

• ⚛️ Next.js 14: React framework
• 📘 TypeScript: Type safety
• 🎨 Tailwind CSS: Utility-first CSS
• 🎯 Shadcn/UI: High-quality components
• 🤖 Vercel AI SDK: AI integration

📈 Performance Optimization

The system is optimized in the following aspects:

• ⚡️ Incremental document processing and async chunking
• 🔄 Streaming responses and real-time feedback
• 📑 Vector database performance tuning
• 🎯 Distributed task processing

📖 Development Guide

docker compose -f docker-compose.dev.yml up -d --build

🔧 Configuration

Core Configuration

LLM Configuration

Embedding Configuration

Vector Database Configuration

Object Storage Configuration

Other Configuration

🤝 Contributing

We welcome community contributions!

Contribution Process

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit changes (git commit -m 'Add some AmazingFeature')
4. Push to branch (git push origin feature/AmazingFeature)
5. Create a Pull Request

Development Guidelines

• Follow Python PEP 8 coding standards
• Follow Conventional Commits

🚧 Roadmap

• Knowledge Base API Integration
• Workflow By Natural Language
• Multi-path Retrieval
• Support Multiple Models
• Support Multiple Vector Databases

🔧 Troubleshooting

For common issues and solutions, please refer to our Troubleshooting Guide.

📄 License

This project is licensed under the Apache-2.0 License

Note

This project is for learning and sharing RAG knowledge only. Please do not use it for commercial purposes. It is not ready for production use and is still under active development.

🙏 Acknowledgments

Thanks to these open source projects:

• FastAPI
• Langchain
• Next.js
• ChromaDB