AI-RAG-Assistant-Chatbot icon indicating copy to clipboard operation
AI-RAG-Assistant-Chatbot copied to clipboard

Published 4 months ago • verified publisher icon hoangsonww
→

Metadata

👨🏻‍💻 Meet Lumina – my personal chatbot assistant designed to answer any questions, either about me or any other topics. Powered by Retrieval-Augmented Generation (RAG), LangChain, kNN cosine simila...

My Personal AI Assistant Project - Lumina 👨🏻‍💻

David Nguyen's Personal AI Assistant - Lumina is a full-stack web application that allows users to ask questions about David Nguyen, as well as any other topics, and receive instant, personalized responses powered by state‑of‑the‑art AI & RAG. Users can log in to save their conversation history or continue as guests. The app uses modern technologies and provides a sleek, responsive user interface with intuitive UX and lots of animations. 🚀

Lumina Logo

Table of Contents

  • Live App
    • Key Technologies
  • Features
  • Architecture
    • High-Level System Architecture
    • RAG Flow
    • Data Flow Architecture
  • Detailed Architecture Documentation
  • Setup & Installation
    • Backend Setup
    • Frontend Setup
    • AI/ML Setup
  • Deployment
    • Current Deployment (Vercel)
    • Docker Deployment
    • AWS Production Deployment
  • Usage
  • Streaming Responses
    • How It Works
    • Technical Implementation
    • Key Features
    • API Endpoints
    • Event Types
    • Error Recovery
  • User Interface
  • API Endpoints
    • Authentication
    • Conversations
    • Chat
    • Swagger API Documentation
  • Project Structure
  • Agentic AI Pipeline
  • Dockerization
  • OpenAPI Specification
  • CI / CD with GitHub Actions
  • Testing
  • Contributing
  • License

Live App

[!IMPORTANT] Currently, the app is deployed live on Vercel at: https://lumina-david.vercel.app/. Feel free to check it out!

For the backend (with Swagger docs), it is deployed live also on Vercel at: https://ai-assistant-chatbot-server.vercel.app/.

Alternatively, the backup app is deployed live on Netlify at: https://lumina-ai-chatbot.netlify.app/.

[!TIP] Go straight to https://lumina-david.vercel.app/chat if you want to chat with the AI right away!

Key Technologies

Vite Node.js Express TypeScript JavaScript React MongoDB Pinecone JWT Material UI Vercel Netlify Swagger RAG OpenAI Google AI Python Docker Jupyter Notebook AWS Terraform Docker Compose Nodemon ESLint Git GitHub GitHub Actions Jest

Features

  • AI Chatbot: Ask questions about David Nguyen and general topics; receive responses from an AI.
  • User Authentication: Sign up, log in, and log out using JWT authentication.
  • Conversation History: Save, retrieve, rename, and search past conversations (only for authenticated users).
  • Auto-Generated Titles: AI automatically generates concise, descriptive titles for new conversations based on the first message.
  • Grounded Knowledge Base: RAG (Retrieval-Augmented Generation) with Pinecone and inline citations; knowledge is managed via CLI (REPL or one-off commands).
  • Dynamic Responses: AI-generated responses with markdown formatting for rich text.
  • Interactive Chat: Real-time chat interface with smooth animations and transitions.
  • Reset Password: Verify email and reset a user's password.
  • Lightning-Fast Development: Built with Vite for instant HMR and optimized production builds.
  • Responsive UI: Built with React and Material‑UI (MUI) with a fully responsive, modern, and animated interface.
  • Landing Page: A dynamic landing page with animations, feature cards, and call-to-action buttons.
  • Guest Mode: Users may interact with the AI assistant as a guest, though conversations will not be saved.
  • Conversation Search: Search through conversation titles and messages to find relevant discussions.
  • Collapsible Sidebar: A sidebar that displays conversation history, allowing users to switch between conversations easily.
  • Reinforced Learning from Human Feedback (RLHF): Implement a feedback loop to continuously improve the AI's responses based on user interactions.
  • Dark/Light Mode: Users can toggle between dark and light themes, with the preference stored in local storage.
  • Enterprise-Grade Deployment: Deployed with blue/green & canary deployment strategies on AWS & Terraform for zero-downtime updates.
  • Comprehensive Testing: Unit and integration tests for both frontend and backend using Jest and React Testing Library.
  • CI/CD Pipeline: Automated testing and deployment using GitHub Actions.

Architecture

The project follows a modern, full-stack architecture with clear separation of concerns across three main layers:

  • Frontend Layer: A React application built with TypeScript and Material-UI (MUI) that provides:

    • Modern, animated user interface with responsive design
    • Client-side routing with React Router
    • JWT-based authentication and authorization
    • Real-time chat interface with markdown support
    • Theme toggling (dark/light mode)
    • Collapsible sidebar for conversation history

  • Backend Layer: An Express.js server written in TypeScript that handles:

    • RESTful API endpoints for authentication and data management
    • JWT token generation and validation
    • User authentication (signup, login, password reset)
    • Conversation management (CRUD operations)
    • Integration with AI services
    • Request validation and error handling

  • AI/ML Layer: RAG (Retrieval-Augmented Generation) implementation that includes:

    • Retrieval: Vector similarity search using Pinecone
    • Augmentation: Context building with conversation history
    • Generation: Response generation using Google Gemini AI
    • Knowledge Storage: CLI-driven ingestion into Pinecone with citations returned in responses

For detailed architecture documentation, including component diagrams, data flows, and deployment strategies, see ARCHITECTURE.md.

High-Level System Architecture

graph TB
    subgraph "Client Layer"
        Browser[Web Browser]
        React[React Application]
    end

    subgraph "API Gateway"
        LB[Load Balancer / CDN]
    end

    subgraph "Application Layer"
        API[Express.js API Server]
        Auth[Authentication Service]
        Chat[Chat Service]
        Conv[Conversation Service]
    end

    subgraph "AI/ML Layer"
        RAG[RAG Pipeline]
        Gemini[Google Gemini AI]
        Embed[Embedding Service]
    end

    subgraph "Data Layer"
        MongoDB[(MongoDB)]
        Pinecone[(Pinecone Vector DB)]
    end

    Browser --> React
    React --> LB
    LB --> API

    API --> Auth
    API --> Chat
    API --> Conv

    Chat --> RAG
    RAG --> Embed
    RAG --> Gemini
    RAG --> Pinecone

    Auth --> MongoDB
    Conv --> MongoDB
    Chat --> MongoDB

    style React fill:#4285F4
    style API fill:#339933
    style MongoDB fill:#47A248
    style Pinecone fill:#FF6F61
    style Gemini fill:#4285F4

RAG (Retrieval-Augmented Generation) Flow

sequenceDiagram
    participant User
    participant Frontend
    participant Backend
    participant Pinecone
    participant Gemini
    participant MongoDB

    User->>Frontend: Send chat message
    Frontend->>Backend: POST /api/chat/auth
    Backend->>MongoDB: Fetch conversation history
    MongoDB-->>Backend: Previous messages

    Note over Backend,Pinecone: Retrieval Phase
    Backend->>Pinecone: Generate embedding & search
    Pinecone-->>Backend: Top-K relevant documents

    Note over Backend,Gemini: Augmentation Phase
    Backend->>Backend: Build augmented context
    Backend->>Gemini: Send enriched prompt

    Note over Gemini: Generation Phase
    Gemini->>Gemini: Generate response
    Gemini-->>Backend: AI response + citations

    Backend->>MongoDB: Save message & sources
    MongoDB-->>Backend: Saved
    Backend-->>Frontend: Return AI response
    Frontend-->>User: Display response

Data Flow Architecture

flowchart LR
    subgraph "Frontend"
        UI[User Interface]
        State[State Management]
        API_Client[API Client]
    end

    subgraph "Backend API"
        Routes[Route Handlers]
        Middleware[Auth Middleware]
        Services[Business Logic]
    end

    subgraph "Data Sources"
        MongoDB[(MongoDB)]
        Pinecone[(Pinecone)]
        Gemini[Gemini API]
    end

    UI --> State
    State --> API_Client
    API_Client -.HTTP/REST.-> Routes
    Routes --> Middleware
    Middleware --> Services

    Services --> MongoDB
    Services --> Pinecone
    Services --> Gemini

    MongoDB -.Data.-> Services
    Pinecone -.Vectors.-> Services
    Gemini -.AI Response.-> Services

    Services -.JSON.-> Routes
    Routes -.Response.-> API_Client
    API_Client --> State
    State --> UI

    style UI fill:#4285F4
    style Services fill:#339933
    style MongoDB fill:#47A248
    style Pinecone fill:#FF6F61
    style Gemini fill:#4285F4

[!NOTE] These diagrams provide a high-level overview of the system architecture. For detailed component interactions, database schemas, deployment strategies, and security architecture, please refer to ARCHITECTURE.md.

Detailed Architecture Documentation

For comprehensive architecture documentation including:

  • Detailed component diagrams and interactions
  • Database schema and data models
  • Security architecture and authentication flows
  • Deployment strategies (Docker, AWS, Terraform)
  • Performance optimization and scalability
  • Monitoring and observability
  • Disaster recovery and backup strategies

Please see ARCHITECTURE.md

Setup & Installation

Backend Setup

  1. Clone the repository:

    git clone https://github.com/hoangsonww/AI-Assistant-Chatbot.git
cd AI-Assistant-Chatbot/server

  2. Install dependencies:

    npm install

  3. Environment Variables:
    Create a .env file in the server folder with the following (adjust values as needed):

    PORT=5000
MONGODB_URI=mongodb://localhost:27017/ai-assistant
JWT_SECRET=your_jwt_secret_here
GOOGLE_AI_API_KEY=your_google_ai_api_key_here
PINECONE_API_KEY=your_pinecone_api_key_here
PINECONE_INDEX_NAME=lumina-index

  4. Run the server in development mode:

    npm run dev

    This uses nodemon with ts-node to watch for file changes.

Frontend Setup

  1. Navigate to the client folder:

    cd ../client

  2. Install dependencies:

    npm install

  3. Run the frontend development server:

    npm start

    The app will run on http://localhost:3000 (or any other port you've specified in the .env file's PORT key).

AI/ML Setup

  1. Install necessary Node.js packages:

    npm install

  2. Ingest knowledge into Pinecone with the CLI (run from server/):

    npm run knowledge:repl

    Or run a single upsert command (use --external-id to update later):

    npm run knowledge:upsert -- \
  --title "Resume 2025" \
  --file ./knowledge/resume.txt \
  --type resume \
  --tags "resume,profile" \
  --external-id "resume-2025"

  3. Use the REPL to edit or delete sources (edit <id>, delete <id>) as your profile changes.

  4. Ensure you ingest at least one knowledge source before using the chatbot so responses can be grounded and cited.

Deployment

Current Deployment (Vercel)

The application is currently deployed on Vercel with the following setup:

Deployment Architecture

graph TB
    subgraph "Client Devices"
        Browser[Web Browser]
        Mobile[Mobile Browser]
    end
    
    subgraph "CDN Layer"
        Vercel[Vercel Edge Network]
        Netlify[Netlify CDN - Backup]
    end
    
    subgraph "Frontend Deployment"
        FrontendVercel[React App on Vercel]
        FrontendNetlify[React App on Netlify]
        StaticAssets[Static Assets]
    end
    
    subgraph "Backend Deployment"
        BackendVercel[Express API on Vercel]
        ServerlessFunctions[Serverless Functions]
    end
    
    subgraph "External Services"
        MongoDB[(MongoDB Atlas)]
        Pinecone[(Pinecone Vector DB)]
        GeminiAPI[Google Gemini AI API]
    end
    
    subgraph "CI/CD Pipeline"
        GitHub[GitHub Repository]
        GitHubActions[GitHub Actions]
        AutoDeploy[Auto Deploy on Push]
    end
    
    subgraph "Monitoring & Analytics"
        VercelAnalytics[Vercel Analytics]
        Logs[Application Logs]
    end
    
    Browser --> Vercel
    Mobile --> Vercel
    Vercel --> FrontendVercel
    Netlify --> FrontendNetlify
    
    FrontendVercel --> StaticAssets
    FrontendVercel --> BackendVercel
    FrontendNetlify --> BackendVercel
    
    BackendVercel --> ServerlessFunctions
    ServerlessFunctions --> MongoDB
    ServerlessFunctions --> Pinecone
    ServerlessFunctions --> GeminiAPI
    
    GitHub --> GitHubActions
    GitHubActions --> AutoDeploy
    AutoDeploy --> Vercel
    AutoDeploy --> Netlify
    
    BackendVercel --> VercelAnalytics
    BackendVercel --> Logs
    FrontendVercel --> VercelAnalytics
    
    style Browser fill:#4285F4
    style Vercel fill:#000000
    style FrontendVercel fill:#61DAFB
    style BackendVercel fill:#339933
    style MongoDB fill:#47A248
    style Pinecone fill:#FF6F61
    style GeminiAPI fill:#4285F4
    style GitHub fill:#181717

Docker Deployment

Run the entire application stack locally using Docker:

# Build and start all services
docker-compose up --build

# Or run in detached mode
docker-compose up -d

# Stop all services
docker-compose down

This will start:

  • Frontend on http://localhost:3000
  • Backend on http://localhost:5000
  • MongoDB on localhost:27017

AWS Production Deployment

For production-grade AWS deployment with high availability and scalability:

# Navigate to infrastructure directory
cd terraform/

# Initialize Terraform
terraform init

# Review deployment plan
terraform plan

# Deploy infrastructure
terraform apply

# Or use provided scripts
cd ../aws/scripts/
./deploy-production.sh

AWS Infrastructure includes:

  • ECS/Fargate for container orchestration
  • Application Load Balancer for traffic distribution
  • DocumentDB (MongoDB-compatible) for database
  • ElastiCache (Redis) for caching
  • CloudFront CDN for static asset delivery
  • CloudWatch for monitoring and logging
  • Auto-scaling groups for high availability
  • Multi-AZ deployment for fault tolerance

See aws/README.md and terraform/README.md for detailed deployment instructions.

Usage

  • Landing Page:
    The landing page provides an overview of the app’s features and two main actions: Create Account (for new users) and Continue as Guest.

  • Authentication:
    Users can sign up, log in, and reset their password. Authenticated users can save and manage their conversation history.

  • Chatting:
    The main chat area allows users to interact with the AI assistant. The sidebar displays saved conversations (for logged-in users) and allows renaming and searching.

  • Theme:
    Toggle between dark and light mode via the navbar. The chosen theme is saved in local storage and persists across sessions.

Streaming Responses

Lumina features real-time streaming responses that make conversations feel more natural and engaging. Instead of waiting for the complete response, you'll see the AI's thoughts appear word-by-word as they're generated.

How It Works

The streaming implementation uses Server-Sent Events (SSE) to deliver AI responses in real-time:

  1. User sends a message → Frontend displays "Processing Message..."
  2. Backend processes → Shows "Thinking & Reasoning..."
  3. Connection established → Displays "Connecting..."
  4. Streaming begins → Text appears word-by-word with a blinking cursor
  5. Response complete → Message is saved to conversation history

Technical Implementation

sequenceDiagram
    participant User
    participant Frontend
    participant Backend
    participant Gemini AI
    
    User->>Frontend: Send message
    Frontend->>Frontend: Show "Processing..."
    Frontend->>Backend: POST /api/chat/auth/stream
    Backend->>Gemini AI: Request streaming response
    
    loop For each chunk
        Gemini AI-->>Backend: Stream text chunk
        Backend-->>Frontend: SSE: chunk data
        Frontend->>Frontend: Append to message bubble
        Frontend->>User: Display growing text + cursor
    end
    
    Gemini AI-->>Backend: Stream complete
    Backend->>Backend: Save to database
    Backend-->>Frontend: SSE: done event
    Frontend->>Frontend: Finalize message

Key Features

  • Live Text Rendering: See responses appear in real-time with markdown formatting
  • Visual Feedback: Multiple loading states (Processing → Thinking → Connecting → Streaming)
  • Blinking Cursor: Animated cursor indicates active streaming
  • Automatic Retries: Up to 3 retry attempts with exponential backoff (1s, 2s, 4s)
  • Error Handling: Graceful degradation with user-friendly error messages
  • Works Everywhere: Available for both authenticated and guest users

API Endpoints

Authenticated Streaming:

POST /api/chat/auth/stream
Content-Type: application/json
Authorization: Bearer <token>

{
  "message": "Your question here",
  "conversationId": "optional-conversation-id"
}

Guest Streaming:

POST /api/chat/guest/stream
Content-Type: application/json

{
  "message": "Your question here",
  "guestId": "optional-guest-id"
}

Event Types

The SSE stream sends different event types:

  • conversationId/guestId: Sent at the start with the conversation identifier
  • chunk: Each piece of text as it's generated from the AI
  • done: Signals that streaming is complete
  • error: Indicates an error occurred during streaming

Error Recovery

If a connection fails during streaming:

  1. First retry: Wait 1 second, then retry
  2. Second retry: Wait 2 seconds, then retry
  3. Third retry: Wait 4 seconds, then retry
  4. All failed: Display error message to user

The retry logic uses exponential backoff to avoid overwhelming the server while providing a smooth user experience.

User Interface

Landing Page

Landing Page

Homepage

Homepage

Homepage - Dark Mode

Homepage - Dark Mode

Homepage - Empty State

Homepage - Empty State

Login Page

Login Page

Login Page - Dark Mode

Login Page - Dark Mode

Signup Page

Signup Page

Signup Page - Dark Mode

Signup Page - Dark Mode

Reset Password Page

Reset Password Page

Reset Password Page - Dark Mode

Reset Password Page - Dark Mode

Homepage - Unauthenticated User

Homepage - Unauthenticated User

Homepage - Unauthenticated User - Dark Mode

Homepage - Unauthenticated User - Dark Mode

404 Page

404 Page

API Endpoints

Authentication

  • POST /api/auth/signup: Create a new user.
  • POST /api/auth/login: Authenticate a user and return a JWT.
  • GET /api/auth/[email protected]: Check if an email exists.
  • POST /api/auth/reset-password: Reset a user's password.
  • GET /api/auth/validate-token: Validate the current JWT token.

Authentication Flow

flowchart TB
    Start([User Visits App]) --> CheckAuth{Has Valid<br/>Token?}
    
    CheckAuth -->|Yes| Dashboard[Access Dashboard]
    CheckAuth -->|No| Landing[Landing Page]
    
    Landing --> Choice{User Choice}
    Choice -->|Sign Up| SignupForm[Signup Form]
    Choice -->|Login| LoginForm[Login Form]
    Choice -->|Guest| GuestChat[Guest Chat Mode]
    
    SignupForm --> ValidateSignup{Valid<br/>Credentials?}
    ValidateSignup -->|No| SignupError[Show Error]
    SignupError --> SignupForm
    ValidateSignup -->|Yes| CreateUser[Create User in MongoDB]
    CreateUser --> GenerateToken[Generate JWT Token]
    
    LoginForm --> ValidateLogin{Valid<br/>Credentials?}
    ValidateLogin -->|No| LoginError[Show Error]
    LoginError --> LoginForm
    ValidateLogin -->|Yes| VerifyPassword[Verify Password with bcrypt]
    VerifyPassword -->|Invalid| LoginError
    VerifyPassword -->|Valid| GenerateToken
    
    GenerateToken --> StoreToken[Store Token in LocalStorage]
    StoreToken --> Dashboard
    
    Dashboard --> Protected[Protected Routes]
    Protected --> ConvHistory[Conversation History]
    Protected --> SavedChats[Saved Chats]
    Protected --> Settings[User Settings]
    
    GuestChat --> TempStorage[Temporary Storage]
    TempStorage --> LimitedFeatures[Limited Features]
    
    Dashboard --> Logout{Logout?}
    Logout -->|Yes| ClearToken[Clear Token]
    ClearToken --> Landing
    
    style Start fill:#4285F4
    style Dashboard fill:#34A853
    style GuestChat fill:#FBBC04
    style GenerateToken fill:#EA4335
    style CreateUser fill:#34A853

Conversations

  • POST /api/conversations: Create a new conversation.
  • GET /api/conversations: Get all conversations for a user.
  • GET /api/conversations/:id: Retrieve a conversation by ID.
  • PUT /api/conversations/:id: Rename a conversation.
  • GET /api/conversations/search/:query: Search for conversations by title or message content.
  • DELETE /api/conversations/:id: Delete a conversation.

Conversation Management Flow

flowchart LR
    subgraph User["👤 User Actions"]
        NewChat[Start New Chat]
        LoadChat[Load Existing Chat]
        SearchChat[Search Conversations]
        RenameChat[Rename Conversation]
        DeleteChat[Delete Conversation]
    end
    
    subgraph Frontend["⚛️ React Frontend"]
        ChatUI[Chat Interface]
        Sidebar[Conversation Sidebar]
        SearchBar[Search Bar]
    end
    
    subgraph API["🔌 Express API"]
        ConvRoutes[api/conversations Route]
        AuthMiddleware{JWT Auth}
    end
    
    subgraph Database["🗄️ MongoDB"]
        ConvCollection[(Conversations Collection)]
        UserCollection[(Users Collection)]
    end
    
    subgraph Operations["📊 CRUD Operations"]
        Create[Create]
        Read[Read]
        Update[Update]
        Delete[Delete]
    end
    
    NewChat --> ChatUI
    LoadChat --> Sidebar
    SearchChat --> SearchBar
    RenameChat --> Sidebar
    DeleteChat --> Sidebar
    
    ChatUI --> ConvRoutes
    Sidebar --> ConvRoutes
    SearchBar --> ConvRoutes
    
    ConvRoutes --> AuthMiddleware
    AuthMiddleware -->|Valid Token| Operations
    AuthMiddleware -->|Invalid Token| ErrorAuth[401 Unauthorized]
    
    Create --> ConvCollection
    Read --> ConvCollection
    Update --> ConvCollection
    Delete --> ConvCollection
    
    ConvCollection -.User Reference.-> UserCollection
    
    ConvCollection --> ConvRoutes
    ConvRoutes --> Frontend
    
    style ChatUI fill:#4285F4
    style ConvCollection fill:#47A248
    style AuthMiddleware fill:#EA4335
    style Operations fill:#34A853

Chat

  • POST /api/chat/auth: Process a chat query for authenticated users and return an AI-generated response.
  • POST /api/chat/auth/stream: Stream AI responses in real-time for authenticated users using Server-Sent Events (SSE).
  • POST /api/chat/guest: Process a chat query for guest users and return an AI-generated response.
  • POST /api/chat/guest/stream: Stream AI responses in real-time for guest users using Server-Sent Events (SSE).

Swagger API Documentation

Swagger API Documentation

Project Structure

AI-Assistant-Chatbot/
├── docker-compose.yml
├── openapi.yaml
├── README.md
├── ARCHITECTURE.md
├── LICENSE
├── Jenkinsfile
├── package.json
├── tsconfig.json
├── .env
├── shell/                          # Shell scripts for app setups
├── terraform/                      # Infrastructure as Code (Terraform)
├── aws/                            # AWS deployment configurations
├── img/                            # Images and screenshots
├── agentic_ai/                     # Agentic AI pipeline in Python
├── client/                         # Frontend React application
│   ├── package.json
│   ├── tsconfig.json
│   ├── docker-compose.yml
│   ├── Dockerfile
│   └── src/
│       ├── App.tsx
│       ├── index.tsx
│       ├── theme.ts
│       ├── globals.css
│       ├── index.css
│       ├── dev/
│       │   ├── palette.tsx
│       │   ├── previews.tsx
│       │   ├── index.ts
│       │   └── useInitial.ts
│       ├── services/
│       │   └── api.ts              # API client with streaming support
│       ├── types/
│       │   ├── conversation.d.ts
│       │   └── user.d.ts
│       ├── components/
│       │   ├── Navbar.tsx
│       │   ├── Sidebar.tsx
│       │   ├── ChatArea.tsx        # Main chat interface with streaming
│       │   └── CopyIcon.tsx
│       ├── styles/
│       │   └── (various style files)
│       └── pages/
│           ├── LandingPage.tsx
│           ├── Home.tsx
│           ├── Login.tsx
│           ├── Signup.tsx
│           ├── NotFoundPage.tsx
│           ├── ForgotPassword.tsx
│           └── Terms.tsx
└── server/                         # Backend Express application
    ├── package.json
    ├── tsconfig.json
    ├── Dockerfile
    ├── docker-compose.yml
    └── src/
        ├── server.ts
        ├── models/
        │   ├── Conversation.ts
        │   ├── GuestConversation.ts
        │   ├── KnowledgeSource.ts
        │   └── User.ts
        ├── routes/
        │   ├── auth.ts
        │   ├── conversations.ts
        │   ├── chat.ts             # Authenticated chat with streaming
        │   └── guest.ts            # Guest chat with streaming
        ├── services/
        │   ├── geminiService.ts    # AI service with streaming support
        │   ├── knowledgeBase.ts    # Chunking, embeddings, retrieval
        │   └── pineconeClient.ts
        ├── scripts/
        │   └── knowledgeCli.ts     # CLI + REPL ingestion
        ├── utils/
        │   └── (utility functions)
        ├── middleware/
        │   └── auth.ts
        └── public/
            └── favicon.ico

Agentic AI Pipeline

There is also a separate Agentic AI pipeline implemented in Python. This pipeline demonstrates how to create an autonomous agent that can perform tasks using tools and interact with the AI model.

The pipeline is located in the agentic_ai/ directory and is optional for the main assistant.

[!TIP] For more information on the Agentic AI pipeline, please refer to the agentic_ai/README.md file.

Dockerization

To run the application using Docker, simply run docker-compose up in the root directory of the project. This will start both the backend and frontend services as defined in the docker-compose.yml file.

Why Dockerize?

  • Consistency: Ensures the application runs the same way in different environments.
  • Isolation: Keeps dependencies and configurations contained.
  • Scalability: Makes it easier to scale services independently.
  • Simplified Deployment: Streamlines the deployment process.
  • Easier Collaboration: Provides a consistent environment for all developers.

OpenAPI Specification

There is an OpenAPI specification file (openapi.yaml) in the root directory that describes the API endpoints, request/response formats, and authentication methods. This can be used to generate client SDKs or documentation.

To view the API documentation, you can use tools like Swagger UI or Postman to import the openapi.yaml file. Or just go to the /docs endpoint of the deployed backend.

CI / CD with GitHub Actions

This project includes a GitHub Actions workflow for continuous integration and deployment. The workflow is defined in the .github/workflows/workflow.yml file and includes steps to:

  • Install dependencies for both the frontend and backend.
  • Run tests for both the frontend and backend.
  • Build the frontend and backend applications.
  • Deploy the applications to Vercel and Netlify.
  • Notify the team via email on successful deployments.
  • Notify the team via email on failed builds or tests.
  • Generate and upload artifacts for the frontend and backend builds.
  • Run linting checks for both the frontend and backend code.
  • and more...

This workflow ensures that every commit and pull request is tested and deployed automatically, providing a robust CI/CD pipeline.

Please ensure you have the necessary secrets configured in your GitHub repository for deployment (e.g, Vercel and Netlify tokens, etc.). Also, feel free to customize the workflow under .github/workflows/workflow.yml to suit your needs.

Testing

This project includes unit and integration tests with Jest for both the frontend and backend. To run the tests:

  • Frontend:
    Navigate to the client directory and run:

    npm test

  • Backend:
    Navigate to the server directory and run:

    npm test

Contributing

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

License

This project is licensed under the MIT License.

Contact

If you have any questions or suggestions, feel free to reach out to me:

Thank you for checking out the AI Assistant Project! If you have any questions or feedback, feel free to reach out. Happy coding! 🚀

⬆️ Back to Top

← Metadata

33
Stars
9
Forks
33
Watchers

Owner

verified publisher icon hoangsonww

Metadata

👨🏻‍💻 Meet Lumina – my personal chatbot assistant designed to answer any questions, either about me or any other topics. Powered by Retrieval-Augmented Generation (RAG), LangChain, kNN cosine simila...

Back