A modern AI-powered chat interface built with Flet UI, integrated with Ollama LLMs and enhanced by LangChain. This project demonstrates a complete conversational AI agent with interactive animations, context-aware prompting, and real-time user interaction — all running locally.

• Features
• Project Structure
• Installation
• Usage Guide
• Built With
• License
• Contributing
• Acknowledgements
• Future Enhancements
• Contact

• Responsive and modern UI built with Flet
• Smooth animations (fade, slide, scale)
• Collapsible side navigation with toggle
• Chat interface using bubble-style messages
• User and AI avatars for a clean experience

• Built-in Ollama LLM (qwen2.5-coder:1.5b)
• Intelligent prompt formatting using LangChain
• In-memory caching for improved response time
• Response formatting criteria:
  • Accurate and complete information
  • Context-aware and easy to understand
  • Grammatically correct and natural phrasing

• Real-time message updates and streaming
• Typing/loading animation for AI responses
• Send message via Enter key or Send button
• Input box with emoji icon and placeholder
• Auto-scroll to latest message on update

• Modular, component-based project structure
• Clear separation of UI, AI logic, and state management
• Uses modern design patterns
• Fully commented and formatted codebase

├── core/
│ ├── animations/ # Animation helpers                           
│ ├── widegets/ # Reusable UI elements                            
│ ├── model_llm/ # LLM integration and prompt templates                      
│ ├── providers/ # State and screen management                     
│ └── interface/ # Main screens and layout views                               
└── LICENSE
└── README.md                 # Project documentation file.
└── demo.png
└── requirements-chatbot # Python dependences
└── main_app.py
└── struc.txt

1. Prerequisites:

• Python 3.8+

2. Clone the repository:

git clone https://github.com/paht2005/mini-AI-Agent-Chatbot-with-Flet.git
cd mini-AI-Agent-Chatboit-with-Flet

3. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

4. Install required packages:

 pip install -r requirements-chatbot.txt

5. Run the app:

   python main_app.py # or python3 main_app.py

• Type your question in the text box at the bottom of the screen.
• Press Enter or click the Send button.
• Wait for a response (AI typing animation shown).
• Use the side menu to toggle navigation panel.

• Flet – Python UI framework based on Flutter
• LangChain – Prompt engineering and LLM orchestration
• Ollama – Lightweight, local LLM deployment

This project is licensed under the MIT License. See the LICENSE file for details.

I welcome contributions to improve this project! Feel free to:

• Submit pull requests
• Report bugs
• Suggest new features

• Support for switching between multiple LLMs (e.g., Mistral, LLaMA)
• Add memory and context window for longer conversations
• Export chat history as PDF or Markdown
• Add user authentication for personalized AI agents
• Light/Dark theme toggle

Contact for work: Nguyễn Công Phát – [email protected]