💬 Chatbot with Memory using LangChain, FastAPI & OpenAI

This project is a simple yet powerful chatbot built with FastAPI and LangChain, integrating OpenAI's GPT-3.5-Turbo model. It supports session-based message memory, a customizable user interface with HTML/JS, dark mode, and persistent chat history using localStorage.

🚀 Features

• ✅ Session-based memory using LangChain
• ✅ FastAPI-powered backend
• ✅ Lightweight HTML + JavaScript frontend
• ✅ Username prompt on first visit
• ✅ Persistent chat history (localStorage)
• ✅ Dark mode toggle
• ✅ Clear chat button

🛠 Installation

1. Clone the repository:

git clone https://github.com/iremhazald/chatbot-memory-app.git
cd chatbot-memory-app

2. Create a virtual environment (recommended):

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

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file and add your OpenAI API key:

OPENAI_API_KEY=your_openai_key_here

5. Run the server:

uvicorn main:app --reload

6. Open in your browser:

http://127.0.0.1:8000

💻 Usage

• When the page loads, you’ll be prompted to enter your name.
• Type your message and click Send.
• Messages will appear in the chat box along with AI responses.
• You can toggle dark mode or clear chat history at any time.

📁 Project Structure

├── main.py               # FastAPI app and routes
├── chat_logic.py         # LangChain logic for session memory
├── templates/
│   └── index.html        # Frontend user interface
├── requirements.txt      # Python dependencies
└── .env                  # Your OpenAI API key (not tracked)

🛠 Technologies Used

• LangChain
• FastAPI
• OpenAI GPT-3.5 Turbo
• HTML + Vanilla JavaScript
• Python 3.9+

👩‍💻 Developer

İrem Hazal Deveci
LinkedIn • GitHub)

---

📃 License

This project is licensed under the MIT License. Feel free to use, modify, and share.