AI Chatbot API

A simple AI chatbot backend built with FastAPI, Groq API, SQLAlchemy, and SQLite.

---

** About the Project

This project is an AI chatbot backend developed to learn how modern AI applications are built.

The chatbot uses the Groq API to generate responses while FastAPI handles the backend API. Instead of storing chat history in a JSON file, conversations are saved in a SQLite database using SQLAlchemy, allowing the chatbot to remember previous messages within the same conversation.

The project includes a responsive web interface built with HTML, CSS, and JavaScript. Users can create conversations, continue previous chats, and interact with the AI through a modern chat interface.

---

** Features

• AI-powered chatbot
• Dynamic conversation memory
• Multiple conversations
• FastAPI backend
• SQLite database
• SQLAlchemy ORM
• Organized project structure (Routers, CRUD, Models, Schemas)
• Swagger UI for testing APIs
• Modern responsive web interface
• Conversation history sidebar
• Continue previous conversations

---

Tech Stack

Technology	Purpose
Python	Programming Language
FastAPI	Backend Framework
Groq API	AI Response Generation
SQLAlchemy	ORM
SQLite	Database
Pydantic	Data Validation
Uvicorn	ASGI Server

---

📸 Screenshots

Chat Response

Database

---

Project Structure

Installation

Clone the repository

git clone https://github.com/Areesha643/AI-chatbot-fastapi.git

Move into the project folder

cd ai-chatbot-fastapi

Create a virtual environment

python -m venv venv

Activate the virtual environment

Windows

venv\Scripts\activate

Linux/macOS

source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Create a .env file

GROQ_API_KEY=your_api_key

Run the server

uvicorn main:app --reload

Open the chatbot

http://127.0.0.1:8000

API Documentation (Swagger UI)

http://127.0.0.1:8000/docs

API Example

Start a new conversation

{
    "message": "Hello!"
}

Example response

{
    "conversation_id": 1,
    "reply": "Hello! How can I help you today?"
}

Continue the conversation

{
    "conversation_id": 1,
    "message": "What is my name?"
}

---

What I Learned

This project helped me understand:

• Building REST APIs with FastAPI
• Integrating AI models using the Groq API
• SQLAlchemy ORM
• Database relationships
• CRUD operations
• Organizing backend projects
• Managing conversation memory
• Environment variables
• Clean backend architecture

---

Future Improvements

• User authentication
• Message timestamps
• Delete conversations
• Docker support
• PostgreSQL integration

---

Author

Developed as a personal learning project while exploring AI integration and backend development with FastAPI.