Chatbot with Intent Recognition

Project Summery

This is a simple chatbot built with FastAPI, Scikit-learn, and Jinja2, which uses machine learning to recognize user intent and respond accordingly.

🚀 Features

• Intent recognition using TF-IDF + Logistic Regression
• REST API with FastAPI
• Auto model retraining when intents change
• Simple web-based UI (HTML + JS)
• Easily extensible for more intents

🧠 Example Intents

intents.json example:

{
  "intents": [
    {
      "tag": "greeting",
      "patterns": ["Hi", "Hello", "Hey"],
      "responses": ["Hello!", "Hi there!"]
    },
    {
      "tag": "goodbye",
      "patterns": ["Bye", "Goodbye", "See you"],
      "responses": ["Goodbye!", "Take care!"]
    }
  ]
}

📦 Installation

Clone the project:

git clone https://github.com/sujit-codezen/chatbot_with_intent.git
cd chatbot-intent

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

⚙️ Train the Model

python model.py

▶️ Run the Server

uvicorn main:app --reload

Output

Server Run

Web Output