College Enquiry Chatbot

A college enquiry chatbot built using Python, Machine Learning, and Flask. Students can ask questions about the college and get instant answers without visiting the campus personally.

---

Project Structure

college_chatbot/
│
├── intents.json          ← Training data (questions + responses)
├── train_model.py        ← ML model training script (run once)
├── chatbot.py            ← Core prediction engine
├── app.py                ← Flask web application
├── requirements.txt      ← Python dependencies
│
├── model/                ← Auto-created after training
│   ├── chatbot_model.pkl
│   └── responses.pkl
│
├── templates/
│   └── index.html        ← Chat UI
│
└── static/
    ├── css/style.css     ← Styling
    └── js/chat.js        ← Frontend logic

---

How to Run

Step 1 — Install the required libraries

pip install -r requirements.txt

Step 2 — Train the model

python train_model.py

Step 3 — Start the server

python app.py

Step 4 — Open in browser

http://127.0.0.1:5000

---

How It Works

The user types a question in the chat. The message is converted into numbers using TF-IDF vectorization and then passed to a Logistic Regression classifier which predicts the intent. Based on the predicted intent, a response is picked and shown to the user. If the confidence is below 25%, a fallback message is shown instead.

---

How to Add New Topics

Open intents.json and add a new block like this:

{
  "tag": "topic_name",
  "patterns": [
    "Question 1",
    "Question 2"
  ],
  "responses": [
    "Answer here"
  ]
}

After adding, run python train_model.py again to retrain the model.

---

Tech Stack

• Language — Python 3.10+
• ML Model — Logistic Regression (Scikit-learn)
• Text Processing — TF-IDF Vectorization
• Web Framework — Flask
• Frontend — HTML, CSS, JavaScript

---