Getting started with AI doesn’t have to be expensive or complicated.
In this guide, we’ll build a simple AI-powered app using completely free tools.
🧠 What You’ll Build
A simple app that:
- Takes user input
- Sends it to an AI model
- Returns a response
Basically your own mini ChatGPT.
🛠️ Tech Stack (Free)
- Ollama → Run AI locally (no API cost)
- Python + FastAPI → Backend
- HTML → Simple frontend
⚙️ Step 1: Install Ollama
Download: https://ollama.com
Run:
ollama run llama3
This starts your local AI model.
⚙️ Step 2: Create Backend
Create a file:
main.py
Add this:
from fastapi import FastAPI
import requests
app = FastAPI()
@app.get("/")
def home():
return {"message": "AI App is running"}
@app.get("/ask")
def ask_ai(question: str):
response = requests.post(
"http://localhost:11434/api/generate",
json={
"model": "llama3",
"prompt": question
}
)
data = response.json()
return {"answer": data["response"]}
▶️ Step 3: Run App
pip install fastapi uvicorn requests
uvicorn main:app --reload
Open:
http://127.0.0.1:8000
🧪 Step 4: Test
Open in browser:
http://127.0.0.1:8000/ask?question=Explain Python simply
🎨 Step 5: Simple UI (Optional)
Create index.html:
<!DOCTYPE html>
<html>
<head>
<title>AI App</title>
</head>
<body>
<h2>Ask AI</h2>
<input id="q" placeholder="Type question"/>
<button onclick="ask()">Ask</button>
<pre id="res"></pre>
<script>
async function ask() {
const q = document.getElementById("q").value;
const res = await fetch(`/ask?question=${q}`);
const data = await res.json();
document.getElementById("res").innerText = data.answer;
}
</script>
</body>
</html>
💡 What You Can Build Next
- AI chatbot
- Resume analyzer
- Interview prep tool
- Code assistant
⚠️ Common Issues
- Ollama not running
- Wrong endpoint
- Missing dependencies
🧠 Final Thought
You don’t need expensive APIs to start with AI.
Start small → build → improve.
🚀 Try This Today
What will you build with this? 👇
Top comments (0)