AI Security

Prima ta aplicatie AI in 30 de minute: tutorial

Nicu Constantin
--7 min lectura
#ai-tutorial#python#flask#openai#beginner

Vrei sa construiesti o aplicatie AI dar nu stii de unde sa incepi? Acest tutorial te duce de la zero la un chatbot AI functional, bazat pe web, in 30 de minute.

Ce construim

┌─────────────────────────────────────┐
│  🤖 AI ChatBot                      │
├─────────────────────────────────────┤
│                                     │
│  You: What's the weather like?      │
│                                     │
│  Bot: I don't have access to        │
│       real-time weather data, but   │
│       I can help with other things! │
│                                     │
│  You: Tell me a joke               │
│                                     │
│  Bot: Why do programmers prefer    │
│       dark mode? Because light     │
│       attracts bugs! 🐛            │
│                                     │
│  [Type a message...        ] [Send] │
└─────────────────────────────────────┘

Cerinte preliminare

  • Python instalat (3.8+)
  • Un cont OpenAI
  • 30 de minute de timp
  • Nu ai nevoie de experienta anterioara in AI!

Pasul 1: Configureaza proiectul (5 minute)

Creeaza folderul proiectului:

# Open terminal and run:
mkdir ai-chatbot
cd ai-chatbot

Creeaza mediul virtual:

# Mac/Linux
python3 -m venv venv
source venv/bin/activate
 
# Windows
python -m venv venv
venv\Scripts\activate

Instaleaza dependentele:

pip install flask openai python-dotenv

Creeaza structura proiectului:

ai-chatbot/
├── app.py              # Main application
├── templates/
│   └── index.html      # Web interface
├── .env                # API key (secret!)
└── requirements.txt    # Dependencies

Pasul 2: Obtine cheia ta API OpenAI (3 minute)

  1. Mergi la https://platform.openai.com
  2. Inregistreaza-te sau autentifica-te
  3. Click pe "API keys" in bara laterala
  4. Creeaza o cheie noua
  5. Copiaz-o imediat!

Creeaza fisierul .env:

# .env - NEVER commit this to git!
OPENAI_API_KEY=sk-your-key-paste-here

Creeaza .gitignore:

# .gitignore
.env
venv/
__pycache__/

Pasul 3: Construieste backend-ul (10 minute)

Creeaza app.py:

# app.py
from flask import Flask, render_template, request, jsonify
from openai import OpenAI
import os
from dotenv import load_dotenv
 
# Load environment variables
load_dotenv()
 
# Initialize Flask app
app = Flask(__name__)
 
# Initialize OpenAI client
client = OpenAI()
 
# Store conversation history (in memory for now)
conversation_history = []
 
@app.route('/')
def home():
    """Render the chat interface."""
    return render_template('index.html')
 
@app.route('/chat', methods=['POST'])
def chat():
    """Handle chat messages."""
    # Get message from request
    data = request.json
    user_message = data.get('message', '').strip()
 
    if not user_message:
        return jsonify({'error': 'No message provided'}), 400
 
    # Add user message to history
    conversation_history.append({
        "role": "user",
        "content": user_message
    })
 
    try:
        # Create messages array with system prompt
        messages = [
            {
                "role": "system",
                "content": "You are a friendly and helpful AI assistant. Be concise but informative."
            }
        ] + conversation_history
 
        # Call OpenAI API
        response = client.chat.completions.create(
            model="gpt-4o-mini",  # Cheap and fast!
            messages=messages,
            max_tokens=500
        )
 
        # Extract response
        bot_message = response.choices[0].message.content
 
        # Add to history
        conversation_history.append({
            "role": "assistant",
            "content": bot_message
        })
 
        # Keep history manageable (last 20 messages)
        if len(conversation_history) > 20:
            conversation_history.pop(0)
            conversation_history.pop(0)
 
        return jsonify({'response': bot_message})
 
    except Exception as e:
        print(f"Error: {e}")
        return jsonify({'error': 'Something went wrong. Please try again.'}), 500
 
@app.route('/clear', methods=['POST'])
def clear():
    """Clear conversation history."""
    global conversation_history
    conversation_history = []
    return jsonify({'status': 'cleared'})
 
if __name__ == '__main__':
    app.run(debug=True, port=5000)

Pasul 4: Construieste frontend-ul (10 minute)

Creeaza templates/index.html:

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>AI ChatBot</title>
    <style>
        * {
            margin: 0;
            padding: 0;
            box-sizing: border-box;
        }
 
        body {
            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
            min-height: 100vh;
            display: flex;
            justify-content: center;
            align-items: center;
            padding: 20px;
        }
 
        .chat-container {
            width: 100%;
            max-width: 600px;
            background: white;
            border-radius: 20px;
            box-shadow: 0 10px 40px rgba(0,0,0,0.2);
            overflow: hidden;
        }
 
        .chat-header {
            background: #667eea;
            color: white;
            padding: 20px;
            text-align: center;
        }
 
        .chat-header h1 {
            font-size: 1.5rem;
            margin-bottom: 5px;
        }
 
        .chat-messages {
            height: 400px;
            overflow-y: auto;
            padding: 20px;
            background: #f5f5f5;
        }
 
        .message {
            margin-bottom: 15px;
            display: flex;
            flex-direction: column;
        }
 
        .message.user {
            align-items: flex-end;
        }
 
        .message.bot {
            align-items: flex-start;
        }
 
        .message-content {
            max-width: 80%;
            padding: 12px 18px;
            border-radius: 18px;
            line-height: 1.5;
        }
 
        .message.user .message-content {
            background: #667eea;
            color: white;
            border-bottom-right-radius: 4px;
        }
 
        .message.bot .message-content {
            background: white;
            color: #333;
            border-bottom-left-radius: 4px;
            box-shadow: 0 1px 2px rgba(0,0,0,0.1);
        }
 
        .message-label {
            font-size: 0.75rem;
            color: #888;
            margin-bottom: 4px;
        }
 
        .chat-input {
            display: flex;
            padding: 20px;
            background: white;
            border-top: 1px solid #eee;
        }
 
        .chat-input input {
            flex: 1;
            padding: 12px 20px;
            border: 2px solid #eee;
            border-radius: 25px;
            font-size: 1rem;
            outline: none;
            transition: border-color 0.3s;
        }
 
        .chat-input input:focus {
            border-color: #667eea;
        }
 
        .chat-input button {
            margin-left: 10px;
            padding: 12px 25px;
            background: #667eea;
            color: white;
            border: none;
            border-radius: 25px;
            font-size: 1rem;
            cursor: pointer;
            transition: background 0.3s;
        }
 
        .chat-input button:hover {
            background: #5a6fd6;
        }
 
        .chat-input button:disabled {
            background: #ccc;
            cursor: not-allowed;
        }
 
        .typing-indicator {
            display: none;
            padding: 12px 18px;
            background: white;
            border-radius: 18px;
            border-bottom-left-radius: 4px;
            color: #888;
            font-style: italic;
        }
 
        .typing-indicator.show {
            display: inline-block;
        }
 
        .clear-btn {
            background: #ff6b6b !important;
        }
 
        .clear-btn:hover {
            background: #ee5a5a !important;
        }
    </style>
</head>
<body>
    <div class="chat-container">
        <div class="chat-header">
            <h1>🤖 AI ChatBot</h1>
            <p>Powered by OpenAI</p>
        </div>
 
        <div class="chat-messages" id="chatMessages">
            <div class="message bot">
                <span class="message-label">Bot</span>
                <div class="message-content">
                    Hello! I'm your AI assistant. How can I help you today?
                </div>
            </div>
        </div>
 
        <div class="chat-input">
            <input type="text" id="messageInput" placeholder="Type a message..." autocomplete="off">
            <button onclick="sendMessage()" id="sendBtn">Send</button>
            <button onclick="clearChat()" class="clear-btn">Clear</button>
        </div>
    </div>
 
    <script>
        const messagesContainer = document.getElementById('chatMessages');
        const messageInput = document.getElementById('messageInput');
        const sendBtn = document.getElementById('sendBtn');
 
        // Send on Enter key
        messageInput.addEventListener('keypress', (e) => {
            if (e.key === 'Enter') {
                sendMessage();
            }
        });
 
        function addMessage(content, isUser) {
            const messageDiv = document.createElement('div');
            messageDiv.className = `message ${isUser ? 'user' : 'bot'}`;
 
            messageDiv.innerHTML = `
                <span class="message-label">${isUser ? 'You' : 'Bot'}</span>
                <div class="message-content">${content}</div>
            `;
 
            messagesContainer.appendChild(messageDiv);
            messagesContainer.scrollTop = messagesContainer.scrollHeight;
        }
 
        function showTyping() {
            const typingDiv = document.createElement('div');
            typingDiv.className = 'message bot';
            typingDiv.id = 'typingIndicator';
            typingDiv.innerHTML = `
                <span class="message-label">Bot</span>
                <div class="typing-indicator show">Thinking...</div>
            `;
            messagesContainer.appendChild(typingDiv);
            messagesContainer.scrollTop = messagesContainer.scrollHeight;
        }
 
        function hideTyping() {
            const typing = document.getElementById('typingIndicator');
            if (typing) typing.remove();
        }
 
        async function sendMessage() {
            const message = messageInput.value.trim();
            if (!message) return;
 
            // Add user message
            addMessage(message, true);
            messageInput.value = '';
 
            // Disable input while processing
            sendBtn.disabled = true;
            messageInput.disabled = true;
 
            // Show typing indicator
            showTyping();
 
            try {
                const response = await fetch('/chat', {
                    method: 'POST',
                    headers: { 'Content-Type': 'application/json' },
                    body: JSON.stringify({ message })
                });
 
                const data = await response.json();
 
                hideTyping();
 
                if (data.error) {
                    addMessage('Sorry, something went wrong. Please try again.', false);
                } else {
                    addMessage(data.response, false);
                }
            } catch (error) {
                hideTyping();
                addMessage('Connection error. Please check your internet.', false);
            }
 
            // Re-enable input
            sendBtn.disabled = false;
            messageInput.disabled = false;
            messageInput.focus();
        }
 
        async function clearChat() {
            await fetch('/clear', { method: 'POST' });
            messagesContainer.innerHTML = `
                <div class="message bot">
                    <span class="message-label">Bot</span>
                    <div class="message-content">
                        Chat cleared! How can I help you?
                    </div>
                </div>
            `;
        }
    </script>
</body>
</html>

Pasul 5: Ruleaza aplicatia! (2 minute)

# Make sure you're in the project folder with venv activated
python app.py

Deschide browser-ul: Mergi la http://localhost:5000

Ar trebui sa vezi chatbot-ul tau! Incearca sa scrii:

  • "Hello!"
  • "Tell me a joke"
  • "What can you help me with?"

Felicitari!

Tocmai ai construit prima ta aplicatie AI!

Ce ai invatat

✅ Setting up Python virtual environment
✅ Using OpenAI API
✅ Building Flask web server
✅ Creating responsive chat interface
✅ Handling API requests/responses
✅ Managing conversation history

Ce urmeaza?

Imbunatatiri pe care le poti face:

  1. Adauga o baza de date - Stocheaza conversatiile permanent
  2. Conturi de utilizator - Permite utilizatorilor sa isi salveze chat-urile
  3. Streaming - Afiseaza raspunsurile cuvant cu cuvant
  4. Publica online - Pune aplicatia pe internet

Upgrade rapid - Adauga streaming:

# In app.py, add streaming endpoint
@app.route('/chat-stream', methods=['POST'])
def chat_stream():
    def generate():
        # ... setup code ...
        stream = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=messages,
            stream=True
        )
        for chunk in stream:
            if chunk.choices[0].delta.content:
                yield f"data: {chunk.choices[0].delta.content}\n\n"
    return Response(generate(), mimetype='text/event-stream')

Depanare

Eroare "Module not found":

pip install flask openai python-dotenv

Eroare "Invalid API key":

  • Verifica ca fisierul .env contine cheia corecta
  • Fara spatii in jurul semnului =
  • Restarteaza serverul Flask

Raspunsuri goale:

  • Verifica ca ai credit in contul OpenAI
  • Incearca un prompt mai simplu mai intai

Fisierele complete de cod

requirements.txt:

flask==3.0.0
openai==1.12.0
python-dotenv==1.0.0

Ai nevoie de ajutor pentru a merge mai departe?

Construirea aplicatiilor AI pentru productie necesita mai mult decat tutoriale. Echipa noastra te poate ajuta cu:

  • Dezvoltare full-stack de aplicatii AI
  • Deployment si scalare
  • Securitate si conformitate
  • Solutii AI personalizate

Obtine ajutor pentru dezvoltare


Sistemul tau AI e conform cu EU AI Act? Evaluare gratuita de risc - afla in 2 minute →

Ai nevoie de ajutor cu conformitatea EU AI Act sau securitatea AI?

Programeaza o consultatie gratuita de 30 de minute. Fara obligatii.

Programeaza un Apel

Weekly AI Security & Automation Digest

Get the latest on AI Security, workflow automation, secure integrations, and custom platform development delivered weekly.

No spam. Unsubscribe anytime.