app.py

from flask import Flask, request, render_template
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import re

app = Flask(__name__)

# Load model and tokenizer
model_path = "./tinyllama_model"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)
device = torch.device("cpu")
model.to(device)

# Load simple knowledge base
knowledge_base = {}
try:
    with open("knowledge_base.txt", "r") as f:
        for line in f:
            if ":" in line:
                key, value = line.strip().split(":", 1)
                knowledge_base[key.lower()] = value.strip()
except FileNotFoundError:
    knowledge_base = {
        "ceo of meta": "Mark Zuckerberg",
        "founder of meta": "Mark Zuckerberg",
        "meta founding year": "2004"
    }

@app.route('/')
def home():
    return render_template('index.html')

@app.route('/generate', methods=['POST'])
def generate():
    user_input = request.form['prompt'].strip().lower()
    
    # Check knowledge base for factual answers
    response = None
    for key in knowledge_base:
        if key in user_input:
            response = knowledge_base[key]
            break
    
    if not response:
        # Create chat prompt template
        prompt = f"<|SYSTEM|> You are a helpful assistant providing accurate and concise answers. Avoid fabricating details or repeating user input unnecessarily. If unsure, say so. <|USER|> {user_input} <|ASSISTANT|> "
        inputs = tokenizer(prompt, return_tensors="pt").to(device)
        outputs = model.generate(**inputs, max_length=100, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
        # Clean response
        response = generated_text.split("<|ASSISTANT|> ")[-1] if "<|ASSISTANT|> " in generated_text else generated_text
        response = re.sub(r"\s+", " ", response).strip()
        # Avoid repetitive or irrelevant output
        if user_input in response.lower() and len(response.split()) < 10:
            response = "I'm not sure how to respond to that. Could you clarify or ask something else?"

    return response

if __name__ == '__main__':
    app.run(debug=True)