app.py

import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "AventIQ-AI/gpt2-book-article-recommendation"
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_name)

def recommend_titles(alphabet, num_recommendations=5):
    """Generate book/article recommendations based on an input alphabet."""
    input_text = alphabet.strip()
    if not input_text:
        return ["⚠️ Please enter a valid letter."]
    
    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
    
    with torch.no_grad():
        outputs = model.generate(input_ids, max_length=15, num_return_sequences=num_recommendations, do_sample=True)
    
    return [tokenizer.decode(output, skip_special_tokens=True) for output in outputs]

# Example Inputs
example_inputs = ["A", "B", "C", "D", "E"]

# Create Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("## 📚 AI-Powered Book & Article Recommendation")
    gr.Markdown("Enter a letter, and the AI will suggest relevant book or article titles!")
    
    with gr.Row():
        alphabet_input = gr.Textbox(label="🔠 Enter a Letter:", placeholder="Example: A")
        num_recommendations = gr.Slider(minimum=1, maximum=10, value=5, step=1, label="Number of Recommendations")
    
    recommend_button = gr.Button("📖 Get Recommendations")
    output_text = gr.Textbox(label="📄 Recommended Titles:", lines=6)
    
    gr.Markdown("### 🎯 Example Inputs")
    example_buttons = [gr.Button(example) for example in example_inputs]
    
    for btn in example_buttons:
        btn.click(fn=lambda letter=btn.value: letter, outputs=alphabet_input)
    
    recommend_button.click(recommend_titles, inputs=[alphabet_input, num_recommendations], outputs=output_text)

demo.launch()