# from transformers import pipeline

# generator = pipeline("text-generation", model="gpt2")

# def generate_blog(topic):
#     return generator(f"Write a blog on: {topic}", max_length=200)[0]["generated_text"]


# from transformers import pipeline
# import gradio as gr

# # Load the model
# generator = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1")

# # Define your function
# def generate_text(prompt):
#     result = generator(prompt, max_length=100, num_return_sequences=1, do_sample=True, 
#     temperature=0.7, 
#     top_p=0.9,)
#     return result[0]["generated_text"]

# # Create Gradio interface
# iface = gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Text Generator with GPT-2")

# # ✅ This line is required to actually launch the app on Hugging Face Spaces
# iface.launch()



from transformers import pipeline
import gradio as gr

generator = pipeline("text-generation", model="sshleifer/tiny-gpt2")

def clean_topic(topic):
    topic = topic.lower()
    if "write a blog on" in topic:
        topic = topic.replace("write a blog on", "").strip()
    elif "write a blog about" in topic:
        topic = topic.replace("write a blog about", "").strip()
    return topic.capitalize()

# def generate_blog(topic):
#     topic = clean_topic(topic)
#     if not topic:
#         return "Please provide a topic."
#     prompt = f"""
#     Write a detailed and engaging blog post about "{topic}".
#     Include an introduction, 2–3 subheadings with paragraphs, and a conclusion.
#     Make it informative and conversational.
#     """
#     result = generator(prompt, max_length=700, do_sample=True, temperature=0.7, top_p=0.9)
#     return result[0]['generated_text']

def generate_blog(topic):
    prompt = f"""
    Write a detailed and engaging blog post about "{topic}".
    Include an introduction, 2–3 subheadings with paragraphs, and a conclusion.
    Make it informative and conversational.
    """
    result = generator(prompt, max_length=700, do_sample=True, temperature=0.7, top_p=0.9)
    return result[0]['generated_text']

gr.Interface(fn=generate_blog, inputs="text", outputs="text", title="AI Blog Writer").launch()