main.py

import gradio as gr

def greet(input_text):
    # Example call to a compiled llama.cpp binary (replace with real model path)
    # subprocess.run(["./llama.cpp/main", "-m", "models/llama-7b.gguf", "-p", input_text])
    return f"Llama.cpp would process: {input_text}"

def run():
    
    demo = gr.Interface(
        fn=greet,
        inputs=gr.Textbox(label="Enter text"),
        outputs="text",
        title="Llama.cpp + Gradio Demo"
    )

    demo.launch(server_name="0.0.0.0", server_port=7860)

if __name__ == "__main__":
    run()