app.py

import gradio as gr
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch
import subprocess

# Load a code-generation model with support for multiple languages
MODEL_NAME = "Salesforce/codet5-small"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)

def generate_code(description, language):
    prompt = f"Generate {language} code: {description}"
    inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
    outputs = model.generate(**inputs, max_length=400)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.strip()

def execute_code(code, language):
    if language == "Python":
        try:
            result = subprocess.run(['python3', '-c', code], capture_output=True, text=True, timeout=5)
            return result.stdout if result.stdout else result.stderr
        except Exception as e:
            return str(e)
    return "Code execution only supported for Python."

def generate_and_execute(description, language):
    code = generate_code(description, language)
    output = execute_code(code, language) if language == "Python" else "Execution not supported for this language."
    return code, output

# Create a Gradio interface with language selection and execution
iface = gr.Interface(
    fn=generate_and_execute,
    inputs=[
        gr.Textbox(lines=5, placeholder="Describe your coding task..."),
        gr.Dropdown(choices=["Python", "JavaScript", "Java"], label="Programming Language")
    ],
    outputs=[gr.Code(label="Generated Code"), gr.Textbox(label="Execution Output")],
    title="Multi-Language Text-to-Code AI",
    description="Convert natural language descriptions into code in different programming languages! Run Python code directly in the app.",
    theme="default",
    allow_flagging="never",
    live=True
)

# Launch the app
if __name__ == "__main__":
    iface.launch(share=True)