app.py

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
import torch
from tools.final_answer import FinalAnswerTool

from Gradio_UI import GradioUI

# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """A tool that does nothing yet 
    Args:
        arg1: the first argument
        arg2: the second argument
    """
    return "What magic will you build ?"

@tool
def get_current_time_in_timezone(timezone: str) -> str:
    """A tool that fetches the current local time in a specified timezone.
    Args:
        timezone: A string representing a valid timezone (e.g., 'America/New_York').
    """
    try:
        # Create timezone object
        tz = pytz.timezone(timezone)
        # Get current time in that timezone
        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
        return f"The current local time in {timezone} is: {local_time}"
    except Exception as e:
        return f"Error fetching time for timezone '{timezone}': {str(e)}"

@tool
def generate_open_source_image(prompt: str) -> str:
    """
    Genera un'immagine a partire da un prompt di testo utilizzando un modello open source di diffusion (Stable Diffusion).
    
    Args:
        prompt: Una stringa contenente il prompt testuale da usare per generare l'immagine.
        
    Returns:
        Una stringa che rappresenta il percorso del file in cui l'immagine generata è stata salvata.
    """
    try:
        # Importa il pipeline di Stable Diffusion
        from diffusers import StableDiffusionPipeline

        # Specifica l'ID del modello open source su Hugging Face
        model_id = "stabilityai/stable-diffusion-2-1"
        
        # Determina il dispositivo da usare (GPU se disponibile, altrimenti CPU)
        device = "cuda" if torch.cuda.is_available() else "cpu"
        
        # Carica il modello; utilizza torch.float16 se disponibile la GPU per prestazioni migliori
        pipe = StableDiffusionPipeline.from_pretrained(
            model_id, 
            torch_dtype=torch.float16 if device == "cuda" else torch.float32
        )
        pipe = pipe.to(device)
        
        # Genera l'immagine a partire dal prompt
        image = pipe(prompt).images[0]
        
        # Crea un nome di file unico per salvare l'immagine
        filename = f"generated_image_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.png"
        image.save(filename)
        
        return f"Immagine generata e salvata in: {filename}"
    except Exception as e:
        return f"Si è verificato un errore nella generazione dell'immagine: {str(e)}"

final_answer = FinalAnswerTool()

# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 

model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)


# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[final_answer, 
          generate_open_source_image], ## add your tools here (don't remove final answer)
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates
)


GradioUI(agent).launch()