app.py

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

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)}"


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
# @tool
# image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
# @tool
# def generate_image_from_text(prompt: str) -> Image:
#     """
#     A tool that generates an image based on the given text prompt and displays it.
#     Args:
#         prompt: A string describing the image to be generated.
#     """
#     try:
#         # Load the image generation tool
#         image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
        
#         # Generate the image and get the URL
#         image_url = image_generation_tool(prompt)

#         # Fetch the image from the URL
#         response = requests.get(image_url)
#         image = Image.open(io.BytesIO(response.content))

#         # Display the image inline for Jupyter Notebook or applications with inline display support
#         display.display(image)
#         image.save("generated_image.png")
#         print("Image saved as generated_image.png. Open the file to view it.")
#         # Return the image object
#         return image

#     except Exception as e:
#         print(f"Error generating image: {str(e)}")



@tool
def generate_image_from_text(prompt: str) -> Image:
    """
    A tool that generates an image based on the given text prompt and displays it.
    
    Args:
        prompt: A string describing the image to be generated.
    
    Returns:
        Image: The generated image that can be displayed by Gradio.
    """
    try:
        # Load the image generation tool
        image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
        
        # Generate the image and get the URL
        image_url = image_generation_tool(prompt)

        # Fetch the image from the URL
        response = requests.get(image_url)
        image = Image.open(io.BytesIO(response.content))

        # Optionally save the image to a file
        image.save("generated_image.png")
        print("Image saved as generated_image.png. Open the file to view it.")

        # Return the image object for Gradio to display
        return image

    except Exception as e:
        print(f"Error generating image: {str(e)}")
        return None

with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[final_answer,get_current_time_in_timezone,generate_image_from_text], ## 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()