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 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 get_random_joke() -> str:
    """Gets a random joke from an open API."""
    response = requests.get("https://official-joke-api.appspot.com/random_joke")
    data = response.json()
    return f"{data.get('setup')} - {data.get('punchline')}"

@tool
def generate_flux_image(prompt: str, width: int = 1024, height: int = 1024, guidance_scale: float = 3.5, num_inference_steps: int = 28) -> str:
    """Generates an image using FLUX.1 text-to-image model.
    
    Args:
        prompt: Text description of the image to generate
        width: Width of the generated image (default: 1024)
        height: Height of the generated image (default: 1024)
        guidance_scale: How closely the image should follow the prompt (default: 3.5)
        num_inference_steps: Number of denoising steps (default: 28)
    """
    try:
        from gradio_client import Client
        import tempfile
        import os
        
        # Create a client for the FLUX model
        client = Client("black-forest-labs/FLUX.1-dev")
        
        # Call the model to generate an image
        result = client.predict(
            prompt=prompt,
            seed=0,
            randomize_seed=True,
            width=width,
            height=height,
            guidance_scale=guidance_scale,
            num_inference_steps=num_inference_steps,
            api_name="/infer"
        )
        
        # The result is typically a path to an image
        image_path = result
        
        # You could return the path or handle the image as needed
        return f"Image successfully generated based on prompt: '{prompt}'. Image path: {image_path}"
        
    except Exception as e:
        return f"Error generating image: {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
model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',
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,get_current_time_in_timezone,get_random_joke,generate_flux_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()