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)}"


# Define a custom image generation tool with better error handling
@tool
def generate_image(prompt: str) -> object:
    """Generates an image based on the text prompt provided.
    Args:
        prompt: A detailed description of the image to generate. For better results,
               include details like 'high-res, photorealistic, detailed lighting'.
    """
    try:
        # First try to use the FLUX model via Tool.from_space
        image_tool = Tool.from_space(
            "black-forest-labs/FLUX.1-schnell",
            name="image_generator",
            description="Generate an image from a prompt"
        )
        return image_tool.forward(prompt=prompt)
    except Exception as e:
        # Fall back to the original tool if the first method fails
        try:
            # Try the m-ric tool which is known to work well
            fallback_tool = load_tool("m-ric/text-to-image", trust_remote_code=True)
            return fallback_tool(prompt=prompt)
        except Exception as e2:
            return f"Image generation failed with both methods. Errors: {str(e)}, then {str(e2)}"


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='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',# 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)

# Convert all templates to nested dicts
for key in list(prompt_templates.keys()):
    if isinstance(prompt_templates[key], str):
        prompt_templates[key] = {"content": prompt_templates[key]}

# Ensure final_answer structure
if 'final_answer' in prompt_templates:
    prompt_templates['final_answer'] = {
        'pre_messages': '',
        'content': prompt_templates['final_answer']['content'],
        'post_messages': ''
    }

# Resolve {final_answer} in system_prompt
if 'system_prompt' in prompt_templates and 'final_answer' in prompt_templates:
    sys_content = prompt_templates['system_prompt']['content']
    final_content = prompt_templates['final_answer']['content']
    prompt_templates['system_prompt']['content'] = sys_content.replace(
        "{final_answer}", 
        final_content
    )
    
agent = CodeAgent(
    model=model,
    tools=[final_answer, my_custom_tool, get_current_time_in_timezone, generate_image, image_generation_tool], ## 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()