app.py

import datetime

import pytz
import yaml
from huggingface_hub import InferenceClient
from smolagents import CodeAgent, HfApiModel, tool, Tool

from Gradio_UI import GradioUI
from tools.final_answer import FinalAnswerTool


class TextToImageTool(Tool):
    description = "This tool creates an image according to a prompt, which is a text description."
    name = "image_generator"
    inputs = {"prompt":
                  {"type": "string",
                   "description": "The image generator prompt. Don't hesitate to add details in the prompt to make the image look better, like 'high-res, photorealistic', etc."}
              }
    output_type = "image"
    model_sdxl = "black-forest-labs/FLUX.1-schnell"
    client = InferenceClient(model_sdxl)


    def forward(self, prompt):
        updated_prompt = prompt + ". Don't use duplicate or overlapping texts. Make sure words used in the image are correctly spelled."
        # print(updated_prompt)
        return self.client.text_to_image(updated_prompt)

@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=0.1,
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)
image_generation_tool = TextToImageTool()
with open("prompts.yaml", 'r') as stream:
    prompt_templates = yaml.safe_load(stream)
    
agent = CodeAgent(
    model=model,
    tools=[image_generation_tool,final_answer], ## 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()