app.py

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

from Gradio_UI import GradioUI
from gradio_client import Client, handle_file

# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def image_to_3d(image_path:str)-> dict: #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 uses the HuggingFace Space "frogleo/Image-to-3D" to transform a 2D image into a 3D model
    Args:
        image_path: A string with the path to the 2D image that will be used
        
    """
    
    client = Client("frogleo/Image-to-3D")
    result = client.predict(
    		image=handle_file(image_path),
    		steps=5,
    		guidance_scale=5.5,
    		seed=1234,
    		octree_resolution=256,
    		num_chunks=8000,
    		target_face_num=10000,
    		randomize_seed=True,
    		api_name="/gen_shape"
    )
    print(result)
    
    return f"""
    MESH_GENERATION_RESULT

    Copy these exact fields into the final answer. Do not invent URLs. Do not omit any field.

    html_preview: {result[0]},

    file_export: {result[1]},

    glb_path: {result[2]},

    obj_path: {result[3]}
    """

@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 = InferenceClientModel(
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, 
        image_to_3d
    ], ## add your tools here (don't remove final answer)
    additional_authorized_imports=["json"],
    max_steps=6,
    instructions="""
    When the image_to_3d tool returns MESH_GENERATION_RESULT, your final answer must copy the html_preview, file_export, glb_path, and obj_path fields exactly. Do not say that a URL exists unless the tool returned that exact URL.
    """
   # prompt_templates=prompt_templates
)


GradioUI(agent, file_upload_folder="uploads").launch()