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
import os, io
from PIL import Image
from smolagents.agent_types import AgentImage
from smolagents import tool
from PIL import Image as PILImage


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 text_to_image(prompt: str) -> AgentImage:
    """Generate an image from text via Hugging Face Inference API (sdxl-turbo).
    Args:
        prompt: The image description in English.
    """
    hf_token = os.getenv("HF_TOKEN")
    if not hf_token:
        raise RuntimeError("HF_TOKEN is missing. Add it in Settings → Variables and Secrets.")

    headers = {"Authorization": f"Bearer {hf_token}", "Accept": "image/png"}
    url = "https://api-inference.huggingface.co/models/stabilityai/sdxl-turbo"

    resp = requests.post(url, headers=headers, json={"inputs": prompt}, timeout=120)
    if resp.status_code != 200:
        # 让错误清晰可见（到 Logs）
        raise RuntimeError(f"Inference API error {resp.status_code}: {resp.text[:300]}")

    img = Image.open(io.BytesIO(resp.content)).convert("RGB")
    return AgentImage(img)


@tool
def generate_image(prompt: str) -> AgentImage:
    """Generate an image and return AgentImage for UI rendering.
    Args:
        prompt: The image description.
    """
    hf_token = os.getenv("HF_TOKEN")
    if not hf_token:
        raise RuntimeError("HF_TOKEN is missing. Add it in Settings → Variables and Secrets.")

    headers = {"Authorization": f"Bearer {hf_token}", "Accept": "image/png"}
    url = "https://api-inference.huggingface.co/models/stabilityai/sdxl-turbo"

    resp = requests.post(url, headers=headers, json={"inputs": prompt}, timeout=120)
    if resp.status_code != 200:
        raise RuntimeError(f"Inference API error {resp.status_code}: {resp.text[:300]}")

    img = Image.open(io.BytesIO(resp.content)).convert("RGB")
    return AgentImage(img)

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
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, DuckDuckGoSearchTool(),  get_current_time_in_timezone, text_to_image , generate_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()