app.py

from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
import datetime
import requests
import pytz
import yaml
import time
import logging
from tools.final_answer import FinalAnswerTool
from tools.text_analysis import analyze_text

from Gradio_UI import GradioUI

# Set up logging
logger = logging.getLogger(__name__)


# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_cutom_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)}"


final_answer = FinalAnswerTool()


class RetryingHfApiModel(HfApiModel):
    """HfApiModel with retry logic for rate limiting"""

    def __init__(self, max_retries=3, retry_delay=2, **kwargs):
        super().__init__(**kwargs)
        self.max_retries = max_retries
        self.retry_delay = retry_delay

    async def async_chat(self, *args, **kwargs):
        for attempt in range(self.max_retries):
            try:
                return await super().async_chat(*args, **kwargs)
            except Exception as e:
                if "429" in str(e) and attempt < self.max_retries - 1:
                    wait_time = self.retry_delay * (attempt + 1)  # Exponential backoff
                    logger.warning(f"Rate limited. Retrying in {wait_time} seconds...")
                    time.sleep(wait_time)
                    continue
                raise  # Re-raise the exception if it's not a 429 or we're out of retries


# Replace the model initialization with our retrying version
model = RetryingHfApiModel(
    max_tokens=2096,
    temperature=0.5,
    model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
    custom_role_conversions=None,
    max_retries=3,  # Will try up to 3 times
    retry_delay=2,  # Start with 2 second delay, will increase with each retry
)

# 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, analyze_text],  # Added analyze_text tool
    max_steps=6,
    verbosity_level=1,
    grammar=None,
    planning_interval=None,
    name=None,
    description=None,
    prompt_templates=prompt_templates,
)


GradioUI(agent).launch()