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

from googleapiclient.discovery import build
import os
from dotenv import load_dotenv
import uuid


# Google Books API setup
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/home/user/app/audiobookagent-aaf910cd6329.json"
google_api_key = os.getenv("AIzaSyDOxfDDznu39CSWR3wlGK-eEV2XH2zoGf4")
books_service = build("books", "v1", developerKey=google_api_key)



# I want to try connect to a google API to get some recommendation of audiobooks!
@tool
def search_audiobooks(topic: str, limit: int = 3)-> list[dict[str, any]]: #it's import to specify the return type
    #Keep this format for the description / args / args description but feel free to modify the tool
    """The tool is designed to connect to the google API platform and retrieve some audiobooks recommendations 
    Args:
        topic: the topic that I would like to use to retieve some audiobooks
        limit: it is a constant as I want to recommend only three audiobooks
    """
    request = books_service.volumes().list(
        q=f"subject:{topic}+audiobook",
        maxResults=limit,
        printType="books",
        gl="us"
    )
    response = request.execute()
    audiobooks = []
    for item in response.get("items", []):
        volume_info = item.get("volumeInfo", {})
        # Check if audiobook (based on categories or accessInfo)
        if "Audiobook" in volume_info.get("categories", []) or volume_info.get("accessInfo", {}).get("epub", {}).get("isAvailable", False):
            audiobooks.append({
                "title": volume_info.get("title", "Unknown"),
                "author": ", ".join(volume_info.get("authors", ["Unknown"])),
                "categories": ", ".join(volume_info.get("categories", ["Unknown"])),
                "url": volume_info.get("canonicalVolumeLink", "#"),
                "estimated_minutes": volume_info.get("pageCount", 180)  # Estimate: 1 page ≈ 1 minute
            })
    return audiobooks

@tool
# Function to estimate if audiobook fits time constraint
def filter_by_time(audiobooks: list[dict[str, any]], free_time: str) -> list[dict[str, any]]:
    """The tool is designed to match the time in terms of duration of the audiobook which is called estimated_minutes and the free time that the person have 
    Args:
        audiobooks: the list of the audiobooks
        free_time: The free time the person inform
    """
    try:
        if "hour" in free_time.lower():
            hours = float(free_time.split()[0])
            max_minutes = hours * 60
        else:
            max_minutes = float(free_time.split()[0])
    except:
        max_minutes = 180  # Default to 3 hours
    return [book for book in audiobooks if book["estimated_minutes"] <= max_minutes]

@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=0.5,
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)

prompt_templates["final_answer"] = "Final answer: {answer}"

agent = CodeAgent(
    model=model,
    tools=[final_answer,search_audiobooks,get_current_time_in_timezone,filter_by_time], ## 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()