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
from googleapiclient.errors import HttpError
from google.oauth2 import service_account
import os
from dotenv import load_dotenv
import uuid


# Google Books API setup with Service Account
json_key_path: str = "/home/user/app/audiobookagent-aaf910cd6329.json" 
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = json_key_path
try:
    credentials = service_account.Credentials.from_service_account_file(
        json_key_path,
        scopes=["https://www.googleapis.com/auth/books"]
    )
except FileNotFoundError:
    raise FileNotFoundError(f"JSON key file not found at {json_key_path}. Please upload it to /app/.")
books_service = build("books", "v1", credentials=credentials)



# 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]]:
    """
    Search Google Play Books for audiobooks by topic.
    
    Args:
        topic (str): Genre or topic to search (e.g., "science").
        limit (int): Maximum number of results to return (default: 3).
    
    Returns:
        List[Dict[str, Any]]: List of audiobook metadata dictionaries.
    """
    audiobooks: list[dict[str, any]] = []
    queries: list[str] = [f"{topic}", f"audiobook {topic}", "fiction audiobook"]  # Broad queries
    
    for query in queries:
        try:
            request = books_service.volumes().list(
                q=query,
                maxResults=limit,
                printType="books"
            )
            response: dict[str, any] = request.execute()
            with open("debug_log.txt", "a") as f:
                f.write(f"API response for query '{query}': {json.dumps(response.get('items', []), indent=2)}\n")
            
            for item in response.get("items", []):
                volume_info: dict[str, any] = item.get("volumeInfo", {})
                categories: list[str] = volume_info.get("categories", [])
                title: str = volume_info.get("title", "")
                description: str = volume_info.get("description", "")
                with open("debug_log.txt", "a") as f:
                    f.write(f"Item: title='{title}', categories={categories}, description='{description[:100]}...'\n")
                
                # No filtering: return all results for debugging
                audiobooks.append({
                    "title": title or "Unknown",
                    "author": ", ".join(volume_info.get("authors", ["Unknown"])),
                    "categories": ", ".join(categories or ["Unknown"]),
                    "url": volume_info.get("canonicalVolumeLink", "#"),
                    "estimated_minutes": volume_info.get("pageCount", 180)
                })
            
            if audiobooks:
                with open("debug_log.txt", "a") as f:
                    f.write(f"Found {len(audiobooks)} audiobooks for query '{query}'\n")
                break
        except HttpError as e:
            with open("debug_log.txt", "a") as f:
                f.write(f"Google Books API error for query '{query}': {e}\n")
            continue
        except Exception as e:
            with open("debug_log.txt", "a") as f:
                f.write(f"Unexpected error in search_audiobooks for query '{query}': {e}\n")
            continue
    
    if not audiobooks:
        with open("debug_log.txt", "a") as f:
            f.write(f"No audiobooks found for topic: {topic} across all queries\n")
    return audiobooks[:limit]


@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)


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