utils.py

import re
import os
import streamlit as st
from transformers import pipeline
from typing import Dict, Optional
from together import Together
from gtts import gTTS
from mail_sender import MailSender


# Image-to-text
def img2txt(url: str) -> str:
    print("Initializing captioning model...")
    captioning_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
    
    print("Generating text from the image...")
    text = captioning_model(url, max_new_tokens=20)[0]["generated_text"]
    
    print(text)
    return text

# Text-to-story generation with LLM model
def txt2story(prompt: str, top_k: int, top_p: float, temperature: float) -> str:
    # Load the Together API client
    client = Together(api_key=os.environ.get("TOGETHER_API_KEY"))

    # Modify the prompt based on user inputs and ensure a 250-word limit
    story_prompt = f"Write a short story of no more than 250 words based on the following prompt: {prompt}"

    # Call the LLM model
    stream = client.chat.completions.create(
        model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
        messages=[
            {"role": "system", "content": '''As an experienced short story writer, write a meaningful story influenced by the provided prompt.
            Ensure the story does not exceed 250 words.'''},
            {"role": "user", "content": story_prompt}
        ],
        top_k=top_k,
        top_p=top_p,
        temperature=temperature,
        stream=True
    )

    # Concatenate story chunks
    story = ''
    for chunk in stream:
        story += chunk.choices[0].delta.content

    return story

# Text-to-speech
def txt2speech(text: str) -> None:
    print("Converting text to speech using gTTS...")
    
    # Generate audio from the text
    tts = gTTS(text=text, lang='en')
    
    # Save the audio output to a file
    tts.save("audio_story.mp3")

# Get user preferences for the story
def get_user_preferences() -> Dict[str, str]:
    preferences = {
        'continent': st.selectbox("Continent", ["North America", "Europe", "Asia", "Africa", "Australia"]),
        'genre': st.selectbox("Genre", ["Science Fiction", "Fantasy", "Mystery", "Romance"]),
        'setting': st.selectbox("Setting", ["Future", "Medieval times", "Modern day", "Alternate reality"]),
        'plot': st.selectbox("Plot", ["Hero's journey", "Solving a mystery", "Love story", "Survival"]),
        'tone': st.selectbox("Tone", ["Serious", "Light-hearted", "Humorous", "Dark"]),
        'theme': st.selectbox("Theme", ["Self-discovery", "Redemption", "Love", "Justice"]),
        'conflict': st.selectbox("Conflict Type", ["Person vs. Society", "Internal struggle", "Person vs. Nature", "Person vs. Person"]),
        'twist': st.selectbox("Mystery/Twist", ["Plot twist", "Hidden identity", "Unexpected ally/enemy", "Time paradox"]),
        'ending': st.selectbox("Ending", ["Happy", "Bittersweet", "Open-ended", "Tragic"])
    }
    return preferences


def send_story_email(recipient_email: str, story_text: str, audio_file_path: str) -> bool:
    """
    Send the story text and audio file to the specified email address using python-mail-sender
    Returns True if successful, False otherwise
    """
    try:
        # Initialize the MailSender with env variables
        mail_sender = MailSender()
        
        # Email configuration
        subject = "Your Generated Story"
        content = f"Here's your generated story:\n\n{story_text}\n\nEnjoy!"
        
        # Send email
        mail_sender.send_mail(
            receiver_address=recipient_email,
            subject=subject,
            email_content=content,
            attached_files=[audio_file_path]
        )
        return True
        
    except Exception as e:
        print(f"Error sending email: {str(e)}")
        return False

def validate_email(email: str) -> bool:
    """
    Basic email validation
    """
    pattern = r'^[\w\.-]+@[\w\.-]+\.\w+$'
    return re.match(pattern, email) is not None