Update app.py

app.py

@@ -1,117 +1,37 @@
-import os
 import streamlit as st
-import requests
-from transformers import pipeline
-from typing import Dict
-from together import Together
+from utils import img2txt, txt2story, txt2speech, get_user_preferences
 
-# 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("Initializing text-to-speech conversion...")
-    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
-    headers = {"Authorization": f"Bearer {os.environ['HUGGINGFACEHUB_API_TOKEN']}"}
-    payloads = {'inputs': text}
-    
-    response = requests.post(API_URL, headers=headers, json=payloads)
-    
-    with open('audio_story.mp3', 'wb') as file:
-        file.write(response.content)
-
-# Get user preferences for the story
-def get_user_preferences() -> Dict[str, str]:
-    preferences = {}
-
-    preferences['continent'] = st.selectbox("Continent", ["North America", "Europe", "Asia", "Africa", "Australia"])
-    preferences['genre'] = st.selectbox("Genre", ["Science Fiction", "Fantasy", "Mystery", "Romance"])
-    preferences['setting'] = st.selectbox("Setting", ["Future", "Medieval times", "Modern day", "Alternate reality"])
-    preferences['plot'] = st.selectbox("Plot", ["Hero's journey", "Solving a mystery", "Love story", "Survival"])
-    preferences['tone'] = st.selectbox("Tone", ["Serious", "Light-hearted", "Humorous", "Dark"])
-    preferences['theme'] = st.selectbox("Theme", ["Self-discovery", "Redemption", "Love", "Justice"])
-    preferences['conflict'] = st.selectbox("Conflict Type", ["Person vs. Society", "Internal struggle", "Person vs. Nature", "Person vs. Person"])
-    preferences['twist'] = st.selectbox("Mystery/Twist", ["Plot twist", "Hidden identity", "Unexpected ally/enemy", "Time paradox"])
-    preferences['ending'] = st.selectbox("Ending", ["Happy", "Bittersweet", "Open-ended", "Tragic"])
-    
-    return preferences
-
-# Main function
 def main():
     st.set_page_config(page_title="🎨 Image-to-Audio Story 🎧", page_icon="🖼️")
     st.title("Turn the Image into Audio Story")
 
-    # Allows users to upload an image file
     uploaded_file = st.file_uploader("# 📷 Upload an image...", type=["jpg", "jpeg", "png"])
 
-    # Parameters for LLM model (in the sidebar)
     st.sidebar.markdown("# LLM Inference Configuration Parameters")
     top_k = st.sidebar.number_input("Top-K", min_value=1, max_value=100, value=5)
     top_p = st.sidebar.number_input("Top-P", min_value=0.0, max_value=1.0, value=0.8)
     temperature = st.sidebar.number_input("Temperature", min_value=0.1, max_value=2.0, value=1.5)
 
-    # Get user preferences for the story
     st.markdown("## Story Preferences")
-    preferences = get_user_preferences()
+    preferences = get_user_preferences(st)
 
     if uploaded_file is not None:
-        # Reads and saves uploaded image file
         bytes_data = uploaded_file.read()
         with open("uploaded_image.jpg", "wb") as file:
             file.write(bytes_data)
 
         st.image(uploaded_file, caption='🖼️ Uploaded Image', use_column_width=True)
 
-        # Initiates AI processing and story generation
         with st.spinner("## 🤖 AI is at Work! "):
-            scenario = img2txt("uploaded_image.jpg")  # Extracts text from the image
+            scenario = img2txt("uploaded_image.jpg")
             
-            # Modify the prompt to include user preferences
             prompt = f"Based on the image description: '{scenario}', create a {preferences['genre']} story set in {preferences['setting']} in {preferences['continent']}. " \
                      f"The story should have a {preferences['tone']} tone and explore the theme of {preferences['theme']}. " \
                      f"The main conflict should be {preferences['conflict']}. " \
                      f"The story should have a {preferences['twist']} and end with a {preferences['ending']} ending."
             
-            story = txt2story(prompt, top_k, top_p, temperature)  # Generates a story based on the image text, LLM params, and user preferences
-            
-            txt2speech(story)  # Converts the story to audio
+            story = txt2story(prompt, top_k, top_p, temperature)
+            txt2speech(story)
 
             st.markdown("---")
             st.markdown("## 📜 Image Caption")