app.py

#############################################################################################################################
# Filename   : app.py
# Description: A Streamlit application to detect facial expressions from images and provide responses.
# Author     : [Your Name]
#
# Copyright © 2024 by [Your Name]
#############################################################################################################################

# Import libraries.
import os  # Load environment variable(s).
import requests  # Send HTTP GET request to Hugging Face models for inference.
import streamlit as st  # Build the GUI of the application.
from PIL import Image  # Handle image operations.
from dotenv import load_dotenv  # Load environment variables.
import torch  # For tensor operations.
from transformers import AutoProcessor, AutoModelForImageClassification  # Hugging Face models.
import openai  # OpenAI API for generating text responses.

#############################################################################################################################
# Load environment variable(s).
load_dotenv()

# Set up the Hugging Face API for emotion detection.
HUGGINGFACE_API_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
# Set up OpenAI API key.
openai.api_key = os.getenv('OPENAI_API_KEY')

# Load the processor and model for facial expression recognition.
processor = AutoProcessor.from_pretrained("trpakov/vit-face-expression")
model = AutoModelForImageClassification.from_pretrained("trpakov/vit-face-expression")

#############################################################################################################################
# Function to query the facial expression recognition model.
def query_emotion(image):
    # Preprocess the image.
    inputs = processor(images=image, return_tensors="pt")

    # Perform inference.
    with torch.no_grad():
        outputs = model(**inputs)

    # Get predicted class index (the class with the highest logit).
    logits = outputs.logits
    predicted_class_idx = torch.argmax(logits, dim=-1).item()

    # Retrieve the label names from the model.
    label_names = model.config.id2label  # Mapping of indices to emotion labels.
    predicted_label = label_names[predicted_class_idx]  # Get the predicted label.

    return predicted_label

#############################################################################################################################
# Function to generate a response using OpenAI based on detected emotion.
def generate_text_based_on_mood(emotion):
    try:
        # Create a dynamic prompt based on the detected emotion.
        prompt = f"Generate a light-hearted joke or motivational message for someone who is feeling {emotion}."

        # Call OpenAI's API using GPT-4.
        response = openai.ChatCompletion.create(
            model="gpt-4",  # Specify the GPT-4 model.
            messages=[
                {"role": "user", "content": prompt}
            ]
        )

        # Extract the generated text.
        generated_text = response['choices'][0]['message']['content']
        return generated_text.strip()

    except Exception as e:
        st.error(f"Error generating text: {e}")
        return "Sorry, I couldn't come up with a message at this moment."

#############################################################################################################################
# Function to convert text to speech using gTTS.
def text_to_speech(text):
    from gtts import gTTS
    try:
        tts = gTTS(text, lang='en')
        audio_file = "output.mp3"
        tts.save(audio_file)  # Save the audio file.
        return audio_file
    except Exception as e:
        st.error(f"Error with TTS: {e}")
        return None

#############################################################################################################################
# Main function to create the Streamlit web application.
def main():
    st.title("Facial Expression Mood Detector")
    st.write("Upload an image of a face to detect mood and receive uplifting messages or jokes.")

    # Upload image.
    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

    if uploaded_file is not None:
        # Load and display the image.
        image = Image.open(uploaded_file)
        st.image(image, caption='Uploaded Image', use_column_width=True)

        # Detect facial expression.
        emotion = query_emotion(image)
        st.write(f"Detected emotion: {emotion}")

        # Generate text based on detected emotion.
        message = generate_text_based_on_mood(emotion)
        st.write("Here's something to remind you:")
        st.write(message)

        # Convert the generated message to audio.
        audio_file = text_to_speech(message)

        # Provide an audio player in the Streamlit app if audio file exists.
        if audio_file:
            st.audio(audio_file)  # Streamlit will handle playback.

#############################################################################################################################
# Run the application.
if __name__ == "__main__":
    main()