app.py

import os
import requests
import openai
import streamlit as st
from PIL import Image
from dotenv import load_dotenv
import time

# Load environment variables from .env file
load_dotenv()

# Set up the Hugging Face API URL and your API key
emotion_model_url = "https://api-inference.huggingface.co/models/trpakov/vit-face-expression"
headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}

# Set up OpenAI API key
openai.api_key = os.getenv('OPENAI_API_KEY')

# Function to query the facial expression recognition model
def query_emotion(filename):
    with open(filename, "rb") as f:
        data = f.read()
    response = requests.post(emotion_model_url, headers=headers, data=data)
    
    if response.status_code == 200:
        return response.json()
    else:
        st.error("Error detecting facial expression: " + response.text)
        return None

# 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
        if emotion == "happy":
            prompt = "Give a motivational quote to celebrate happiness."
        elif emotion == "sad":
            prompt = "Provide a comforting message for someone feeling sad."
        elif emotion == "angry":
            prompt = "Suggest a way to calm down someone feeling angry."
        elif emotion == "fear":
            prompt = "Give an encouraging message for someone feeling fearful."
        elif emotion == "surprised":
            prompt = "Offer a fun fact or light-hearted comment for someone feeling surprised."
        elif emotion == "neutral":
            prompt = "Provide a general motivational quote."
        
        # Call OpenAI's API using the new interface
        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

# Streamlit UI
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)

    # Save the uploaded file temporarily
    with open("uploaded_image.jpg", "wb") as f:
        f.write(uploaded_file.getbuffer())

    # Detect facial expression
    expression_output = query_emotion("uploaded_image.jpg")
    if expression_output:
        # Assuming the response has a 'label' field with the detected emotion
        emotion = expression_output[0]['label']  # Adjust based on response structure
        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 cheer you up:")
        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