Update app.py

app.py

@@ -3,70 +3,94 @@ import google.generativeai as genai
 import os
 from PIL import Image
 import numpy as np
-from deepface import DeepFace
+from deepface import DeepFace  # Replacing FER with DeepFace
 from dotenv import load_dotenv
 
+# Print out successful imports
+print("DeepFace is installed and ready to use!")
+print("Google Generative AI module is successfully imported!")
+
 # Load API keys and environment variables
 load_dotenv()
-genai.configure(api_key=os.getenv("GEMINI_API_KEY"))  # Use environment variable for security
+genai.configure(api_key="AIzaSyAEzZLb7R1CNTWwFXoUsWNrV47X9JgGu1o")
 
-# Gemini function for content generation
-def get_gemini_response(input_text):
+# gemini function for general content generation
+def get_gemini_response(input):
     try:
         model = genai.GenerativeModel('gemini-pro')
-        response = model.generate_content(input_text)
-        return response.text if response else "No response received."
+        response = model.generate_content(input)
+        return response
     except Exception as e:
-        st.error(f"Error with Gemini AI: {e}")
-        return "Error processing request."
+        # Handle quota exceeded error
+        if "RATE_LIMIT_EXCEEDED" in str(e):
+            st.error("Quota exceeded for content generation. Please try again later.")
+            return None
+        else:
+            st.error(f"Error: {e}")
+            return None
 
 # Function to analyze image for depression and emotion detection using DeepFace
 def detect_emotions(image):
     try:
+        # Convert PIL Image to NumPy array
         image_array = np.array(image)
+        # Use DeepFace to analyze emotions
         analysis = DeepFace.analyze(image_array, actions=['emotion'], enforce_detection=False)
-        if isinstance(analysis, list) and len(analysis) > 0:
-            emotions = analysis[0]['emotion']
-            dominant_emotion = max(emotions, key=emotions.get)  # Get emotion with highest percentage
-            return dominant_emotion, emotions
+        # Return the dominant emotion and its score
+        return analysis[0]['dominant_emotion'], analysis[0]['emotion']
     except Exception as e:
         st.error(f"Error during emotion detection: {e}")
-    return None, None
+        return None, None
 
 # Function to analyze detected emotions with LLM
-def analyze_emotions_with_llm(dominant_emotion, emotions):
-    emotions_text = "\n".join([f"{key}: {value:.2f}%" for key, value in emotions.items()])
+def analyze_emotions_with_llm(emotion, emotions):
+    emotion_analysis = f"{emotion}: {emotions[emotion]:.2f}"
     analysis_prompt = f"""
-    You are an expert in mental health. Analyze the following detected emotions and provide insights.
-    
+    ### As a mental health and emotional well-being expert, analyze the following detected emotions.
     ### Detected Emotions:
-    {emotions_text}
-    
-    ### Questions:
-    1. What does the dominant emotion '{dominant_emotion}' indicate?
-    2. Could these emotions be potential signs of depression?
-    3. What general recommendations would you give based on these emotions?
+    {emotion_analysis}
+    ### Analysis Output:
+    1. Identify any potential signs of depression based on the detected emotions.
     """
-    return get_gemini_response(analysis_prompt)
+    response = get_gemini_response(analysis_prompt)
+    return response
+
+# Function to parse and display response content
+def display_response_content(response):
+    st.subheader("Response Output")
+    if response and hasattr(response, 'candidates'):
+        response_content = response.candidates[0].content.parts[0].text if response.candidates[0].content.parts else ""
+        sections = response_content.split('###')
+        for section in sections:
+            if section.strip():
+                section_lines = section.split('\n')
+                section_title = section_lines[0].strip()
+                section_body = '\n'.join(line.strip() for line in section_lines[1:] if line.strip())
+                if section_title:
+                    st.markdown(f"**{section_title}**")
+                if section_body:
+                    st.write(section_body)
+    else:
+        st.write("No response received from the model or quota exceeded.")
 
-# Streamlit App UI
+# Streamlit App
 st.title("AI-Powered Depression and Emotion Detection System")
-st.text("Upload an image to analyze emotions and receive AI-based insights.")
+st.text("Use the AI system for detecting depression and emotions from images.")
 
-uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-if uploaded_file and st.button("Analyze Image"):
-    image = Image.open(uploaded_file)
-    st.image(image, caption="Uploaded Image", use_column_width=True)
-    
-    emotion, emotions = detect_emotions(image)
-    if emotion:
-        st.subheader("Detected Emotions:")
-        for key, value in emotions.items():
-            st.write(f"{key.capitalize()}: {value:.2f}%")
-        
-        # Get recommendations from AI
-        response = analyze_emotions_with_llm(emotion, emotions)
-        st.subheader("AI Analysis & Recommendations:")
-        st.write(response)
-    else:
-        st.error("No emotions detected. Try another image.")
+# Tabs for different functionalities (only image analysis in this version)
+with st.container():
+    st.header("Image Analysis")
+    uploaded_file = st.file_uploader("Upload an image for analysis", type=["jpg", "jpeg", "png"], help="Please upload an image file.")
+    submit_image = st.button('Analyze Image')
+
+    if submit_image:
+        if uploaded_file is not None:
+            image = Image.open(uploaded_file)  # Open the uploaded image
+            emotion, emotions = detect_emotions(image)  # Detect emotions using DeepFace
+            if emotion:  # If emotions are detected
+                response = analyze_emotions_with_llm(emotion, emotions)  # Analyze detected emotions with LLM
+                display_response_content(response)  # Display the analysis response
+            else:
+                st.write("No emotions detected in the image.")  # If no emotion is detected
+        else:
+            st.write("Please upload an image first.")  #