Update src/app.py

src/app.py

@@ -2,6 +2,7 @@ import streamlit as st
 import cv2
 import numpy as np
 import os
+import tempfile                   # <-- 1. IMPORT TEMPFILE
 from dotenv import load_dotenv
 from st_audiorec import st_audiorec
 from analysis import (
@@ -11,7 +12,7 @@ from analysis import (
     get_llm_response
 )
 
-# --- LOAD .ENV FILE ---
+# Load the .env file
 load_dotenv()
 
 # Page configuration
@@ -21,102 +22,82 @@ st.set_page_config(
     layout="wide"
 )
 
-# --- SESSION STATE INITIALIZATION ---
-# This is the "secure vault" to save our data
-if "camera_bytes" not in st.session_state:
-    st.session_state.camera_bytes = None
-if "audio_bytes" not in st.session_state:
-    st.session_state.audio_bytes = None
-if "user_query" not in st.session_state:
-    st.session_state.user_query = ""
-
-# --- CALLBACK FUNCTIONS ---
-# These functions run *immediately* when a widget changes,
-# saving the data to the "secure vault" *before* the re-run.
-
-def camera_on_change():
-    """Saves the raw bytes of the photo or clears it."""
-    if st.session_state.camera_widget_buffer is not None:
-        st.session_state.camera_bytes = st.session_state.camera_widget_buffer.getvalue()
-    else:
-        st.session_state.camera_bytes = None
-
-def query_on_change():
-    """Saves the text query."""
-    st.session_state.user_query = st.session_state.query_widget_buffer
-
-# --- UI LAYOUT ---
-
+# Title and description
 st.title("🤖 Empathetic AI Assistant")
 st.markdown("""
 This AI assistant analyzes your emotional state through:
 - 📸 **Facial Expression** (from camera)
 - 🎤 **Vocal Tone** (from microphone)
 - 💬 **Spoken Words** (transcribed from audio)
+
+Then provides an empathetic, context-aware response to your query.
 """)
+
 st.divider()
 
+# Create two columns for layout
 col1, col2 = st.columns([1, 1])
 
 with col1:
     st.subheader("📸 1. Capture Your Expression")
-    # We MUST use 'key' and 'on_change'
-    st.camera_input(
-        "Take a snapshot", 
-        key="camera_widget_buffer", 
-        on_change=camera_on_change
-    )
+    camera_image = st.camera_input("Take a snapshot")
     
 with col2:
     st.subheader("💭 2. Your Query")
-    st.text_area(
+    user_query = st.text_area(
         "What would you like to ask?",
         placeholder="Type your question or concern here...",
-        height=100,
-        key="query_widget_buffer",
-        on_change=query_on_change
+        height=100
     )
 
 st.divider()
 
 st.subheader("🎙️ 3. Record Your Voice")
 st.write("Click the microphone to record your voice, then click 'Analyze' below.")
-audio_data = st_audiorec()
-
-# When new audio comes in, save it to our "vault"
-if audio_data is not None:
-    st.session_state.audio_bytes = audio_data
+audio_bytes = st_audiorec()
 
 st.divider()
 
-# --- ANALYSIS BUTTON ---
+# Main action button
 if st.button("🧠 Analyze My Emotion & Answer", type="primary", use_container_width=True):
     
-    # We check our "secure vault" variables, not the widgets
-    if not st.session_state.camera_bytes:
+    # Validation
+    if not camera_image:
         st.error("❌ Please take a snapshot using the camera first!")
-    elif not st.session_state.audio_bytes:
+    elif not audio_bytes:
         st.error("❌ Please record your voice first!")
-    elif not st.session_state.user_query.strip():
+    elif not user_query.strip():
         st.error("❌ Please enter your query!")
     else:
-        # --- PROCESSING ---
+        # Step 1: Process camera image
         with st.spinner("📸 Processing facial expression..."):
             try:
-                file_bytes = np.asarray(bytearray(st.session_state.camera_bytes), dtype=np.uint8)
+                file_bytes = np.asarray(bytearray(camera_image.read()), dtype=np.uint8)
                 image = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
-                cv2.imwrite("temp_image.jpg", image)
-                facial_emotion = get_facial_emotion("temp_image.jpg")
+                
+                # --- 2. USE A NAMED TEMPORARY FILE FOR THE IMAGE ---
+                with tempfile.NamedTemporaryFile(delete=True, suffix=".jpg") as temp_img:
+                    cv2.imwrite(temp_img.name, image)
+                    # Pass the unique temp file's name for analysis
+                    facial_emotion = get_facial_emotion(temp_img.name)
+                # The temp_img file is now automatically deleted
+                
             except Exception as e:
                 st.error(f"Error processing image: {e}")
                 facial_emotion = "neutral"
         
+        # Step 2: Process recorded audio
         with st.spinner("🎵 Saving and analyzing audio..."):
             try:
-                with open("temp_audio.wav", "wb") as f:
-                    f.write(st.session_state.audio_bytes)
-                voice_emotion = get_voice_emotion("temp_audio.wav")
-                transcript = get_transcript("temp_audio.wav")
+                # --- 3. USE A NAMED TEMPORARY FILE FOR THE AUDIO ---
+                with tempfile.NamedTemporaryFile(delete=True, suffix=".wav") as temp_aud:
+                    temp_aud.write(audio_bytes)
+                    
+                    # Pass the unique temp file's name for analysis
+                    voice_emotion = get_voice_emotion(temp_aud.name)
+                    transcript = get_transcript(temp_aud.name)
+                # The temp_aud file is now automatically deleted
+
             except Exception as e:
                 st.error(f"Error processing audio: {e}")
                 voice_emotion = "neutral"
@@ -125,27 +106,48 @@ if st.button("🧠 Analyze My Emotion & Answer", type="primary", use_container_w
         # Display analysis results
         st.divider()
         st.subheader("📊 Emotional Analysis Results")
+        
         col_a, col_b, col_c = st.columns(3)
-        with col_a: st.metric(label="😊 Facial Emotion", value=facial_emotion.capitalize())
-        with col_b: st.metric(label="🎤 Vocal Tone", value=voice_emotion.capitalize())
-        with col_c: st.metric(label="💬 Speech Detected", value="Yes" if transcript else "No")
-        if transcript: st.info(f"**Transcription:** {transcript}")
+        
+        with col_a:
+            st.metric(
+                label="😊 Facial Emotion",
+                value=facial_emotion.capitalize()
+            )
+        
+        with col_b:
+            st.metric(
+                label="🎤 Vocal Tone",
+                value=voice_emotion.capitalize()
+            )
+        
+        with col_c:
+            st.metric(
+                label="💬 Speech Detected",
+                value="Yes" if transcript else "No"
+            )
+        
+        if transcript:
+            st.info(f"**Transcription:** {transcript}")
         
         # Step 5: Get empathetic AI response
         st.divider()
         with st.spinner("🤖 Empathetic AI is thinking..."):
             ai_response = get_llm_response(
-                user_query=st.session_state.user_query, 
+                user_query=user_query,
                 face=facial_emotion,
                 voice=voice_emotion,
                 text=transcript
             )
         
+        # Display final response
         st.subheader("💙 Empathetic Response")
         st.markdown(ai_response)
+        
+        # Success feedback
         st.balloons()
 
-# --- SIDEBAR (No changes needed) ---
+# Sidebar with instructions
 with st.sidebar:
     st.header("ℹ️ How to Use")
     st.markdown("""
@@ -155,17 +157,23 @@ with st.sidebar:
     4. **Click the 'Analyze' button**
     5. **Receive** your response
     """)
+    
     st.divider()
+    
     st.header("🔑 Setup Requirements")
     st.markdown("""
-    Make sure these environment variables are set in your
-    Hugging Face Space **Settings > Repository secrets**:
+    Make sure these environment variables are set.
+    
+    Create a `.env` file in the same
+    directory as `app.py`:
     ```
     ROBOFLOW_API_KEY="your_key"
     GROQ_API_KEY="your_key"
     ```
     """)
+    
     st.divider()
+    
     st.header("🛠️ Tech Stack")
     st.markdown("""
     - **Frontend:** Streamlit