Update src/app.py

src/app.py

@@ -1,28 +1,207 @@
+# import streamlit as st
+# import cv2
+# import numpy as np
+# import os
+# from dotenv import load_dotenv
+# from st_audiorec import st_audiorec
+# from analysis import (
+#     get_facial_emotion,
+#     get_voice_emotion,
+#     get_transcript,
+#     get_llm_response
+# )
+
+# # --- LOAD .ENV FILE ---
+# load_dotenv()
+
+# # Page configuration
+# st.set_page_config(
+#     page_title="Empathetic AI Assistant",
+#     page_icon="🤖",
+#     layout="wide"
+# )
+
+# # --- SESSION STATE INITIALIZATION ---
+# # Initialize all our state variables securely
+# 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.
+# # This is the key to saving the data before a re-run erases it.
+
+# def camera_on_change():
+#     """Saves the raw bytes of the photo or clears it."""
+#     # 'camera_widget_buffer' is the key we give to the camera
+#     if st.session_state.camera_widget_buffer is not None:
+#         st.session_state.camera_bytes = st.session_state.camera_widget_buffer.getvalue()
+#     else:
+#         # User must have clicked "Clear photo"
+#         st.session_state.camera_bytes = None
+
+# def query_on_change():
+#     """Saves the text query."""
+#     # 'query_widget_buffer' is the key we give to the text_area
+#     st.session_state.user_query = st.session_state.query_widget_buffer
+
+# # --- UI LAYOUT ---
+
+# 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()
+
+# col1, col2 = st.columns([1, 1])
+
+# with col1:
+#     st.subheader("📸 1. Capture Your Expression")
+#     # Use the 'key' and 'on_change' parameters.
+#     st.camera_input(
+#         "Take a snapshot", 
+#         key="camera_widget_buffer", 
+#         on_change=camera_on_change
+#     )
+    
+# with col2:
+#     st.subheader("💭 2. Your 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
+#     )
+
+# 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()
+
+# # We manually save the audio data if it's new
+# if audio_data is not None:
+#     st.session_state.audio_bytes = audio_data
+
+# st.divider()
+
+# # --- ANALYSIS BUTTON ---
+# if st.button("🧠 Analyze My Emotion & Answer", type="primary", use_container_width=True):
+    
+#     # Now, we check our *secure* session state variables
+#     if not st.session_state.camera_bytes:
+#         st.error("❌ Please take a snapshot using the camera first!")
+#     elif not st.session_state.audio_bytes:
+#         st.error("❌ Please record your voice first!")
+#     elif not st.session_state.user_query.strip():
+#         st.error("❌ Please enter your query!")
+#     else:
+#         # --- PROCESSING ---
+#         # All data is guaranteed to be safe in session_state
+        
+#         # 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)
+#                 image = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+#                 cv2.imwrite("temp_image.jpg", image)
+#                 facial_emotion = get_facial_emotion("temp_image.jpg")
+                
+#             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")
+
+#             except Exception as e:
+#                 st.error(f"Error processing audio: {e}")
+#                 voice_emotion = "neutral"
+#                 transcript = ""
+        
+#         # 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}")
+        
+#         # 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, # Use query from state
+#                 face=facial_emotion,
+#                 voice=voice_emotion,
+#                 text=transcript
+#             )
+        
+#         st.subheader("💙 Empathetic Response")
+#         st.markdown(ai_response)
+#         st.balloons()
+
+# # --- SIDEBAR (Unchanged) ---
+# with st.sidebar:
+#     st.header("ℹ️ How to Use")
+#     st.markdown("""
+#     1. **Take a snapshot**
+#     2. **Type your query**
+#     3. **Click the mic** to record (click again to stop)
+#     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**:
+#     ```
+#     ROBOFLOW_API_KEY="your_key"
+#     GROQ_API_KEY="your_key"
+#     ```
+#     """)
+#     st.divider()
+#     st.header("🛠️ Tech Stack")
+#     st.markdown("""
+#     - **Frontend:** Streamlit
+#     - **Audio:** `streamlit-audiorec`
+#     - **Facial Analysis:** Roboflow
+#     - **Voice Analysis:** Hugging Face
+#     - **Speech-to-Text:** Google SR
+#     - **LLM:** Groq (Llama 3)
+#     """)
+
+
 import streamlit as st
-import cv2
 import numpy as np
-import os
-from dotenv import load_dotenv
-from st_audiorec import st_audiorec
-from analysis import (
-    get_facial_emotion,
-    get_voice_emotion,
-    get_transcript,
-    get_llm_response
-)
-
-# --- LOAD .ENV FILE ---
-load_dotenv()
+import cv2
 
-# Page configuration
+# --- Page Config (MUST be the first Streamlit command) ---
 st.set_page_config(
-    page_title="Empathetic AI Assistant",
-    page_icon="🤖",
+    page_title="Step 1: Capture",
+    page_icon="📸",
     layout="wide"
 )
 
 # --- SESSION STATE INITIALIZATION ---
-# Initialize all our state variables securely
+# Initialize all variables that need to be passed between pages
 if "camera_bytes" not in st.session_state:
     st.session_state.camera_bytes = None
 if "audio_bytes" not in st.session_state:
@@ -30,48 +209,37 @@ if "audio_bytes" not in st.session_state:
 if "user_query" not in st.session_state:
     st.session_state.user_query = ""
 
-# --- CALLBACK FUNCTIONS ---
-# These functions run *immediately* when a widget changes.
-# This is the key to saving the data before a re-run erases it.
-
+# --- Callback Functions ---
 def camera_on_change():
-    """Saves the raw bytes of the photo or clears it."""
-    # 'camera_widget_buffer' is the key we give to the camera
+    """Saves the raw bytes of the photo."""
     if st.session_state.camera_widget_buffer is not None:
         st.session_state.camera_bytes = st.session_state.camera_widget_buffer.getvalue()
     else:
-        # User must have clicked "Clear photo"
         st.session_state.camera_bytes = None
 
 def query_on_change():
     """Saves the text query."""
-    # 'query_widget_buffer' is the key we give to the text_area
     st.session_state.user_query = st.session_state.query_widget_buffer
 
-# --- UI LAYOUT ---
-
+# --- Page Layout ---
 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.header("Step 1: Provide Your Inputs")
 st.divider()
 
 col1, col2 = st.columns([1, 1])
 
 with col1:
     st.subheader("📸 1. Capture Your Expression")
-    # Use the 'key' and 'on_change' parameters.
     st.camera_input(
         "Take a snapshot", 
         key="camera_widget_buffer", 
         on_change=camera_on_change
     )
     
+    # --- Show a confirmation that the photo is saved ---
+    if st.session_state.camera_bytes:
+        st.success("✅ Photo captured and saved!")
+
 with col2:
     st.subheader("💭 2. Your Query")
     st.text_area(
@@ -81,109 +249,28 @@ with col2:
         key="query_widget_buffer",
         on_change=query_on_change
     )
+    
+    # --- Show a confirmation that the query is saved ---
+    if st.session_state.user_query:
+        st.success("✅ Query saved!")
 
 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()
-
-# We manually save the audio data if it's new
-if audio_data is not None:
-    st.session_state.audio_bytes = audio_data
-
-st.divider()
-
-# --- ANALYSIS BUTTON ---
-if st.button("🧠 Analyze My Emotion & Answer", type="primary", use_container_width=True):
-    
-    # Now, we check our *secure* session state variables
-    if not st.session_state.camera_bytes:
-        st.error("❌ Please take a snapshot using the camera first!")
-    elif not st.session_state.audio_bytes:
-        st.error("❌ Please record your voice first!")
-    elif not st.session_state.user_query.strip():
-        st.error("❌ Please enter your query!")
-    else:
-        # --- PROCESSING ---
-        # All data is guaranteed to be safe in session_state
-        
-        # 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)
-                image = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
-                cv2.imwrite("temp_image.jpg", image)
-                facial_emotion = get_facial_emotion("temp_image.jpg")
-                
-            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")
+# --- Navigation Button ---
+st.write("Once your photo is captured and your query is typed, proceed to the next step.")
 
-            except Exception as e:
-                st.error(f"Error processing audio: {e}")
-                voice_emotion = "neutral"
-                transcript = ""
-        
-        # 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}")
-        
-        # 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, # Use query from state
-                face=facial_emotion,
-                voice=voice_emotion,
-                text=transcript
-            )
-        
-        st.subheader("💙 Empathetic Response")
-        st.markdown(ai_response)
-        st.balloons()
+# Check if inputs are ready
+if st.session_state.camera_bytes and st.session_state.user_query:
+    if st.button("Go to Step 2: Record Voice 🎤", type="primary", use_container_width=True):
+        st.switch_page("pages/2_Analyze.py")
+else:
+    st.warning("Please take a photo and enter a query to continue.")
 
-# --- SIDEBAR (Unchanged) ---
+# --- Sidebar ---
 with st.sidebar:
-    st.header("ℹ️ How to Use")
+    st.header("Instructions")
     st.markdown("""
     1. **Take a snapshot**
     2. **Type your query**
-    3. **Click the mic** to record (click again to stop)
-    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**:
-    ```
-    ROBOFLOW_API_KEY="your_key"
-    GROQ_API_KEY="your_key"
-    ```
-    """)
-    st.divider()
-    st.header("🛠️ Tech Stack")
-    st.markdown("""
-    - **Frontend:** Streamlit
-    - **Audio:** `streamlit-audiorec`
-    - **Facial Analysis:** Roboflow
-    - **Voice Analysis:** Hugging Face
-    - **Speech-to-Text:** Google SR
-    - **LLM:** Groq (Llama 3)
+    3. Click **'Go to Step 2'**
     """)