Update app.py

app.py

@@ -1,41 +1,87 @@
-import streamlit as st
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+# import streamlit as st
+# from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+
+# # Load chatbot model
+# chatbot_model = "microsoft/DialoGPT-medium"
+# tokenizer = AutoTokenizer.from_pretrained(chatbot_model)
+# model = AutoModelForCausalLM.from_pretrained(chatbot_model)
+
+# # Load emotion detection model
+# emotion_pipeline = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base")
+
+# st.title("🧠 Mental Health Chatbot")
+
+# # Chat history
+# if "chat_history" not in st.session_state:
+#     st.session_state.chat_history = []
+
+# # User Input
+# user_input = st.text_input("You:", key="user_input")
+
+# if st.button("Send"):
+#     if user_input:
+#         # Generate chatbot response
+#         input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
+#         output = model.generate(input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id)
+#         response = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+
+#         # Detect emotion
+#         emotion_result = emotion_pipeline(user_input)
+#         emotion = emotion_result[0]["label"]
 
-# Load chatbot model
-chatbot_model = "microsoft/DialoGPT-medium"
-tokenizer = AutoTokenizer.from_pretrained(chatbot_model)
-model = AutoModelForCausalLM.from_pretrained(chatbot_model)
+#         # Store chat history
+#         st.session_state.chat_history.append(("You", user_input))
+#         st.session_state.chat_history.append(("Bot", response))
 
-# Load emotion detection model
-emotion_pipeline = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base")
+#         # Display chat
+#         for sender, msg in st.session_state.chat_history:
+#             st.write(f"**{sender}:** {msg}")
 
-st.title("🧠 Mental Health Chatbot")
+#         # Display emotion
+#         st.write(f"🧠 **Emotion Detected:** {emotion}")
 
-# Chat history
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
+
+
+import streamlit as st
+
+st.title("🧠 Mental Health Assistant Bot")
 
 # User Input
-user_input = st.text_input("You:", key="user_input")
+user_input = st.text_input("How are you feeling today?", "")
 
-if st.button("Send"):
+if st.button("Submit"):
     if user_input:
-        # Generate chatbot response
-        input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
-        output = model.generate(input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id)
-        response = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+        # Get Emotion Analysis
+        emotion_result = emotion_pipeline(user_input)[0]
+        st.write(f"**Emotion Detected:** {emotion_result['label']} ({emotion_result['score']:.2f})")
+
+        # Get Mental Health Condition Analysis
+        mental_health_result = mental_bert_pipeline(user_input)[0]
+        st.write(f"**Possible Mental Health Condition:** {mental_health_result['label']} ({mental_health_result['score']:.2f})")
+
+        # Get Stress Level Analysis
+        stress_result = stress_pipeline(user_input)[0]
+        st.write(f"**Stress Level:** {stress_result['label']} ({stress_result['score']:.2f})")
+
+        # Chatbot Response using DeepSeek AI
+        deepseek_response = deepseek_pipeline(user_input, max_length=100, do_sample=True)[0]['generated_text']
+        st.write(f"🤖 **Chatbot:** {deepseek_response}")
+
+# Question Answering Section
+st.subheader("Ask Mental Health Questions")
+user_question = st.text_input("Ask me anything about mental health:", "")
 
-        # Detect emotion
-        emotion_result = emotion_pipeline(user_input)
-        emotion = emotion_result[0]["label"]
+if st.button("Ask"):
+    if user_question:
+        answer = qa_pipeline(question=user_question, context="Mental health is important for overall well-being.")
+        st.write(f"**Answer:** {answer['answer']}")
 
-        # Store chat history
-        st.session_state.chat_history.append(("You", user_input))
-        st.session_state.chat_history.append(("Bot", response))
+# PHQ-9 Depression Assessment
+st.subheader("Depression Severity Assessment (PHQ-9)")
+phq9_question = st.text_input("Describe your mood over the last two weeks:", "")
 
-        # Display chat
-        for sender, msg in st.session_state.chat_history:
-            st.write(f"**{sender}:** {msg}")
+if st.button("Analyze Depression Level"):
+    if phq9_question:
+        phq9_result = phq9_pipeline(phq9_question)[0]
+        st.write(f"**PHQ-9 Score Suggests:** {phq9_result['label']} ({phq9_result['score']:.2f})")
 
-        # Display emotion
-        st.write(f"🧠 **Emotion Detected:** {emotion}")