Update app.py

app.py

@@ -3,7 +3,6 @@ import requests
 import os
 from dotenv import load_dotenv
 from requests.exceptions import RequestException
-import time
 from nltk.sentiment import SentimentIntensityAnalyzer
 import nltk
 
@@ -34,66 +33,45 @@ model_pre_instructions = {
 # Initialize sentiment analyzer
 sia = SentimentIntensityAnalyzer()
 
-# Function to interact with the selected model via the Together API and perform sentiment analysis and diagnosis prediction
-def interact_with_together_api(messages, model_link):
-    all_messages = []
-
-    # Add pre-instructions to the message history if it's the first interaction with this model
-    if not any("role" in msg for msg in messages):
-        all_messages.append({"role": "system", "content": model_pre_instructions[selected_model]})
-    else:
-        all_messages.append({"role": "system", "content": f"Switched to model: {selected_model}"})
-
-    # Append user and assistant messages
-    for human, assistant in messages:
-        all_messages.append({"role": "user", "content": human})
-        all_messages.append({"role": "assistant", "content": assistant})
-
-    # Add the latest user message
-    all_messages.append({"role": "user", "content": messages[-1][1]})
-
-    url = "https://api.together.xyz/v1/chat/completions"
-    payload = {
-        "model": model_link,
-        "temperature": 1.05,
-        "top_p": 0.9,
-        "top_k": 50,
-        "repetition_penalty": 1,
-        "n": 1,
-        "messages": all_messages,
-    }
-
-    TOGETHER_API_KEY = os.getenv('TOGETHER_API_KEY')
-    headers = {
-        "accept": "application/json",
-        "content-type": "application/json",
-        "Authorization": f"Bearer {TOGETHER_API_KEY}",
+# Function to predict diagnosis based on sentiment analysis and chat content
+def predict_diagnosis(messages):
+    # Perform sentiment analysis
+    sentiment_score = sia.polarity_scores(messages[-1][1])  # Analyze only the last user message
+    
+    # Analyze chat content for specific mental health conditions
+    chat_text = " ".join([msg[1] for msg in messages if msg[0] == "user"])
+    
+    # Initialize diagnosis list
+    diagnoses = []
+
+    # Analyze chat content for specific mental health conditions
+    mental_conditions = {
+        "Depression": ["depression", "sad", "hopeless", "lonely", "empty", "worthless", "miserable"],
+        "Anxiety": ["anxiety", "nervous", "worried", "fearful", "panicked", "stressed", "tense"],
+        "Panic disorder": ["panic attack", "panic", "scared", "terrified", "frightened", "hyperventilate", "heart racing"],
+        "Bipolar disorder": ["bipolar", "manic", "mania", "euphoric", "energetic", "depressed", "hopeless"],
+        "Schizophrenia": ["schizophrenia", "hallucination", "delusion", "paranoia", "disorganized", "psychotic", "dissociation"],
+        "PTSD": ["ptsd", "trauma", "nightmare", "flashback", "startled", "avoidance", "hypervigilance"],
+        "Obsessive-Compulsive Disorder": ["ocd", "obsession", "compulsion", "intrusive thought", "ritual", "cleaning", "checking"],
+        "Eating disorder": ["eating disorder", "anorexia", "bulimia", "binge eating", "body image", "weight obsession", "purging"]
     }
 
-    try:
-        response = requests.post(url, json=payload, headers=headers)
-        response.raise_for_status()  # Ensure HTTP request was successful
-
-        # Extract response from JSON
-        response_data = response.json()
-        assistant_response = response_data["choices"][0]["message"]["content"]
-
-        # Perform sentiment analysis
-        sentiment_score = sia.polarity_scores(messages[-1][1])  # Analyze only the last user message
-        
-        # Predict diagnosis based on sentiment score and chat content
-        if sentiment_score['compound'] > 0.5:
-            diagnosis = "Positive mood"
-        elif sentiment_score['compound'] < -0.5:
-            diagnosis = "Negative mood"
+    for condition, keywords in mental_conditions.items():
+        for keyword in keywords:
+            if keyword in chat_text.lower():
+                diagnoses.append(condition)
+                break
+
+    # If no specific condition is detected, determine mood based on sentiment score
+    if not diagnoses:
+        if sentiment_score['compound'] > 0.1:
+            diagnoses.append("Positive mood")
+        elif sentiment_score['compound'] < -0.1:
+            diagnoses.append("Negative mood")
         else:
-            diagnosis = "Neutral mood"
+            diagnoses.append("Neutral mood")
 
-        return assistant_response, sentiment_score, diagnosis
-
-    except RequestException as e:
-        st.error(f"Error communicating with the API: {e}")
-        return None, None, None
+    return diagnoses
 
 # Create sidebar with model selection dropdown and reset button
 selected_model = st.sidebar.selectbox("Select Model", list(model_links.keys()), key="model_selection")
@@ -102,44 +80,14 @@ if st.session_state.get('selected_model') != selected_model:
     st.info(f"You have switched to {selected_model}.")
 st.sidebar.button('Reset Chat', on_click=reset_conversation)
 
-# Add cautionary message about testing phase at the bottom of the sidebar
-st.sidebar.markdown("**Note**: This model is still in the beta phase. Responses may be inaccurate or undesired. Use it cautiously, especially for critical issues.")
+# Display diagnosis based on chat messages
+diagnosis = predict_diagnosis(st.session_state.messages)
+st.sidebar.subheader("User Diagnosis")
+st.sidebar.write(", ".join(diagnosis))
 
 # Add logo and text to the sidebar
 st.sidebar.image("https://assets.isu.pub/document-structure/221118065013-a6029cf3d563afaf9b946bb9497d45d4/v1/2841525b232adaef7bd0efe1da81a4c5.jpeg", width=200)
 st.sidebar.write("A product proudly developed by Kisii University")
 
-# Initialize chat history
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-    st.session_state.message_count = 0
-    st.session_state.ask_intervention = False
-
-# Display chat messages from history on app rerun
-for message in st.session_state.messages:
-    with st.chat_message(message[0]):
-        st.markdown(message[1])
-
-# Accept user input
-if prompt := st.chat_input(f"Hi, I'm {selected_model}, let's chat"):
-    # Display user message in chat message container
-    with st.chat_message("user"):
-        st.markdown(prompt)
-    # Add user message to chat history
-    st.session_state.messages.append(("user", prompt))
-    st.session_state.message_count += 1
-
-    # Interact with the selected model and perform sentiment analysis and diagnosis prediction
-    assistant_response, sentiment_score, diagnosis = interact_with_together_api(st.session_state.messages, model_links[selected_model])
-
-    if assistant_response is not None:
-        # Display assistant response in chat message container
-        with st.chat_message("assistant"):
-            st.markdown(assistant_response)
-
-        # Update sidebar with sentiment analysis and diagnosis
-        st.sidebar.subheader("Sentiment Analysis")
-        st.sidebar.write(sentiment_score)
-
-        st.sidebar.subheader("User Diagnosis")
-        st.sidebar.write(diagnosis)
+# Add cautionary message about testing phase at the bottom of the sidebar
+st.sidebar.markdown("**Note**: This model is still in the beta phase. Responses may be inaccurate or undesired. Use it cautiously, especially for critical issues.")