Update app.py

app.py

@@ -1,5 +1,5 @@
 from fastai.text.all import *
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 import gradio as gr
 
@@ -15,7 +15,7 @@ def classify_medical_text(txt):
     return dict(zip(medical_categories, map(float, probs)))
 
 # Load the psychiatric model from Hugging Face
-psychiatric_model_name = "nlp4good/psych-search"  # Replace with the appropriate model
+psychiatric_model_name = "mental/mental-bert-base-uncased"  # Replace with the appropriate model
 psychiatric_tokenizer = AutoTokenizer.from_pretrained(psychiatric_model_name)
 psychiatric_model = AutoModelForSequenceClassification.from_pretrained(psychiatric_model_name)
 
@@ -31,6 +31,27 @@ def classify_psychiatric_text(txt):
     probabilities = torch.softmax(logits, dim=1).squeeze().tolist()
     return dict(zip(psychiatric_labels, probabilities))
 
+# Load pre-trained conversational model for Lifestyle and Nutrition Chatbot
+lifestyle_model_name = "microsoft/DialoGPT-medium"  # Replace with a fine-tuned model if available
+lifestyle_tokenizer = AutoTokenizer.from_pretrained(lifestyle_model_name)
+lifestyle_model = AutoModelForCausalLM.from_pretrained(lifestyle_model_name)
+
+# Chat function for Lifestyle and Nutrition
+chat_history = []
+
+def chatbot_response(user_input):
+    global chat_history
+    new_input_ids = lifestyle_tokenizer.encode(user_input + lifestyle_tokenizer.eos_token, return_tensors='pt')
+    bot_input_ids = torch.cat([chat_history, new_input_ids], dim=-1) if chat_history else new_input_ids
+    chat_history = lifestyle_model.generate(bot_input_ids, max_length=1000, pad_token_id=lifestyle_tokenizer.eos_token_id)
+    response = lifestyle_tokenizer.decode(chat_history[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return response
+
+def clear_chat():
+    global chat_history
+    chat_history = []
+    return []
+
 # Gradio Interfaces
 medical_text = gr.Textbox(lines=2, label='Describe your symptoms in detail')
 medical_label = gr.Label()
@@ -40,6 +61,17 @@ psychiatric_text = gr.Textbox(lines=2, label='Describe your mental health concer
 psychiatric_label = gr.Label()
 psychiatric_examples = ['I feel hopeless and have no energy.', 'I am unable to concentrate and feel anxious all the time.', 'I have recurring intrusive thoughts.']
 
+lifestyle_chatbot = gr.Chatbot(label="Chat with me about your health and nutrition!")
+lifestyle_msg = gr.Textbox(placeholder="Ask your question here...", label="Your Question")
+lifestyle_clear = gr.Button("Clear Chat")
+
+def user_message(input_text):
+    if not input_text.strip():
+        return lifestyle_chatbot, "Please enter a question."
+    response = chatbot_response(input_text)
+    lifestyle_chatbot.append((input_text, response))
+    return lifestyle_chatbot, ""
+
 medical_interface = gr.Interface(
     fn=classify_medical_text,
     inputs=medical_text,
@@ -56,6 +88,16 @@ psychiatric_interface = gr.Interface(
     description=psychiatric_description,
 )
 
+with gr.Blocks() as lifestyle_interface:
+    gr.Markdown("## Lifestyle and Nutrition Chatbot")
+    gr.Markdown("Ask me anything about fitness, nutrition, or wellness!")
+    lifestyle_msg.submit(user_message, inputs=[lifestyle_msg], outputs=[lifestyle_chatbot, lifestyle_msg])
+    lifestyle_clear.click(clear_chat, outputs=[lifestyle_chatbot])
+
 # Combine interfaces using Tabs
-app = gr.TabbedInterface([medical_interface, psychiatric_interface], ["Medical Diagnosis", "Psychiatric Analysis"])
+app = gr.TabbedInterface(
+    [medical_interface, psychiatric_interface, lifestyle_interface],
+    ["Medical Diagnosis", "Psychiatric Analysis", "Lifestyle & Nutrition Chat"]
+)
+
 app.launch(inline=False)