Update app.py

app.py

@@ -1,27 +1,29 @@
 import streamlit as st
-from transformers import RagRetriever, RagTokenizer, RagTokenForGeneration
+import requests
 
-# Load the RAG model
-@st.cache_resource
-def load_rag_model():
-    retriever = RagRetriever.from_pretrained("facebook/rag-token-nq")
-    tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
-    rag_model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever)
-    return tokenizer, retriever, rag_model
+# Hugging Face API details
+API_URL = "https://api-inference.huggingface.co/models/facebook/blenderbot-400M-distill"
+headers = {"Authorization": f"Bearer {api_key}"}
 
-# Set up the Streamlit interface
-def main():
-    st.title("Mental Health Chatbot")
+# Function to query the model
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
 
-    tokenizer, retriever, rag_model = load_rag_model()
+# Streamlit UI for Mental Health Chatbot
+st.title("Mental Health Chatbot")
+st.write("""
+This chatbot provides responses to mental health-related queries. 
+Please note that this is an AI-based tool and is not a substitute for professional mental health support.
+""")
 
-    user_input = st.text_input("Ask me something about mental health:")
-    
-    if user_input:
-        input_ids = tokenizer(user_input, return_tensors="pt").input_ids
-        output = rag_model.generate(input_ids)
-        response = tokenizer.decode(output[0], skip_special_tokens=True)
-        st.write(f"Response: {response}")
+# User input
+user_input = st.text_input("How can I help you today?")
 
-if __name__ == "__main__":
-    main()
+if st.button("Get Response"):
+    if user_input:
+        # Query the model
+        output = query({"inputs": user_input})
+        st.write(f"**Response:** {output['generated_text']}")
+    else:
+        st.write("Please enter a query to get a response.")