Update app.py

app.py

@@ -1,9 +1,12 @@
 # app.py
+import os
+import requests
 import streamlit as st
-from models import load_model
+from models import get_hf_api
 
-# Load the model once
-generator = load_model()
+# Configure API
+API_URL = get_hf_api()
+headers = {"Authorization": f"Bearer {st.secrets['HF_TOKEN']}"}
 
 # Page configuration
 st.set_page_config(
@@ -16,82 +19,75 @@ st.set_page_config(
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-# Sidebar for model parameters
+# Sidebar configuration
 with st.sidebar:
     st.header("Model Configuration")
+    st.markdown("[Get HuggingFace Token](https://huggingface.co/settings/tokens)")
     
-    # System message
     system_message = st.text_area(
         "System Message",
         value="You are a friendly Chatbot created by ruslanmv.com",
         height=100
     )
     
-    # Generation parameters
     max_tokens = st.slider(
         "Max Tokens",
-        min_value=1,
-        max_value=4000,
-        value=512,
-        step=10
+        1, 4000, 512
     )
     
     temperature = st.slider(
         "Temperature",
-        min_value=0.1,
-        max_value=4.0,
-        value=0.7,
-        step=0.1
+        0.1, 4.0, 0.7
     )
     
     top_p = st.slider(
-        "Top-p (nucleus sampling)",
-        min_value=0.1,
-        max_value=1.0,
-        value=0.9,
-        step=0.1
+        "Top-p",
+        0.1, 1.0, 0.9
     )
 
-# Main chat interface
+# Chat interface
 st.title("🤖 DeepSeek Chatbot")
-st.caption("Powered by ruslanmv.com - Configure parameters in the sidebar")
+st.caption("Powered by Hugging Face Inference API - Configure in sidebar")
 
-# Display chat messages
+# Display chat history
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-# Chat input
+# Handle input
 if prompt := st.chat_input("Type your message..."):
-    # Add user message to chat history
     st.session_state.messages.append({"role": "user", "content": prompt})
     
-    # Display user message
     with st.chat_message("user"):
         st.markdown(prompt)
-    
+
     try:
-        # Generate response using the model
         with st.spinner("Generating response..."):
             full_prompt = f"{system_message}\n\nUser: {prompt}\nAssistant:"
-            response = generator(
-                full_prompt,
-                max_length=max_tokens,
-                temperature=temperature,
-                top_p=top_p,
-                do_sample=True,
-                num_return_sequences=1
-            )[0]['generated_text']
             
-            # Extract only the assistant's response
-            assistant_response = response.split("Assistant:")[-1].strip()
-        
-        # Display assistant response
+            response = requests.post(
+                API_URL,
+                headers=headers,
+                json={
+                    "inputs": full_prompt,
+                    "parameters": {
+                        "max_new_tokens": max_tokens,
+                        "temperature": temperature,
+                        "top_p": top_p,
+                        "return_full_text": False
+                    }
+                }
+            ).json()
+            
+            if isinstance(response, list) and len(response) > 0:
+                assistant_response = response[0].get('generated_text', '')
+            else:
+                assistant_response = "Error: Unexpected API response"
+
         with st.chat_message("assistant"):
             st.markdown(assistant_response)
         
-        # Add assistant response to chat history
         st.session_state.messages.append({"role": "assistant", "content": assistant_response})
-    
+
     except Exception as e:
-        st.error(f"An error occurred: {str(e)}")
+        st.error(f"API Error: {str(e)}")