Update app.py

app.py

@@ -1,43 +1,70 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from collections import defaultdict
 
+# Initialize the model client
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
-def format_alpaca_prompt(user_input, system_prompt):
-    """Formats input in Alpaca/LLaMA style"""
-    prompt = f"""{system_prompt}
+# Store user preferences & history
+user_preferences = defaultdict(int)  # Tracks keywords & topics
+session_histories = defaultdict(list)  # Stores conversation history per session
 
-### Instruction:
-{user_input}
-
-### Response:
-"""
-    return prompt
+def extract_keywords(text):
+    """Extracts simple keywords from user input."""
+    words = text.lower().split()
+    common_words = {"the", "is", "a", "and", "to", "of", "in", "it", "you", "for"}  # Ignore common words
+    return [word for word in words if word not in common_words]
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
-    formatted_prompt = format_alpaca_prompt(message, system_message)
+    session_id = id(history)  # Unique ID for each session
+    session_history = session_histories[session_id]  # Retrieve session history
+    
+    # Extract keywords & update preferences
+    keywords = extract_keywords(message)
+    for kw in keywords:
+        user_preferences[kw] += 1
+
+    # Add past conversation to message history
+    messages = [{"role": "system", "content": system_message}]
+    for user_msg, bot_response in session_history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_response})
+
+    # Append current user message
+    messages.append({"role": "user", "content": message})
 
-    response = client.text_generation(
-        formatted_prompt,
-        max_new_tokens=max_tokens,
+    # Generate response from model
+    response = ""
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
         top_p=top_p,
-    )
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response  # Stream response to user
 
-    # ✅ Extract only the response
-    cleaned_response = response.split("### Response:")[-1].strip()
-    
-    yield cleaned_response  # ✅ Output only the answer
+    # Save to session history
+    session_history.append((message, response))
+
+    # Optionally, adapt responses based on learned preferences
+    most_asked = max(user_preferences, key=user_preferences.get, default=None)
+    if most_asked and most_asked in message.lower():
+        response += f"\n\nI see you're interested in {most_asked} a lot! Want to explore more details?"
+        yield response  # Update response with learning behavior
 
+# Create Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=250, value=128, step=1, label="Max new tokens"),
+        gr.Textbox(value="You are a friendly chatbot that learns user interests.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
-#
+
 if __name__ == "__main__":
     demo.launch()