Update app.py

app.py

@@ -1,73 +1,64 @@
 import gradio as gr
-import requests
-import importlib
-from bs4 import BeautifulSoup
 from huggingface_hub import InferenceClient
 
-# Import weather script
-weather = importlib.import_module("weather")
-
-# Hugging Face model
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
-def google_search(query):
-    """Scrape Google search for an answer."""
-    url = f"https://www.google.com/search?q={query}"
-    headers = {"User-Agent": "Mozilla/5.0"}
-    
-    try:
-        response = requests.get(url, headers=headers)
-        soup = BeautifulSoup(response.text, "html.parser")
-        result = soup.find("div", class_="BNeawe iBp4i AP7Wnd")
-        
-        if result:
-            return result.text
-        return "Samahani, siwezi kupata majibu."
-    except Exception:
-        return "Samahani, siwezi kuwasiliana na Google kwa sasa."
-
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    """Chatbot that answers user and fetches real-time info if needed."""
-    
-    # Handle weather requests
-    if "weather" in message.lower() or "hali ya hewa" in message.lower():
-        city = message.split()[-1]  # Last word as city name
-        return weather.get_weather(city)
-
-    # Handle time requests
-    if "time" in message.lower() or "saa ngapi" in message.lower():
-        from datetime import datetime
-        return f"Saa ya sasa ni {datetime.now().strftime('%H:%M:%S')}."
 
-    # Model response
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
+
     for val in history:
-        if val[0]: messages.append({"role": "user", "content": val[0]})
-        if val[1]: messages.append({"role": "assistant", "content": val[1]})
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
     messages.append({"role": "user", "content": message})
 
     response = ""
-    for message in client.chat_completion(messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p):
+
+    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
 
-    # If model doesn't know, fetch from Google
-    if "I don't know" in response or response.strip() == "":
-        response = google_search(message)
-    
-    return response
 
-# Gradio UI
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", 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"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )
-# try
+
+
 if __name__ == "__main__":
     demo.launch()
-