Update app.py4

app.py4

@@ -1,68 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-from selenium.webdriver.chrome.service import Service
-from webdriver_manager.chrome import ChromeDriverManager
-import time
 
+"""
+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 is_uncertain(question, response):
-    """Check if the model's response is unreliable."""
-    if len(response.split()) < 4 or response.lower() in question.lower():
-        return True
-    uncertain_phrases = ["Kulingana na utafiti", "Inaaminika kuwa", "Ninadhani", "It is believed that", "Some people say"]
-    return any(phrase.lower() in response.lower() for phrase in uncertain_phrases)
 
-def google_search(query):
-    """Fetch search results using Selenium."""
-    options = webdriver.ChromeOptions()
-    options.add_argument("--headless")  # Run in background
-    driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)
-
-    driver.get(f"https://www.google.com/search?q={query}")
-    time.sleep(2)  # Wait for page to load
-
-    try:
-        # Extract answer from featured snippet if available
-        snippet = driver.find_element(By.CLASS_NAME, "hgKElc").text
-    except:
-        # Extract first search result
-        try:
-            snippet = driver.find_element(By.CSS_SELECTOR, "div.BNeawe.s3v9rd.AP7Wnd").text
-        except:
-            snippet = "Sorry, I couldn't find an answer on Google."
-
-    driver.quit()
-    return snippet
-
-def respond(message, history, system_message, max_tokens, temperature, top_p):
+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  # Stream the response
+        yield response
 
-    if is_uncertain(message, response):
-        google_response = google_search(message)
-        yield f"🤖 AI: {response}\n\n🌍 Google: {google_response}"
 
+"""
+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)",
+        ),
     ],
 )
 
+
 if __name__ == "__main__":
     demo.launch()