Update app.py

app.py

@@ -1,114 +1,83 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from bs4 import BeautifulSoup
-import requests
-import os
-from typing import List, Tuple, Optional
 
-# --- Configuration ---
-MODEL_NAME = "meta-llama/Meta-Llama-3.1-405B-Instruct"
-API_KEY_ENV_VAR = "HF_TOKEN"
-SEARCH_TRIGGER_WORD = "search"
-DEFAULT_NUM_RESULTS = 3
+# Initialize the InferenceClient with the model ID from Hugging Face
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
-# --- Utility Functions ---
-
-def get_api_key() -> str:
-    """Retrieves the API key from an environment variable."""
-    api_key = os.getenv(API_KEY_ENV_VAR)
-    if not api_key:
-        raise ValueError(f"API key not found. Please set the {API_KEY_ENV_VAR} environment variable.")
-    return api_key
-
-def scrape_yahoo_search(query: str, num_results: int = DEFAULT_NUM_RESULTS) -> Tuple[Optional[str], Optional[str]]:
-    """Scrapes Yahoo search results and returns formatted snippets and the search URL."""
-    search_url = f"https://search.yahoo.com/search?p={query}"
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'} 
-
-    try:
-        response = requests.get(search_url, headers=headers)
-        response.raise_for_status() 
-
-        soup = BeautifulSoup(response.content, 'html.parser')
-        result_elements = soup.find_all('div', {'class': 'dd algo algo-sr Sr'}, limit=num_results)
-
-        if result_elements:
-            results = [
-                f"**Title:** {res.find('h3').get_text(strip=True)}\n**Snippet:** {res.find('div', {'class': 'compText aAbs'}).get_text(strip=True)}\n**URL:** {res.find('a')['href']}" 
-                for res in result_elements 
-                if res.find('h3') and res.find('div', {'class': 'compText aAbs'}) and res.find('a')
-            ]
-            return "\n\n".join(results), search_url
-        else:
-            return None, search_url 
-
-    except requests.RequestException as e:
-        return f"Request error: {str(e)}", None
-    except Exception as e:
-        return f"Processing error: {str(e)}", None
-
-def extract_search_query(message: str, trigger_word: str = SEARCH_TRIGGER_WORD) -> Optional[str]:
-    """Extracts the search query from the message if the trigger word is present."""
-    lower_message = message.lower()
-    if trigger_word in lower_message:
-        query = lower_message.split(trigger_word, 1)[1].strip()
-        return query if query else None
-    return None
-
-# --- Initialize Inference Client ---
-client = InferenceClient(model=MODEL_NAME, token=get_api_key())
-
-# --- Chatbot Logic ---
 def respond(
     message: str,
-    history: List[Tuple[str, str]],
+    history: list[tuple[str, str]],
     system_message: str,
     max_tokens: int,
     temperature: float,
     top_p: float,
-) -> str:
-    """Generates a response from the AI model, incorporating search results if requested."""
-    query = extract_search_query(message)
-
-    if query:
-        search_results, search_url = scrape_yahoo_search(query)
-        if search_results:
-            message += f"\n\n## Web Search Results:\n{search_results}\n**Source:** {search_url}"
-        else:
-            message += "\n\nI couldn't find any relevant web results for your query."
+):
+    """
+    Generates a response from the AI model based on the user's message and chat history.
+    
+    Args:
+        message (str): The user's input message.
+        history (list): A list of tuples representing the conversation history (user, assistant).
+        system_message (str): A system-level message guiding the AI's behavior.
+        max_tokens (int): The maximum number of tokens for the output.
+        temperature (float): Sampling temperature for controlling the randomness.
+        top_p (float): Top-p (nucleus sampling) for controlling diversity.
+
+    Yields:
+        str: The AI's response as it is generated.
+    """
     
-    messages = [{"role": "system", "content": system_message}] + \
-               [{"role": role, "content": content} for role, content in history] + \
-               [{"role": "user", "content": message}]
+    # Prepare the conversation history for the API call
+    messages = [{"role": "system", "content": system_message}]
+    
+    for user_input, assistant_response in history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if assistant_response:
+            messages.append({"role": "assistant", "content": assistant_response})
+
+    # Add the latest user message to the conversation
+    messages.append({"role": "user", "content": message})
 
+    # Initialize an empty response
     response = ""
+
     try:
-        for response_chunk in client.chat_completion(
+        # Generate a response from the model with streaming
+        for message in client.chat_completion(
             messages=messages,
             max_tokens=max_tokens,
             stream=True,
             temperature=temperature,
             top_p=top_p,
         ):
-            response += response_chunk.choices[0].delta.content
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+
     except Exception as e:
-        return f"AI model error: {str(e)}" 
+        yield f"An error occurred: {str(e)}"
 
-    return response
 
-# --- Gradio Interface ---
+# Define the ChatInterface with additional input components for user customization
 demo = gr.ChatInterface(
     fn=respond,
     additional_inputs=[
-        gr.Textbox(value="You are a helpful and informative AI assistant.", label="System Message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens"),
-        gr.Slider(minimum=0.1, maximum=1.0, 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)"),
+        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 (nucleus sampling)",
+        ),
     ],
-    title="Chatbot with Search",
-    description="Chat and search the web using the power of Meta-Llama!",
+    title="Chatbot Interface",
+    description="A customizable chatbot interface using Hugging Face's Inference API.",
 )
 
-# --- Launch the App ---
+# Launch the Gradio interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()