app.py

import gradio as gr
from huggingface_hub import InferenceClient

import requests
from bs4 import BeautifulSoup
import urllib
import random

# List of user agents to choose from for requests
_useragent_list = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/111.0'
]

def get_useragent():
    """Returns a random user agent from the list."""
    return random.choice(_useragent_list)

def extract_text_from_webpage(html_content):
    """Extracts visible text from HTML content using BeautifulSoup."""
    soup = BeautifulSoup(html_content, "html.parser")
    # Remove unwanted tags
    for tag in soup(["script", "style", "header", "footer", "nav"]):
        tag.extract()
    # Get the remaining visible text
    visible_text = soup.get_text(strip=True)
    return visible_text

def search(term, num_results=1, lang="en", advanced=True, sleep_interval=0, timeout=5, safe="active", ssl_verify=None):
    """Performs a Google search and returns the results."""
    escaped_term = urllib.parse.quote_plus(term)
    start = 0
    all_results = []

    # Fetch results in batches
    while start < num_results:
        resp = requests.get(
            url="https://www.google.com/search",
            headers={"User-Agent": get_useragent()}, # Set random user agent
            params={
                "q": term,
                "num": num_results - start, # Number of results to fetch in this batch
                "hl": lang,
                "start": start,
                "safe": safe,
            },
            timeout=timeout,
            verify=ssl_verify,
        )
        resp.raise_for_status() # Raise an exception if request fails

        soup = BeautifulSoup(resp.text, "html.parser")
        result_block = soup.find_all("div", attrs={"class": "g"})

        # If no results, continue to the next batch
        if not result_block:
            start += 1
            continue

        # Extract link and text from each result
        for result in result_block:
            link = result.find("a", href=True)
            if link:
                link = link["href"]
                try:
                    # Fetch webpage content
                    webpage = requests.get(link, headers={"User-Agent": get_useragent()})
                    webpage.raise_for_status()
                    # Extract visible text from webpage
                    visible_text = extract_text_from_webpage(webpage.text)
                    all_results.append({"link": link, "text": visible_text})
                except requests.exceptions.RequestException as e:
                    # Handle errors fetching or processing webpage
                    print(f"Error fetching or processing {link}: {e}")
                    all_results.append({"link": link, "text": None})
            else:
                all_results.append({"link": None, "text": None})

        start += len(result_block) # Update starting index for next batch

    return all_results


client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": "Your name is Chatchat.And, you have to follow the instrutions.There could be no instructions or there is a instruction.The instructions: "+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]})

    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,
    ):
        token = message.choices[0].delta.content

        response += token
        yield 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 (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()