File size: 5,248 Bytes
34054e0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
import random
import requests
from bs4 import BeautifulSoup
from transformers import AutoTokenizer, AutoModelForCausalLM
# List of user agents
_useragent_list = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Edge/91.0.864.59 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Edge/91.0.864.59 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36",
]
# Function to extract visible text from HTML content of a webpage
def extract_text_from_webpage(html):
print("Extracting text from webpage...")
soup = BeautifulSoup(html, 'html.parser')
for script in soup(["script", "style"]):
script.extract() # Remove scripts and styles
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = '\n'.join(chunk for chunk in chunks if chunk)
print(f"Extracted text length: {len(text)}")
return text
# Function to perform a Google search and retrieve results
def google_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_verify=None):
"""Performs a Google search and returns the results."""
print(f"Searching for term: {term}")
escaped_term = requests.utils.quote(term)
start = 0
all_results = []
max_chars_per_page = 8000 # Limit the number of characters from each webpage to stay under the token limit
with requests.Session() as session:
while start < num_results:
print(f"Fetching search results starting from: {start}")
try:
# Choose a random user agent
user_agent = random.choice(_useragent_list)
headers = {
'User-Agent': user_agent
}
print(f"Using User-Agent: {headers['User-Agent']}")
resp = session.get(
url="https://www.google.com/search",
headers=headers,
params={
"q": term,
"num": num_results - start,
"hl": lang,
"start": start,
"safe": safe,
},
timeout=timeout,
verify=ssl_verify,
)
resp.raise_for_status()
except requests.exceptions.RequestException as e:
print(f"Error fetching search results: {e}")
break
soup = BeautifulSoup(resp.text, "html.parser")
result_block = soup.find_all("div", attrs={"class": "g"})
if not result_block:
print("No more results found.")
break
for result in result_block:
link = result.find("a", href=True)
if link:
link = link["href"]
print(f"Found link: {link}")
try:
webpage = session.get(link, headers=headers, timeout=timeout)
webpage.raise_for_status()
visible_text = extract_text_from_webpage(webpage.text)
if len(visible_text) > max_chars_per_page:
visible_text = visible_text[:max_chars_per_page] + "..."
all_results.append({"link": link, "text": visible_text})
except requests.exceptions.RequestException as e:
print(f"Error fetching or processing {link}: {e}")
all_results.append({"link": link, "text": None})
else:
print("No link found in result.")
all_results.append({"link": None, "text": None})
start += len(result_block)
print(f"Total results fetched: {len(all_results)}")
return all_results
# Load the Mixtral-8x7B-Instruct model and tokenizer
model_name = 'mistralai/Mistral-7B-Instruct-v0.3'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Example usage
search_term = "How did Tesla perform in Q1 2024"
search_results = google_search(search_term, num_results=3)
# Combine text from search results to create a prompt
combined_text = "\n\n".join(result['text'] for result in search_results if result['text'])
# Tokenize the input text
inputs = tokenizer(combined_text, return_tensors="pt")
# Generate a response
outputs = model.generate(**inputs, max_length=150, temperature=0.7, top_p=0.9, top_k=50)
# Decode the generated tokens to a readable string
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Print the response
print(response) |