!pip install BeautifulSoup

ollama run llama3.1 

import time
import requests
from bs4 import BeautifulSoup
import ollama

def fetch_article_content(url, retries=3, content_limit=None):
    attempt = 0
    while attempt < retries:
        try:
            response = requests.get(url, timeout=30)  # Add timeout to prevent hanging
            response.raise_for_status()  # Raise an error for bad responses (4xx, 5xx)
            soup = BeautifulSoup(response.content, 'html.parser')
            # Remove script and style elements
            for script in soup(["script", "style"]):
                script.decompose()
            # Get text
            text = soup.get_text()
            # Break into lines and remove leading and trailing space on each
            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)
            # Limit content if specified
            if content_limit:
                text = text[:content_limit]
            return text
  except (requests.exceptions.RequestException, requests.exceptions.ChunkedEncodingError) as e:
            attempt += 1
            print(f"Attempt {attempt} failed: {e}")
            if attempt >= retries:
                raise
            time.sleep(2)  # Wait before retrying

book_url = "https://www.deeplearningbook.org/contents/intro.html"
book_content = fetch_article_content(book_url, content_limit=200000)
print(f"Fetched {len(book_content)} characters from the book.")
print("First 500 characters:")
print(book_content[:500])

def make_non_cached_inference(prompt):
    start_time = time.time()
    response = ollama.generate(model="llama3", prompt=prompt)
    end_time = time.time()
    # Print the response to inspect its structure
    print(f"Full response: {response}")
    # Access the generated summary
    generated_summary = response.get('response', 'No summary found in response')  
    return generated_summary, end_time - start_time

def make_cached_inference(prompt, cache):
    if prompt in cache:
        print("Using cached result...")
        return cache[prompt], 0  # Return cached response with 0 latency
    start_time = time.time()
    response = ollama.generate(model="llama3", prompt=prompt)
    end_time = time.time()
    # Print the response to inspect its structure (if needed)
    print(f"Full response (cached call): {response}")
    # Access the generated summary
    generated_summary = response.get('response', 'No summary found in response')
    cache[prompt] = generated_summary  # Store result in cache
    return generated_summary, end_time - start_time

prompt = f"<book>{book_content[:10000]}</book>\nPlease provide a summary of this book."

non_cached_response, non_cached_time = make_non_cached_inference(prompt)
print(f"Non-cached inference time: {non_cached_time:.2f} seconds")
print(f"Non-cached summary: {non_cached_response}")
cache = {}

# Cached inference to generate a summary
cached_response, cached_time = make_cached_inference(prompt, cache)
print(f"Cached inference time: {cached_time:.2f} seconds")
print(f"Cached summary: {cached_response}")