Spaces:
Build error
Build error
File size: 9,712 Bytes
44198e0 d7b6953 44198e0 dd884bf 6c83b94 44198e0 5e3672b 44198e0 d7b6953 44198e0 d7b6953 44198e0 5e3672b 44198e0 6c83b94 5e3672b dd884bf 5e3672b d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 5e3672b 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 dd884bf 44198e0 dd884bf 6c83b94 dd884bf 6c83b94 dd884bf 6c83b94 dd884bf 6c83b94 dd884bf 5e3672b dd884bf 5e3672b dd884bf 6c83b94 dd884bf 6c83b94 44198e0 d7b6953 44198e0 d7b6953 44198e0 d7b6953 6c83b94 d7b6953 5e3672b d7b6953 44198e0 d7b6953 44198e0 d7b6953 44198e0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 |
from typing import Dict, List, Any
import requests
from bs4 import BeautifulSoup
from transformers import pipeline
from langchain_community.embeddings import HuggingFaceEmbeddings
import time
import json
import os
from urllib.parse import urlparse, quote_plus
import logging
import random
logger = logging.getLogger(__name__)
class SearchResult:
def __init__(self, title: str, link: str, snippet: str):
self.title = title
self.link = link
self.snippet = snippet
class ModelManager:
"""Manages different AI models for specific tasks"""
def __init__(self):
self.device = "cpu"
self.models = {}
self.load_models()
def load_models(self):
# Use smaller models for CPU deployment
self.models['summarizer'] = pipeline(
"summarization",
model="facebook/bart-base",
device=self.device
)
self.models['embeddings'] = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-MiniLM-L6-v2",
model_kwargs={"device": self.device}
)
class ContentProcessor:
"""Processes and analyzes different types of content"""
def __init__(self):
self.model_manager = ModelManager()
def process_content(self, content: str) -> Dict:
"""Process content and generate insights"""
try:
# Generate summary
summary = self.model_manager.models['summarizer'](
content[:1024],
max_length=100,
min_length=30,
do_sample=False
)[0]['summary_text']
return {
'summary': summary,
'content': content
}
except Exception as e:
return {
'summary': f"Error processing content: {str(e)}",
'content': content
}
class WebSearchEngine:
"""Main search engine class"""
def __init__(self):
self.processor = ContentProcessor()
self.session = requests.Session()
self.request_delay = 2.0
self.last_request_time = 0
self.max_retries = 3
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'DNT': '1',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1'
}
def safe_get(self, url: str, max_retries: int = 3) -> requests.Response:
"""Make a GET request with retries and error handling"""
for i in range(max_retries):
try:
# Add delay between requests
current_time = time.time()
time_since_last = current_time - self.last_request_time
if time_since_last < self.request_delay:
time.sleep(self.request_delay - time_since_last + random.uniform(0.5, 1.5))
response = self.session.get(url, headers=self.headers, timeout=10)
self.last_request_time = time.time()
if response.status_code == 200:
return response
elif response.status_code == 429: # Rate limit
wait_time = (i + 1) * 5
time.sleep(wait_time)
continue
else:
response.raise_for_status()
except Exception as e:
if i == max_retries - 1:
raise
time.sleep((i + 1) * 2)
raise Exception(f"Failed to fetch URL after {max_retries} attempts")
def is_valid_url(self, url: str) -> bool:
"""Check if URL is valid for crawling"""
try:
parsed = urlparse(url)
return bool(parsed.netloc and parsed.scheme)
except:
return False
def get_metadata(self, soup: BeautifulSoup) -> Dict:
"""Extract metadata from page"""
title = soup.title.string if soup.title else "No title"
description = ""
if soup.find("meta", attrs={"name": "description"}):
description = soup.find("meta", attrs={"name": "description"}).get("content", "")
return {
'title': title,
'description': description
}
def process_url(self, url: str) -> Dict:
"""Process a single URL"""
if not self.is_valid_url(url):
return {'error': f"Invalid URL: {url}"}
try:
response = self.safe_get(url)
soup = BeautifulSoup(response.text, 'lxml')
# Extract text content
for script in soup(["script", "style"]):
script.decompose()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
content = ' '.join(chunk for chunk in chunks if chunk)
# Get metadata
metadata = self.get_metadata(soup)
# Process content
processed = self.processor.process_content(content)
return {
'url': url,
'title': metadata['title'],
'description': metadata['description'],
'summary': processed['summary'],
'content': processed['content']
}
except Exception as e:
return {'error': f"Error processing {url}: {str(e)}"}
def search_duckduckgo(self, query: str, max_results: int = 5) -> List[Dict]:
"""Search DuckDuckGo and parse HTML results"""
search_results = []
try:
# Encode query for URL
encoded_query = quote_plus(query)
# DuckDuckGo HTML search URL
search_url = f'https://html.duckduckgo.com/html/?q={encoded_query}'
# Get search results page
response = self.safe_get(search_url)
soup = BeautifulSoup(response.text, 'lxml')
# Find all result elements
results = soup.find_all('div', {'class': 'result'})
for result in results[:max_results]:
try:
# Extract link
link_elem = result.find('a', {'class': 'result__a'})
if not link_elem:
continue
link = link_elem.get('href', '')
if not link or not self.is_valid_url(link):
continue
# Extract title
title = link_elem.get_text(strip=True)
# Extract snippet
snippet_elem = result.find('a', {'class': 'result__snippet'})
snippet = snippet_elem.get_text(strip=True) if snippet_elem else ""
search_results.append({
'link': link,
'title': title,
'snippet': snippet
})
# Add delay between processing results
time.sleep(random.uniform(0.2, 0.5))
except Exception as e:
logger.warning(f"Error processing search result: {str(e)}")
continue
return search_results
except Exception as e:
logger.error(f"Error during DuckDuckGo search: {str(e)}")
return []
def search(self, query: str, max_results: int = 5) -> Dict:
"""Perform search and process results"""
try:
# Search using DuckDuckGo HTML
search_results = self.search_duckduckgo(query, max_results)
if not search_results:
return {'error': 'No results found'}
results = []
for result in search_results:
if 'link' in result:
processed = self.process_url(result['link'])
if 'error' not in processed:
results.append(processed)
time.sleep(random.uniform(0.5, 1.0))
if not results:
return {'error': 'Failed to process any search results'}
# Generate insights from results
all_content = " ".join([r['summary'] for r in results if 'summary' in r])
return {
'results': results,
'insights': all_content[:1000] if all_content else "No insights available.",
'follow_up_questions': [
f"What are the key differences between {query} and related topics?",
f"Can you explain {query} in simple terms?",
f"What are the latest developments in {query}?"
]
}
except Exception as e:
return {'error': f"Search failed: {str(e)}"}
# Main search function
def search(query: str, max_results: int = 5) -> Dict:
"""Main search function"""
engine = WebSearchEngine()
return engine.search(query, max_results)
|