Add Kiwix local wiki server support with configuration options

Co-authored-by: SpudGunMan <12676665+SpudGunMan@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2025-10-08 15:00:44 +00:00
parent 2292fb2655
commit c97004b410
3 changed files with 96 additions and 0 deletions
+7
View File
@@ -57,6 +57,13 @@ spaceWeather = True
# enable or disable the wikipedia search module
wikipedia = True
# Use local Kiwix server instead of online Wikipedia
# Set to False to use online Wikipedia, or provide Kiwix server URL
useKiwixServer = False
# Kiwix server URL (e.g., http://127.0.0.1:8080)
kiwixURL = http://127.0.0.1:8080
# Kiwix library name (e.g., wikipedia_en_100_nopic_2024-06)
kiwixLibraryName = wikipedia_en_100_nopic_2024-06
# Enable ollama LLM see more at https://ollama.com
ollama = False
+3
View File
@@ -226,6 +226,9 @@ try:
bee_enabled = config['general'].getboolean('bee', False) # 🐝 off by default undocumented
solar_conditions_enabled = config['general'].getboolean('spaceWeather', True)
wikipedia_enabled = config['general'].getboolean('wikipedia', False)
use_kiwix_server = config['general'].getboolean('useKiwixServer', False)
kiwix_url = config['general'].get('kiwixURL', 'http://127.0.0.1:8080')
kiwix_library_name = config['general'].get('kiwixLibraryName', 'wikipedia_en_100_nopic_2024-06')
llm_enabled = config['general'].getboolean('ollama', False) # https://ollama.com
ollamaHostName = config['general'].get('ollamaHostName', 'http://localhost:11434') # default localhost
llmModel = config['general'].get('ollamaModel', 'gemma3:270m') # default gemma3:270m
+86
View File
@@ -209,6 +209,13 @@ if wikipedia_enabled:
import wikipedia # pip install wikipedia
trap_list = trap_list + ("wiki:", "wiki?",)
help_message = help_message + ", wiki:"
# Kiwix support for local wiki
if use_kiwix_server:
import requests
from bs4 import BeautifulSoup
from urllib.parse import quote
from bs4.element import Comment
# LLM Configuration
if llm_enabled:
@@ -753,7 +760,86 @@ def send_message(message, ch, nodeid=0, nodeInt=1, bypassChuncking=False):
interface.sendText(text=message, channelIndex=ch, destinationId=nodeid)
return True
# Kiwix helper functions (only loaded if use_kiwix_server is True)
if wikipedia_enabled and use_kiwix_server:
def tag_visible(element):
"""Filter visible text from HTML elements for Kiwix"""
if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
return False
if isinstance(element, Comment):
return False
return True
def text_from_html(body):
"""Extract visible text from HTML content"""
soup = BeautifulSoup(body, 'html.parser')
texts = soup.findAll(string=True)
visible_texts = filter(tag_visible, texts)
return " ".join(t.strip() for t in visible_texts if t.strip())
def get_kiwix_summary(search_term):
"""Query local Kiwix server for Wikipedia article"""
try:
search_encoded = quote(search_term)
# Try direct article access first
wiki_article = search_encoded.capitalize().replace("%20", "_")
exact_url = f"{kiwix_url}/raw/{kiwix_library_name}/content/A/{wiki_article}"
response = requests.get(exact_url, timeout=urlTimeoutSeconds)
if response.status_code == 200:
# Extract and clean text
text = text_from_html(response.text)
# Remove common Wikipedia metadata prefixes
text = text.split("Jump to navigation", 1)[-1]
text = text.split("Jump to search", 1)[-1]
# Truncate to reasonable length (first few sentences)
sentences = text.split('. ')
summary = '. '.join(sentences[:wiki_return_limit])
if summary and not summary.endswith('.'):
summary += '.'
return summary.strip()[:500] # Hard limit at 500 chars
# If direct access fails, try search
search_url = f"{kiwix_url}/search?content={kiwix_library_name}&pattern={search_encoded}"
response = requests.get(search_url, timeout=urlTimeoutSeconds)
if response.status_code == 200 and "No results were found" not in response.text:
soup = BeautifulSoup(response.text, 'html.parser')
links = [a['href'] for a in soup.find_all('a', href=True) if "start=" not in a['href']]
for link in links[:3]: # Check first 3 results
article_name = link.split("/")[-1]
if not article_name or article_name[0].islower():
continue
article_url = f"{kiwix_url}{link}"
article_response = requests.get(article_url, timeout=urlTimeoutSeconds)
if article_response.status_code == 200:
text = text_from_html(article_response.text)
text = text.split("Jump to navigation", 1)[-1]
text = text.split("Jump to search", 1)[-1]
sentences = text.split('. ')
summary = '. '.join(sentences[:wiki_return_limit])
if summary and not summary.endswith('.'):
summary += '.'
return summary.strip()[:500]
logger.warning(f"System: No Kiwix Results for:{search_term}")
return ERROR_FETCHING_DATA
except requests.RequestException as e:
logger.warning(f"System: Kiwix connection error: {e}")
return "Unable to connect to local wiki server"
except Exception as e:
logger.warning(f"System: Error with Kiwix for:{search_term} {e}")
return ERROR_FETCHING_DATA
def get_wikipedia_summary(search_term):
# Use Kiwix if configured
if use_kiwix_server:
return get_kiwix_summary(search_term)
# Otherwise use online Wikipedia
wikipedia_search = wikipedia.search(search_term, results=3)
wikipedia_suggest = wikipedia.suggest(search_term)
#wikipedia_aroundme = wikipedia.geosearch(location[0], location[1], results=3)