perf: cache parsed CHANGELOG to skip markdown+BS4 on cold start

Author: Algorithm5838

backend/open_webui/env.py

@@ -1,3 +1,4 @@
+import hashlib
 import importlib.metadata
 import json
 import logging
@@ -186,35 +187,60 @@ def parse_section(section):
 except Exception:
     changelog_content = (pkgutil.get_data('open_webui', 'CHANGELOG.md') or b'').decode()
 
-# Convert markdown content to HTML
-html_content = markdown.markdown(changelog_content)
+# Cache parsed CHANGELOG to avoid markdown+BeautifulSoup overhead on every cold
+# start. The cache is content-addressed (MD5 of raw markdown) so it invalidates
+# automatically whenever CHANGELOG.md changes (e.g. on a version upgrade).
+_changelog_cache_dir = Path(os.getenv('DATA_DIR', BACKEND_DIR / 'data'))
+_changelog_cache_path = _changelog_cache_dir / 'changelog_cache.json'
+_changelog_hash = hashlib.md5(changelog_content.encode()).hexdigest()
 
-# Parse the HTML content
-soup = BeautifulSoup(html_content, 'html.parser')
+changelog_json = None
+try:
+    _cached = json.loads(_changelog_cache_path.read_text(encoding='utf8'))
+    if _cached.get('_hash') == _changelog_hash:
+        changelog_json = _cached['data']
+except Exception:
+    pass
+
+if changelog_json is None:
+    # Convert markdown content to HTML
+    html_content = markdown.markdown(changelog_content)
+
+    # Parse the HTML content
+    soup = BeautifulSoup(html_content, 'html.parser')
 
-# Initialize JSON structure
-changelog_json = {}
+    # Initialize JSON structure
+    changelog_json = {}
 
-# Iterate over each version
-for version in soup.find_all('h2'):
-    version_number = version.get_text().strip().split(' - ')[0][1:-1]  # Remove brackets
-    date = version.get_text().strip().split(' - ')[1]
+    # Iterate over each version
+    for version in soup.find_all('h2'):
+        version_number = version.get_text().strip().split(' - ')[0][1:-1]  # Remove brackets
+        date = version.get_text().strip().split(' - ')[1]
 
-    version_data = {'date': date}
+        version_data = {'date': date}
 
-    # Find the next sibling that is a h3 tag (section title)
-    current = version.find_next_sibling()
+        # Find the next sibling that is a h3 tag (section title)
+        current = version.find_next_sibling()
 
-    while current and current.name != 'h2':
-        if current.name == 'h3':
-            section_title = current.get_text().lower()  # e.g., "added", "fixed"
-            section_items = parse_section(current.find_next_sibling('ul'))
-            version_data[section_title] = section_items
+        while current and current.name != 'h2':
+            if current.name == 'h3':
+                section_title = current.get_text().lower()  # e.g., "added", "fixed"
+                section_items = parse_section(current.find_next_sibling('ul'))
+                version_data[section_title] = section_items
 
-        # Move to the next element
-        current = current.find_next_sibling()
+            # Move to the next element
+            current = current.find_next_sibling()
 
-    changelog_json[version_number] = version_data
+        changelog_json[version_number] = version_data
+
+    try:
+        _changelog_cache_dir.mkdir(parents=True, exist_ok=True)
+        _changelog_cache_path.write_text(
+            json.dumps({'_hash': _changelog_hash, 'data': changelog_json}),
+            encoding='utf8',
+        )
+    except Exception:
+        pass
 
 CHANGELOG = changelog_json