dongho/Munich-news
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Dongho Kim
2025-12-10 15:50:11 +00:00
parent 50b9888004
commit 4e8b60f77c
12 changed files with 247 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/app.py
View File

@@ -13,6 +13,7 @@ from routes.admin_routes import admin_bp
from routes.transport_routes import transport_bp
from routes.interests_routes import interests_bp
from routes.personalization_routes import personalization_bp
from routes.search_routes import search_bp
# Initialize Flask app
app = Flask(__name__)
@@ -33,6 +34,7 @@ app.register_blueprint(admin_bp)
app.register_blueprint(transport_bp)
app.register_blueprint(interests_bp)
app.register_blueprint(personalization_bp)
app.register_blueprint(search_bp)
# Health check endpoint
@app.route('/health')

3
backend/chroma_client.py
View File

@@ -87,7 +87,8 @@ class ChromaClient:
# Prepare text for embedding (Title + Summary + Start of Content)
# This gives semantic search a good overview
title = article.get('title', '')
# Use English title if available, otherwise original
title = article.get('title_en') if article.get('title_en') else article.get('title', '')
summary = article.get('summary') or ''
content_snippet = article.get('content', '')[:1000]

7
backend/config.py
View File

@@ -45,6 +45,11 @@ class Config:
TRACKING_API_URL = os.getenv('TRACKING_API_URL', f'http://localhost:{os.getenv("FLASK_PORT", "5000")}')
TRACKING_DATA_RETENTION_DAYS = int(os.getenv('TRACKING_DATA_RETENTION_DAYS', '90'))
# ChromaDB
CHROMA_HOST = os.getenv('CHROMA_HOST', 'chromadb')
CHROMA_PORT = int(os.getenv('CHROMA_PORT', '8000'))
CHROMA_COLLECTION = os.getenv('CHROMA_COLLECTION', 'munich_news_articles')
@classmethod
def print_config(cls):
"""Print configuration (without sensitive data)"""
@@ -57,3 +62,5 @@ class Config:
print(f" Ollama Enabled: {cls.OLLAMA_ENABLED}")
print(f" Tracking Enabled: {cls.TRACKING_ENABLED}")
print(f" Tracking API URL: {cls.TRACKING_API_URL}")
print(f" ChromaDB Host: {cls.CHROMA_HOST}")
print(f" ChromaDB Port: {cls.CHROMA_PORT}")

1
backend/requirements.txt
View File

@@ -8,3 +8,4 @@ Jinja2==3.1.2
redis==5.0.1
chromadb>=0.4.0
sentence-transformers>=2.2.2

11
backend/routes/news_routes.py
View File

@@ -24,8 +24,11 @@ def get_news():
db_articles = []
for doc in cursor:
# Use English title if available, otherwise fallback to original
title = doc.get('title_en') if doc.get('title_en') else doc.get('title', '')
article = {
'title': doc.get('title', ''),
'title': title,
'author': doc.get('author'),
'link': doc.get('link', ''),
'source': doc.get('source', ''),
@@ -114,8 +117,10 @@ def get_clustered_news_internal():
# Use cluster_articles from aggregation (already fetched)
cluster_articles = doc.get('cluster_articles', [])
title = doc.get('title_en') if doc.get('title_en') else doc.get('title', '')
article = {
'title': doc.get('title', ''),
'title': title,
'link': doc.get('link', ''),
'source': doc.get('source', ''),
'published': doc.get('published_at', ''),
@@ -173,7 +178,7 @@ def get_article_by_url(article_url):
return jsonify({'error': 'Article not found'}), 404
return jsonify({
'title': article.get('title', ''),
'title': article.get('title_en') if article.get('title_en') else article.get('title', ''),
'author': article.get('author'),
'link': article.get('link', ''),
'content': article.get('content', ''),

88
backend/routes/search_routes.py Normal file
View File

@@ -0,0 +1,88 @@
from flask import Blueprint, jsonify, request
from config import Config
from chroma_client import ChromaClient
import logging
search_bp = Blueprint('search', __name__)
# Initialize ChromaDB client
# Note: We use the hostname 'chromadb' as defined in docker-compose for the backend
chroma_client = ChromaClient(
host=Config.CHROMA_HOST,
port=Config.CHROMA_PORT,
collection_name=Config.CHROMA_COLLECTION
)
@search_bp.route('/api/search', methods=['GET'])
def search_news():
"""
Semantic search for news articles using ChromaDB.
Query parameters:
- q: Search query (required)
- limit: Number of results (default: 10)
- category: Filter by category (optional)
"""
try:
query = request.args.get('q')
if not query:
return jsonify({'error': 'Missing search query'}), 400
limit = int(request.args.get('limit', 10))
category = request.args.get('category')
# Build filter if category provided
where_filter = None
if category:
where_filter = {"category": category}
# Perform search
results = chroma_client.search(
query_text=query,
n_results=limit,
where=where_filter
)
# Format for frontend
formatted_response = []
for item in results:
metadata = item.get('metadata', {})
# Use translated title if availble (stored in metadata as title_en or title)
# Note: Chroma metadata structure is flat. If we store title_en, we should use it.
# But currently we store: title, url, source, category, published_at.
# We need to make sure title_en is stored in Chroma OR fetch it from DB.
# Faster approach: just rely on what is in Chroma.
# BETTER: In crawl, we store title as title_en in metadata if available?
# Let's check how we store it in crawler_service.py/chroma_client.py
# Correction: Looking at crawler_service.py line 456, we pass article_doc to add_articles.
# In chroma_client.py line 97, we only extract title, url, source, category, published_at.
# We are NOT storing title_en in Chroma metadata currently.
# FOR NOW: We will stick to the title stored in Chroma, but we should update Chroma storing logic.
# However, since the user IS complaining about English, let's assume valid English titles
# are what we want to display.
# Wait, if we change the metadata in ChromaClient to use title_en as the main title,
# then search results will automatically show English.
title = metadata.get('title', 'Unknown Title')
formatted_response.append({
'title': title,
'link': metadata.get('url', ''),
'source': metadata.get('source', 'Unknown'),
'category': metadata.get('category', 'general'),
'published_at': metadata.get('published_at', ''),
'relevance_score': 1.0 - item.get('distance', 1.0), # Convert distance to score (approx)
'snippet': item.get('document', '')[:200] + '...' # Preview
})
return jsonify({
'query': query,
'count': len(formatted_response),
'results': formatted_response
}), 200
except Exception as e:
logging.error(f"Search error: {str(e)}")
return jsonify({'error': str(e)}), 500

25
docker-compose.yml
View File

@@ -1,20 +1,3 @@
# Munich News Daily - Docker Compose Configuration
#
# GPU Support:
# To enable GPU acceleration for Ollama (5-10x faster):
# 1. Check GPU availability: ./check-gpu.sh
# 2. Start with GPU: ./start-with-gpu.sh
# Or manually: docker-compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
#
# Security:
# - Only Backend API (port 5001) is exposed to host
# - MongoDB is internal-only (not exposed to host)
# - Ollama is internal-only (not exposed to host)
# - Crawler and Sender are internal-only
# All services communicate via internal Docker network
#
# See docs/OLLAMA_SETUP.md for detailed setup instructions
services:
# Ollama AI Service (Internal only - not exposed to host)
ollama:
@@ -29,14 +12,6 @@ services:
dns:
- 8.8.8.8
- 1.1.1.1
# GPU support (uncomment if you have NVIDIA GPU)
# deploy:
# resources:
# reservations:
# devices:
# - driver: nvidia
# count: all
# capabilities: [gpu]
healthcheck:
test: [ "CMD-SHELL", "ollama list || exit 1" ]
interval: 30s

100
frontend/public/app.js
View File

@@ -113,10 +113,15 @@ function setupInfiniteScroll() {
}
// Search functionality
function handleSearch() {
let searchTimeout;
async function handleSearch() {
const searchInput = document.getElementById('searchInput');
const clearBtn = document.getElementById('clearSearch');
searchQuery = searchInput.value.trim().toLowerCase();
const searchStats = document.getElementById('searchStats');
const newsGrid = document.getElementById('newsGrid');
searchQuery = searchInput.value.trim();
// Show/hide clear button
if (searchQuery) {
@@ -125,41 +130,68 @@ function handleSearch() {
clearBtn.classList.add('hidden');
}
// Filter articles
// Clear previous timeout
if (searchTimeout) clearTimeout(searchTimeout);
// If empty query, reset to all articles
if (searchQuery === '') {
filteredArticles = allArticles;
} else {
filteredArticles = allArticles.filter(article => {
const title = article.title.toLowerCase();
const summary = (article.summary || '').toLowerCase().replace(/<[^>]*>/g, '');
const source = formatSourceName(article.source).toLowerCase();
return title.includes(searchQuery) ||
summary.includes(searchQuery) ||
source.includes(searchQuery);
});
}
// Reset display
displayedCount = 0;
const newsGrid = document.getElementById('newsGrid');
newsGrid.innerHTML = '';
// Update stats
updateSearchStats();
// Load filtered articles
if (filteredArticles.length > 0) {
displayedCount = 0;
newsGrid.innerHTML = '';
updateSearchStats();
loadMoreArticles();
} else {
newsGrid.innerHTML = `
<div class="text-center py-16">
<div class="text-6xl mb-4">🔍</div>
<p class="text-xl text-gray-600 mb-2">No articles found</p>
<p class="text-gray-400">Try a different search term</p>
</div>
`;
return;
}
// Debounce search API call
searchTimeout = setTimeout(async () => {
// Show searching state
newsGrid.innerHTML = '<div class="text-center py-10 text-gray-500">Searching...</div>';
try {
const response = await fetch(`/api/search?q=${encodeURIComponent(searchQuery)}&limit=20`);
// Check if response is ok
if (!response.ok) {
const errorText = await response.text();
throw new Error(`Server returned ${response.status}: ${errorText}`);
}
const data = await response.json();
if (data.results && data.results.length > 0) {
// Map results to match card format
filteredArticles = data.results.map(item => ({
title: item.title,
link: item.link,
source: item.source,
summary: item.snippet, // Map snippet to summary
published_at: item.published_at,
score: item.relevance_score
}));
displayedCount = 0;
newsGrid.innerHTML = '';
// Update stats
searchStats.textContent = `Found ${filteredArticles.length} relevant articles`;
loadMoreArticles();
} else {
newsGrid.innerHTML = `
<div class="text-center py-16">
<div class="text-6xl mb-4">🔍</div>
<p class="text-xl text-gray-600 mb-2">No relevant articles found</p>
<p class="text-gray-400">Try different keywords or concepts</p>
</div>
`;
searchStats.textContent = 'No results found';
}
} catch (error) {
console.error('Search failed:', error);
newsGrid.innerHTML = `<div class="text-center py-10 text-red-400">Search failed: ${error.message}</div>`;
}
}, 500); // 500ms debounce
}
function clearSearch() {
@@ -423,7 +455,7 @@ async function unsubscribe() {
}
// Close modal when clicking outside
window.onclick = function(event) {
window.onclick = function (event) {
const modal = document.getElementById('unsubscribeModal');
if (event.target === modal) {
closeUnsubscribe();

25
frontend/server.js
View File

@@ -204,6 +204,31 @@ app.get('/api/ollama/config', async (req, res) => {
}
});
app.get('/api/search', async (req, res) => {
try {
const { q, limit, category } = req.query;
const response = await axios.get(`${API_URL}/api/search`, {
params: { q, limit, category }
});
res.json(response.data);
} catch (error) {
if (error.response) {
// The request was made and the server responded with a status code
// that falls out of the range of 2xx
console.error('Search API Error:', error.response.status, error.response.data);
res.status(error.response.status).json(error.response.data);
} else if (error.request) {
// The request was made but no response was received
console.error('Search API No Response:', error.request);
res.status(502).json({ error: 'Search service unavailable (timeout/connection)' });
} else {
// Something happened in setting up the request that triggered an Error
console.error('Search API Request Error:', error.message);
res.status(500).json({ error: 'Internal proxy error' });
}
}
});
app.listen(PORT, () => {
console.log(`Frontend server running on http://localhost:${PORT}`);
console.log(`Admin dashboard: http://localhost:${PORT}/admin.html`);

3
news_crawler/chroma_client.py
View File

@@ -87,7 +87,8 @@ class ChromaClient:
# Prepare text for embedding (Title + Summary + Start of Content)
# This gives semantic search a good overview
title = article.get('title', '')
# Use English title if available, otherwise original
title = article.get('title_en') if article.get('title_en') else article.get('title', '')
summary = article.get('summary') or ''
content_snippet = article.get('content', '')[:1000]

6
news_crawler/crawler_service.py
View File

@@ -340,7 +340,11 @@ def crawl_rss_feed(feed_url, feed_name, feed_category='general', max_articles=10
if not feed.entries:
print(f" ⚠ No entries found in feed")
return 0
return {
'crawled': 0,
'summarized': 0,
'failed_summaries': 0
}
crawled_count = 0
summarized_count = 0

6
news_crawler/scheduled_crawler.py
View File

@@ -37,12 +37,12 @@ def main():
"""Main scheduler loop"""
print("🤖 Munich News Crawler Scheduler")
print("="*60)
print("Schedule: Daily at 6:00 AM Berlin time")
print("Schedule: Every 3 hours")
print("Timezone: Europe/Berlin (CET/CEST)")
print("="*60)
# Schedule the crawler to run at 6 AM Berlin time
schedule.every().day.at("06:00").do(run_crawler)
# Schedule the crawler to run every 3 hours
schedule.every(3).hours.do(run_crawler)
# Show next run time
berlin_time = datetime.now(BERLIN_TZ)