Update app.py

app.py

@@ -1,8 +1,9 @@
 import os
 import threading
-from flask import Flask, render_template, request, jsonify
+from flask import Flask, render_template, request, jsonify, Response
 from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db
 import logging
+import json
 
 app = Flask(__name__)
 
@@ -22,9 +23,14 @@ def load_feeds_in_background():
         process_and_store_articles(articles)
         logger.info("Background feed processing complete")
         loading_complete = True
+        # Notify frontend of new data (simulated via SSE for simplicity)
+        def event_stream():
+            yield f"data: {json.dumps({'status': 'updated'})}\n\n"
+        app.response_class = Response
+        return Response(event_stream(), mimetype="text/event-stream")
     except Exception as e:
         logger.error(f"Error in background feed loading: {e}")
-        loading_complete = True  # Mark as complete even on error to avoid infinite polling
+        loading_complete = True
 
 @app.route('/')
 def index():
@@ -35,13 +41,13 @@ def index():
     threading.Thread(target=load_feeds_in_background, daemon=True).start()
 
     try:
-        # Retrieve the 10 most recent articles from Chroma DB
+        # Retrieve all articles from Chroma DB
         all_docs = vector_db.get(include=['documents', 'metadatas'])
         if not all_docs.get('metadatas'):
             logger.info("No articles in DB yet")
             return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
 
-        # Sort by 'published' date (if available) and take top 10
+        # Process and categorize articles, getting 10 most recent per category
         enriched_articles = []
         seen_keys = set()
         for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
@@ -61,20 +67,25 @@ def index():
                     "image": meta.get("image", "svg"),
                 })
 
-        # Sort by published date (assuming it's in a parseable format; fallback to order if not)
+        # Sort by published date (assuming ISO format or comparable string)
         enriched_articles.sort(key=lambda x: x["published"], reverse=True)
-        recent_articles = enriched_articles[:10]
-        logger.info(f"Displaying {len(recent_articles)} recent articles")
 
-        # Categorize recent articles
+        # Group by category and limit to 10 most recent per category
         categorized_articles = {}
-        for article in recent_articles:
+        for article in enriched_articles:
             cat = article["category"]
-            categorized_articles.setdefault(cat, []).append(article)
-
+            if cat not in categorized_articles:
+                categorized_articles[cat] = []
+            categorized_articles[cat].append(article)
+        
+        # Limit to 10 most recent per category
+        for cat in categorized_articles:
+            categorized_articles[cat] = sorted(categorized_articles[cat], key=lambda x: x["published"], reverse=True)[:10]
+
+        logger.info(f"Displaying articles: {sum(len(articles) for articles in categorized_articles.values())} total")
         return render_template("index.html", categorized_articles=categorized_articles, has_articles=True, loading=True)
     except Exception as e:
-        logger.error(f"Error retrieving recent articles: {e}")
+        logger.error(f"Error retrieving articles: {e}")
         return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
 
 @app.route('/search', methods=['POST'])
@@ -114,7 +125,7 @@ def search():
         logger.error(f"Search error: {e}")
         return render_template("index.html", categorized_articles={}, has_articles=False, loading=False)
 
-@app.route('/check_loading', methods=['GET'])
+@app.route('/check_loading')
 def check_loading():
     global loading_complete
     if loading_complete: