Update app.py

app.py

@@ -1,4 +1,5 @@
 import os
+import threading
 from flask import Flask, render_template, request, jsonify
 from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db
 import logging
@@ -9,22 +10,38 @@ app = Flask(__name__)
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-@app.route('/')
-def index():
+# Global flag to track background loading
+loading_complete = False
+
+def load_feeds_in_background():
+    global loading_complete
     try:
-        # Fetch and store articles synchronously on first load
+        logger.info("Starting background RSS feed fetch")
         articles = fetch_rss_feeds()
         logger.info(f"Fetched {len(articles)} articles")
         process_and_store_articles(articles)
-        logger.info("Articles processed and stored")
+        logger.info("Background feed processing complete")
+        loading_complete = True
+    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
+
+@app.route('/')
+def index():
+    global loading_complete
+    loading_complete = False  # Reset on each load
+
+    # Start background feed loading
+    threading.Thread(target=load_feeds_in_background, daemon=True).start()
 
-        # Retrieve all articles from Chroma DB
+    try:
+        # Retrieve the 10 most recent articles from Chroma DB
         all_docs = vector_db.get(include=['documents', 'metadatas'])
         if not all_docs.get('metadatas'):
-            logger.warning("No articles in DB yet")
-            return render_template("index.html", categorized_articles={}, has_articles=False)
+            logger.info("No articles in DB yet")
+            return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
 
-        # Process retrieved documents
+        # Sort by 'published' date (if available) and take top 10
         enriched_articles = []
         seen_keys = set()
         for doc, meta in zip(all_docs['documents'], all_docs['metadatas']):
@@ -32,36 +49,39 @@ def index():
                 continue
             title = meta.get("title", "No Title")
             link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
             key = f"{title}|{link}"
             if key not in seen_keys:
                 seen_keys.add(key)
                 enriched_articles.append({
                     "title": title,
                     "link": link,
-                    "description": description,
+                    "description": meta.get("original_description", "No Description"),
                     "category": meta.get("category", "Uncategorized"),
                     "published": meta.get("published", "Unknown Date"),
                     "image": meta.get("image", "svg"),
                 })
-        logger.info(f"Displaying {len(enriched_articles)} unique articles")
 
-        # Categorize articles
+        # Sort by published date (assuming it's in a parseable format; fallback to order if not)
+        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
         categorized_articles = {}
-        for article in enriched_articles:
+        for article in recent_articles:
             cat = article["category"]
             categorized_articles.setdefault(cat, []).append(article)
 
-        return render_template("index.html", categorized_articles=categorized_articles, has_articles=True)
+        return render_template("index.html", categorized_articles=categorized_articles, has_articles=True, loading=True)
     except Exception as e:
-        logger.error(f"Error in index: {e}")
-        return render_template("index.html", categorized_articles={}, has_articles=False)
+        logger.error(f"Error retrieving recent articles: {e}")
+        return render_template("index.html", categorized_articles={}, has_articles=False, loading=True)
 
 @app.route('/search', methods=['POST'])
 def search():
     query = request.form.get('search')
     if not query:
-        return render_template("index.html", categorized_articles={}, has_articles=False)
+        return render_template("index.html", categorized_articles={}, has_articles=False, loading=False)
 
     try:
         logger.info(f"Searching for: {query}")
@@ -72,14 +92,13 @@ def search():
             meta = doc.metadata
             title = meta.get("title", "No Title")
             link = meta.get("link", "")
-            description = meta.get("original_description", "No Description")
             key = f"{title}|{link}"
             if key not in seen_keys:
                 seen_keys.add(key)
                 enriched_articles.append({
                     "title": title,
                     "link": link,
-                    "description": description,
+                    "description": meta.get("original_description", "No Description"),
                     "category": meta.get("category", "Uncategorized"),
                     "published": meta.get("published", "Unknown Date"),
                     "image": meta.get("image", "svg"),
@@ -90,10 +109,17 @@ def search():
             cat = article["category"]
             categorized_articles.setdefault(cat, []).append(article)
 
-        return render_template("index.html", categorized_articles=categorized_articles, has_articles=bool(enriched_articles))
+        return render_template("index.html", categorized_articles=categorized_articles, has_articles=bool(enriched_articles), loading=False)
     except Exception as e:
         logger.error(f"Search error: {e}")
-        return render_template("index.html", categorized_articles={}, has_articles=False)
+        return render_template("index.html", categorized_articles={}, has_articles=False, loading=False)
+
+@app.route('/check_loading', methods=['GET'])
+def check_loading():
+    global loading_complete
+    if loading_complete:
+        return jsonify({"status": "complete"})
+    return jsonify({"status": "loading"}), 202
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)