Update app.py

app.py

@@ -12,28 +12,19 @@ app = Flask(__name__)
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-@app.route('/')
-def loading():
-    # Start loading feeds in a subprocess
-    subprocess.Popen(["python", "rss_processor.py", "load_feeds"])
-    return render_template("loading.html")
-
-@app.route('/check_feeds', methods=['GET'])
-def check_feeds():
-    try:
-        # Check if vector DB has documents
-        docs = vector_db.similarity_search("news", k=1)
-        if docs:
-            logger.info("Feeds loaded successfully in vector DB")
-            return jsonify({"status": "loaded"})
-        return jsonify({"status": "loading"}), 202
-    except Exception as e:
-        logger.error(f"Error checking feeds: {e}")
-        return jsonify({"status": "error", "message": str(e)}), 500
+def load_feeds_in_background():
+    logger.info("Starting to fetch and process RSS feeds in background")
+    start_time = time.time()
+    articles = fetch_rss_feeds()
+    logger.info(f"Fetched {len(articles)} articles")
+    process_and_store_articles(articles)
+    logger.info("Articles processed and stored")
+    end_time = time.time()
+    logger.info(f"RSS feed loading took {end_time - start_time:.2f} seconds")
 
-@app.route('/index', methods=['GET'])
+@app.route('/')
 def index():
-    # Show existing articles while new feeds load in background
+    # Show existing articles immediately
     stored_docs = vector_db.similarity_search("news", k=1000)  # Show all available articles
     # Use a set to ensure unique articles by title, link, and description hash
     unique_articles = {}
@@ -55,29 +46,8 @@ def index():
     enriched_articles = list(unique_articles.values())
     logger.info(f"Enriched {len(enriched_articles)} unique articles for display")
 
-    if request.method == 'POST' and 'search' in request.form:
-        query = request.form.get('search')
-        if query:
-            logger.info(f"Processing search query: {query}")
-            results = vector_db.similarity_search(query, k=10)
-            unique_search_articles = {}
-            for doc in results:
-                title = doc.metadata["title"]
-                link = doc.metadata["link"]
-                description = doc.metadata["original_description"]
-                desc_hash = hashlib.md5(description.encode()).hexdigest()[:10]
-                key = f"{title}|{link}|{desc_hash}"
-                if key not in unique_search_articles:
-                    unique_search_articles[key] = {
-                        "title": title,
-                        "link": link,
-                        "description": description,
-                        "category": doc.metadata["category"],
-                        "published": doc.metadata["published"],
-                        "image": doc.metadata.get("image", "svg"),
-                    }
-            enriched_articles = list(unique_search_articles.values())
-            logger.info(f"Search returned {len(enriched_articles)} unique results")
+    # Start loading new feeds in the background
+    subprocess.Popen(["python", "rss_processor.py", "load_feeds"])
 
     categorized_articles = {}
     for article in enriched_articles:
@@ -88,5 +58,18 @@ def index():
 
     return render_template("index.html", categorized_articles=categorized_articles, loading_new_feeds=True)
 
+@app.route('/check_feeds', methods=['GET'])
+def check_feeds():
+    try:
+        # Check if vector DB has new documents (simplified check)
+        docs = vector_db.similarity_search("news", k=1)
+        if docs:
+            logger.info("Feeds loaded successfully in vector DB")
+            return jsonify({"status": "loaded"})
+        return jsonify({"status": "loading"}), 202
+    except Exception as e:
+        logger.error(f"Error checking feeds: {e}")
+        return jsonify({"status": "error", "message": str(e)}), 500
+
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)