Update app.py

app.py

@@ -4,6 +4,7 @@ from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db
 import logging
 import time
 from threading import Thread
+import hashlib
 
 app = Flask(__name__)
 
@@ -32,9 +33,10 @@ def loading():
 @app.route('/check_feeds', methods=['GET'])
 def check_feeds():
     try:
-        # Check if vector DB has documents (simplified check)
+        # 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:
@@ -43,28 +45,20 @@ def check_feeds():
 
 @app.route('/index', methods=['GET'])
 def index():
-    # Poll until feeds are loaded
-    while True:
-        response = check_feeds()
-        if response.status_code == 200 and response.get_json()["status"] == "loaded":
-            break
-        time.sleep(1)  # Check every second
-
-    stored_docs = vector_db.similarity_search("news", k=1000)  # Increased k for all unique articles
+    stored_docs = vector_db.similarity_search("news", k=1000)  # Ensure all unique articles
     # Use a set to ensure unique articles by title, link, and description hash
     unique_articles = {}
     for doc in stored_docs:
-        import hashlib
         title = doc.metadata["title"]
         link = doc.metadata["link"]
-        desc = doc.metadata["original_description"]
-        desc_hash = hashlib.md5(desc.encode()).hexdigest()[:10]  # Short hash for uniqueness
+        description = doc.metadata["original_description"]
+        desc_hash = hashlib.md5(description.encode()).hexdigest()[:10]
         key = f"{title}|{link}|{desc_hash}"
         if key not in unique_articles:
             unique_articles[key] = {
                 "title": title,
                 "link": link,
-                "description": doc.metadata["original_description"],
+                "description": description,
                 "category": doc.metadata["category"],
                 "published": doc.metadata["published"],
                 "image": doc.metadata.get("image", "svg"),
@@ -81,14 +75,14 @@ def index():
             for doc in results:
                 title = doc.metadata["title"]
                 link = doc.metadata["link"]
-                desc = doc.metadata["original_description"]
-                desc_hash = hashlib.md5(desc.encode()).hexdigest()[:10]
+                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": doc.metadata["original_description"],
+                        "description": description,
                         "category": doc.metadata["category"],
                         "published": doc.metadata["published"],
                         "image": doc.metadata.get("image", "svg"),