Update rss_processor.py

rss_processor.py

@@ -13,13 +13,15 @@ logger = logging.getLogger(__name__)
 
 # Hugging Face setup
 HF_API_TOKEN = os.getenv("DEMO_HF_API_TOKEN", "YOUR_HF_API_TOKEN")
-HF_MODEL = "Qwen/Qwen2.5-Coder-32B-Instruct"
+HF_MODEL = "Qwen/Qwen2.5-Coder-32B-Instruct"  # Updated to your specified model
 REPO_ID = "broadfield-dev/news-rag-db"
 LOCAL_DB_DIR = "chroma_db"
 
+# Explicitly login to Hugging Face Hub
 login(token=HF_API_TOKEN)
 client = InferenceClient(model=HF_MODEL, token=HF_API_TOKEN)
 
+# RSS feeds
 RSS_FEEDS = [
     "https://www.sciencedaily.com/rss/top/science.xml",
     "https://www.horoscope.com/us/horoscopes/general/rss/horoscope-rss.aspx",
@@ -62,6 +64,7 @@ RSS_FEEDS = [
     "https://www.atlasobscura.com/feeds/latest"
 ]
 
+# Embedding model and vector DB
 embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 vector_db = Chroma(persist_directory=LOCAL_DB_DIR, embedding_function=embedding_model)
 hf_api = HfApi()
@@ -122,14 +125,13 @@ def categorize_article(text):
         logger.error(f"Error categorizing article: {e}")
         return "Neutral"
 
-def process_and_store_articles(articles, summarize=False):
+def process_and_store_articles(articles):
     documents = []
     for article in articles:
         try:
-            summary = summarize_article(article["description"]) if summarize else article["description"]
-            sentiment = categorize_article(article["description"])
+            sentiment = categorize_article(article["description"])  # Still categorize for initial display
             doc = Document(
-                page_content=summary,
+                page_content=article["description"],  # Store original description without summarization
                 metadata={
                     "title": article["title"],
                     "link": article["link"],