feat: Implement complete RSS news fetching system with multi-source support

backend/config.py

@@ -0,0 +1,46 @@
+"""Configuration settings for DS Task AI News"""
+import os
+from typing import List
+from pydantic_settings import BaseSettings
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class Settings(BaseSettings):
+    # API Keys
+    cohere_api_key: str = os.getenv("COHERE_API_KEY", "")
+    groq_api_key: str = os.getenv("GROQ_API_KEY", "")
+    
+    # Vector Database
+    vector_db_type: str = os.getenv("VECTOR_DB_TYPE", "faiss")
+    vector_dimension: int = int(os.getenv("VECTOR_DIMENSION", "384"))
+    
+    # RSS Feeds
+    @property
+    def rss_feeds(self) -> List[str]:
+        feeds_str = os.getenv(
+            "RSS_FEEDS",
+            "https://feeds.bbci.co.uk/news/technology/rss.xml,"
+            "https://techcrunch.com/feed/,"
+            "https://www.wired.com/feed/rss"
+        )
+        return [feed.strip() for feed in feeds_str.split(",") if feed.strip()]
+    
+    # Server Settings
+    host: str = os.getenv("HOST", "0.0.0.0")
+    port: int = int(os.getenv("PORT", "8000"))
+    debug: bool = os.getenv("DEBUG", "true").lower() == "true"
+    
+    # Data Storage
+    raw_news_dir: str = os.getenv("RAW_NEWS_DIR", "data/raw_news")
+    processed_news_dir: str = os.getenv("PROCESSED_NEWS_DIR", "data/processed_news")
+    vector_index_path: str = os.getenv("VECTOR_INDEX_PATH", "data/news_vectors.faiss")
+    
+    # Embedding Model
+    embedding_model: str = "sentence-transformers/all-MiniLM-L6-v2"
+    
+    # News Processing
+    max_articles_per_feed: int = 50
+    similarity_threshold: float = 0.7
+
+settings = Settings()