once more

components/generators/daily_feed.py

@@ -7,34 +7,34 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
 
 import redis
 from typing import List, Dict
-from llama_index.core.settings import Settings
 from llama_index.core import VectorStoreIndex
 from llama_index.core.query_engine import RetrieverQueryEngine
 from llama_index.core.schema import Document
-from components.indexers.news_indexer import load_news_index
+from llama_index.core.settings import Settings
 
+# ✅ Disable OpenAI LLM fallback
 Settings.llm = None
 
-# Load environment variables
+# 🔐 Load environment variables
 REDIS_URL = os.environ.get("UPSTASH_REDIS_URL", "redis://localhost:6379")
 REDIS_KEY = os.environ.get("UPSTASH_REDIS_TOKEN")
-MISTRAL_URL = os.environ.get("MISTRAL_URL")  # Inference endpoint URL
-HF_TOKEN = os.environ.get("HF_TOKEN")        # Hugging Face endpoint token
+MISTRAL_URL = os.environ.get("MISTRAL_URL")       # Mistral inference endpoint
+HF_TOKEN = os.environ.get("HF_TOKEN")             # Hugging Face access token
 
-# Connect to Redis
+# ✅ Connect to Redis
 redis_client = redis.Redis.from_url(REDIS_URL, decode_responses=True)
 
-# Topics to query
+# 🔍 Topics to query and summarize
 TOPICS = ["India news", "World news", "Tech news", "Finance news", "Sports news"]
 
-# Prompt to summarize topic
+# 🧠 Prompt builder for summarization
 def build_prompt(content: str, topic: str) -> str:
     return (
         f"You are a news summarizer. Summarize the following content in 25-30 words. "
         f"Make it engaging and informative. Include appropriate emojis. Topic: {topic}\n\n{content}"
     )
 
-# Call Mistral via inference endpoint
+# 🔗 Call Mistral API
 def call_mistral(prompt: str) -> str:
     headers = {
         "Authorization": f"Bearer {HF_TOKEN}",
@@ -53,7 +53,7 @@ def call_mistral(prompt: str) -> str:
         print(f"⚠️ Mistral error: {e}")
         return None
 
-# Generate summary for topic using Mistral
+# ✂️ Summarize a list of documents into a short news feed
 def summarize_topic(docs: List[str], topic: str) -> List[Dict]:
     feed = []
     for doc in docs[:5]:
@@ -67,10 +67,11 @@ def summarize_topic(docs: List[str], topic: str) -> List[Dict]:
             })
     return feed
 
-# Main generation pipeline
+# 🚀 Main pipeline
 def generate_and_cache_daily_feed(documents: List[Document]):
     index = VectorStoreIndex.from_documents(documents)
-    query_engine = RetrieverQueryEngine.from_args(index)
+    retriever = index.as_retriever()
+    query_engine = RetrieverQueryEngine(retriever=retriever)
 
     final_feed = []
     for topic in TOPICS:
@@ -84,13 +85,12 @@ def generate_and_cache_daily_feed(documents: List[Document]):
             "feed": topic_feed
         })
 
-    # Cache to Redis
+    # 💾 Cache to Redis
     redis_client.set(REDIS_KEY, json.dumps(final_feed, ensure_ascii=False))
     print(f"✅ Cached daily feed under key '{REDIS_KEY}'")
     return final_feed
 
-# Redis fetch for API
-
+# 🧪 Redis fetch (for use in APIs)
 def get_cached_daily_feed():
     cached = redis_client.get(REDIS_KEY)
     return json.loads(cached) if cached else []