update recommender and news_fetcher

backend/recommender.py

@@ -1,3 +1,4 @@
+from typing import List, Dict, Optional
 from .embeddings import get_embeddings, get_query_embedding, rerank_results
 from .vector_store import VectorDB
 import groq
@@ -10,6 +11,56 @@ groq_client = groq.Groq(api_key=Config.GROQ_API_KEY)
 vector_db = VectorDB()
 
 
+class NewsRecommender:
+    """News recommendation system using vector similarity search"""
+
+    def __init__(self, vector_db: VectorDB):
+        self.vector_db = vector_db
+
+    def recommend_by_text(self, text_description: str, top_n: int = 3) -> List[Dict]:
+        """
+        Recommend articles based on text description
+
+        Args:
+            text_description: Text description to find similar articles for
+            top_n: Number of recommendations to return
+
+        Returns:
+            List of recommended articles
+        """
+        query_embedding = get_query_embedding(text_description)
+        if not query_embedding:
+            return []
+
+        # Search for similar articles
+        similar_articles = self.vector_db.search(query_embedding, k=top_n)
+
+        # Re-rank results for better relevance
+        if similar_articles:
+            documents = [f"{art['title']} {art['content']}" for
+                         art in similar_articles]
+            reranked = rerank_results(text_description, documents)
+
+            if reranked:
+                # Reorder recommendations based on reranking
+                reordered = []
+                for result in reranked:
+                    if result.index < len(similar_articles):
+                        reordered.append(similar_articles[result.index])
+                return reordered
+
+        return similar_articles
+
+    def get_personalized_recommendations(self, user_interests: str, top_n:
+                                         int = 5) -> List[Dict]:
+        """Get personalized recommendations based on user interests"""
+        return self.recommend_by_text(user_interests, top_n)
+
+
+# Initialize recommender instance
+news_recommender = NewsRecommender(vector_db)
+
+
 def process_articles_for_vector_db(articles):
     """Process articles and add to vector database"""
     if not articles:
@@ -35,18 +86,14 @@ def recommend_similar(article_id, top_n=3):
 
     # Get embedding for the article
     article_text = f"{article['title']} {article['content']}"
-    query_embedding = get_query_embedding(article_text)
 
-    if not query_embedding:
-        return []
-
-    # Search for similar articles
-    similar_articles = vector_db.search(query_embedding, k=top_n + 1)
+    # Use the new recommender with text description
+    recommendations = news_recommender.recommend_by_text(article_text, top_n + 1)
 
     # Filter out the original article
-    recommendations = [art for art in similar_articles if art.get('slug') != article_id]
+    filtered_recommendations = [art for art in recommendations if art.get('slug') != article_id]
 
-    return recommendations[:top_n]
+    return filtered_recommendations[:top_n]
 
 
 def analyze_article_with_groq(article_text):
@@ -57,7 +104,8 @@ def analyze_article_with_groq(article_text):
             messages=[
                 {
                     "role": "system",
-                    "content": "You are an AI news analyst. Provide insights, key points, and sentiment analysis for the given article."
+                    "content": "You are an AI news analyst. Provide insights, "
+                    "key points, and sentiment analysis for the given article."
                 },
                 {
                     "role": "user",
@@ -75,23 +123,5 @@ def analyze_article_with_groq(article_text):
 
 def get_personalized_recommendations(user_interests, top_n=5):
     """Get personalized recommendations based on user interests"""
-    query_embedding = get_query_embedding(user_interests)
-    if not query_embedding:
-        return []
-
-    recommendations = vector_db.search(query_embedding, k=top_n)
-
-    # Re-rank results for better relevance
-    if recommendations:
-        documents = [f"{art['title']} {art['content']}" for art in recommendations]
-        reranked = rerank_results(user_interests, documents)
-
-        if reranked:
-            # Reorder recommendations based on reranking
-            reordered = []
-            for result in reranked:
-                if result.index < len(recommendations):
-                    reordered.append(recommendations[result.index])
-            return reordered
-
-    return recommendations
+    return news_recommender.get_personalized_recommendations(user_interests,
+                                                             top_n)